Dissertations / Theses on the topic 'Dynamic discrete choice experiments'

This thesis investigates the problem of strategic bias in discrete choice experiments using three approaches: simulations, a laboratory experiment, and a field experiment. Carson et al. (2007) state that choice experiments must be seen as consequential by respondents in order to provide useful information about preferences. To meet this requirement, surveys must exhibit two characteristics. First, the survey must be seen as influencing the provision of the good/service and second, the respondent must care about that provision outcome. However, the notion that the survey must be consequential, may also induce respondents to misrepresent their preferences in order to influence the decision making process. This is known as strategic bias. Using simulations, laboratory experiments and field studies, this thesis will investigate strategic bias in discrete choice experiments. To do so, we must assume that the discrete choice experiment will be used to influence a provisioning decision. Strategic behaviour is conceptualised as changes in choice behaviour that occurs when respondents have information on the relative likelihood of the provision outcomes. This information causes changes in choice strategies. In Chapter 1 we create a simulated environment that replicates when respondents may have incentive to bias their choice strategies. We explore the ramifications of biased choices through simulations. In Chapter 2 we replicate that environment in an induced value laboratory experiment. We present respondents with three possible `provision' outcomes, each of which was defined in terms of levels of arbitrary attributes. Each possible provision outcome was associated with a monetary payout to the respondent, therefore we know a respondents preference ordering over the possible outcomes. The monetary payouts varied such that there was a clear ranking between possible outcomes, such that respondents had a first, second and worst provision outcome. Respondents then completed a discrete choice experiment (DCE) that would decide which provision outcome is paid out. A respondent's payout was determined by which of the competing provision outcomes had the highest choice probability, based on their individual choice behaviour. As this was an unlabelled choice experiment, participants had to use choice strategies based on attributes in order to influence the provision outcome they hoped would get paid out. To introduce strategic bias, respondents were given information on the likelihood of the provision contenders being implemented. This information would affect which provision outcome would be chosen and hence paid out. In this respect, a respondent has incentive to act strategically if they believe (i) their first best outcome will lose in the final provision decision; (ii) their worst outcome is most likely to be paid out; and (iii) their choices can influence the provision to deliver the second best outcome. Strategic respondents are therefore those who chose to target their second best outcome to avoid worst outcome, which respondents are told is the most likely. We find approximately 27% of respondents exhibit strategic behaviour in the laboratory choice experiment. In Chapter 3 we implement the approach in the field. We administered a choice experiment about tidal energy development in Puget Sound, Washington. Local opposition to tidal energy has been strong in the past, with no project ever coming to fruition. As a result, we envision respondents to have strong sentiments towards the location of tidal energy development and potentially have incentives to behave strategically when location is a factor in their decision making process. We presented respondents with three possible site locations for tidal energy development in Puget Sound. Respondents can use the choice experiment as a means to reveal which site location they prefer (if any). As this was an unlabelled experiment, respondents must use choice strategies based on the attributes of tidal development in order to reveal preference for location. In order to identify strategic behaviour, rather than simply differences in preferences, half way through the DCE, we provide respondents with additional information on the likelihood of each of the tidal energy sites being chosen. Respondents whose first best location is revealed as the site least likely to be chosen, may seek to secure their second best location. Strategic bias is when respondents are trying to push preference away from their worst location site, when the set of provision outcomes has gone from three to two possible sites. Despite the complexity of the task, there is evidence of behavioural changes when the final set of possible locations changes. We find that 25% of respondents exhibit signs of strategic behaviour. These respondents are more likely to 1) believe their survey responses will affect future policy; and, 2) prefer the site which was revealed to be the unlikely site location and thus have strong motive to push development away from their worst location, and towards a second best site.

Um Strommärkte so zu konzipieren damit sie sowohl zur Verringerung der Nutzung fossiler Brennstoffe als auch zur Deckung des steigenden Energiebedarfes beitragen, ist Wissen über die Präferenzen der Konsumenten notwendig. Die vorliegende kumulative Dissertation untersucht Präferenzen für Elektrizitätsattribute von privaten Haushalten und trägt zu einem tieferen Verständnis dieser in unterschiedlichen Kontextsituationen bei. Der erste Artikel betrachtet statistische Methoden um die zwei am häufigsten angewandten Modelle – das Random Parameter Logit und das Latent Class Logit Modell – zu vergleichen. Der Artikel trägt dazu bei, den Prozess der Modellwahl zu verbessern und für die angewandte Forschung im Energiebereich anzupassen. Basierend auf den empirischen Ergebnissen des ersten Artikels untersucht der zweite Artikel die Präferenzen von privaten Haushalten in Hyderabad, Indien mit besonderem Fokus auf die physische Qualität der Energieversorgung. Die Ergebnisse deuten auf eine geringe Zahlungsbereitschaft der Konsumenten hin. Jedoch unterscheiden sich die Präferenzen der Haushalte. Die Artikel 3 und 4 basieren auf Datenerhebungen in Deutschland. Im dritten Artikel werden die Präferenzen privater Haushalte hinsichtlich der Organisationsform von Stromanbietern untersucht. Die Ergebnisse zeigen, dass die Kunden bereit sind mehr zu zahlen, wenn die Stromversorgung von Genossenschaften oder Stadtwerken übernommen wird. Der vierte Artikel betrachtet die Erfolgsfaktoren von Energiegenossenschaften in Deutschland. Die Ergebnisse zeigen, dass die Governance des Stromanbieters die Zahlungsbereitschaft für Strom beeinflussen. Insbesondere Genossenschaften werden den großen Privatunternehmen und Aktiengesellschaften vorgezogen.
In order to design electricity markets to simultaneously reduce the share of fossil fuels in energy production and meet the increasing demand for electricity, knowledge on consumer preferences is necessary. The goal of this cumulative dissertation is to contribute to the understanding of preferences of private households for electricity supply attributes in different contexts. In Paper 1 I review statistical methods to compare two frequently applied models, the random parameters logit and the latent class logit. The methods presented here can be readily used by other researchers and practitioners to better understand model performance which ultimately contributes to improving model choice in applied energy research. Based on the empirical findings of Paper 1, Paper 2 identifies preferences of private households in Hyderabad in India for electricity supply quality. The results indicate that willingness to pay for improvements are, on average, rather low. However, the preferences strongly vary between subjects. Papers 3 and 4 investigate preferences of German private households. In \textbf{Paper 3}, the respondents stated their preferences for the organization of the electricity distribution company under different renewable energy scenarios. It turned out that most people are willing to pay more for electricity supplied by municipally-owned companies and cooperatives. This additional willingness to pay increases disproportionally when the share of renewable energy is high. The paper identifies non-profit orientated distribution companies as potential drivers of the energy transition. Paper 4 investigates the determinants for the success of energy cooperatives in Germany. The results indicate that the governance of distribution companies impacts the choices of private households for electricity supply contracts. Especially, people preferred cooperative-like governance attributes.

Introduction. In the United Kingdom (UK), recent policy developments include an increased role for the community phannacist in the management of drug therapy in primary care. When embarking on such service redesign, it is recognised that. patient preferences must be considered. The quality adjusted life years (QALY) approach is the common economic approach ~o 1'. considering preferences in economic evaluations. However, it is limited to consideration of - ·only health outcomes. Other approaches widely used in health services research, such as · satisfaction surveys, do not find a place in the economic eval~tion framework because they' do not incorporate any notion of opportunity cost or strength of preference. Another measure of benefit is required to go beyond the scope of the QALY and pla~e a value on non-health outcomes (e.g. information, reassurance, regret, anxiety) and process attributes (e.g. waiting · time at the ~ealth care centre, staff involyed, waiting time for test res!llts), as well as estimate trade-offs between such aspects ofcare. . . One technique adopted over the past decade in health economics to go beyond health outcome is Discrete Choice Experiment (DCEs). This is an attribute-based technique for eliciting preferenc~s. ~en a price proxy is included, willingness to pay (WTP), a monetary measure of benefit, can be estimated for both marginal changes in service characteristics and changes in the overall service. Whilst the last 15 years has seen an increased uSe of DeEs in health care, there has been limited application in pharmacy. The Community Pharmacy Medicines Management Project (Medman study) constituted the perfect platfonn for this PhD thesis. It was a large, randomised, controlled trial (ReT) to evaluate the introduction of a pharmacy-led medicines management service for patients with 'cQronary- heart -disease-(CHD): It- allowed comparison of results between traditional outcome measures (such as clinical outcomes, QALYs and satisfaction) and a broader measure of benefit llsing the DCE. As well as considering the relevance of DCE ·to policy making, methodological issues in their development were also considered. Aim and ·objectives. The aims of this PhD programme are: to consider the implications of ..taking a .broader patient centred approach (which goes beyond he~th outcomes) to ev~luating ' . a proposed policy change in community pharmacy; and to develop' and apply the DCE '. ' ~ . methodology to pharmacy. The specific objectives ofthe thesis are: • to conduct a review ofthe literature relating to benefit evaluation and its application to the economic evaluation framework in pharmacy; ' • to apply traditional benefit evaluation approaches, including' clinical outcomes, - . QALYs and a satisfaction survey to a' pharmacy setting;. jI ' i .J I' • to develop an alternative approach, DCEs, to value benefits, looking at different design appr?ache~ \\,~en defining multiple choice· DCEs and addressing welfare . estimation issJles when.analysing the data; • to apply DCE to phaimacy within the Medman .study and to compare the results with _these ofclinical and QALY approaches within an economic evaluation framework; • to consider the impact on policy when different approaches are applied. Methods. A fully comprehensive review of the health care literature was conducted to . identify possible methods for valuing community pharmacy-based services and their integration into economic evaluation.

The aim of this thesis is to broaden work in the area of discrete choice experiments (DCEs) in health economics by focusing on the development of some key areas which have to date received relatively little attention.  By firstly outlining the background, theory and context of DCEs in health economics, areas are identified that deserve further exploration due to their particular relevance to health economics.  Specific contributions of the thesis are in three main areas:  modelling the participation decision in DCEs in health care; the use of strength of preference choice modelling approaches; and the applicability of a new approach, best attribute scaling (BSc), to health economics.  The contributions of the thesis are to the design, analysis and interpretation of DCE studies. The seven key recommendations for the conduct of DCE surveys arising from this thesis have been made on the basis of the best available knowledge gleaned from empirical analysis carried out.  They are as follows:  (1) Researchers conducting DCE studies in health care should carefully consider the participation decision when designing and analysing a DCE and where appropriate pay particular attention to describing the opt-out or status quo option as realistically as possible (2) When incorporating status quo or opt-out scenarios within a DCE design researchers should check that the statistical properties of the resulting design are still valid (3) Strength of preference models appear to improve the statistical efficiency of models and produce more accurate estimates of welfare however this may come at the expense of the predictive ability of the model and consistency rates (4) Where possible DCE surveys should provide respondents with the most realistic range of preference ‘capture’ mechanisms as possible, this includes providing opting out, status quo and indifference options where appropriate.  (5) As shown in the environmental economics literature strength of preference models facilitates the elicitation of preferences in health economics (6)  BSc methods can be used to predict choices in health care preference surveys (7) BSc has the ability to separate scale and weight in choice experiments and hence place all attribute levels on a common scale, unlike traditional choice experiments however future work with larger samples should clarify this result.

This thesis concerns about using discrete choice experiment for valuing health state utilities within the QALY framework. Therefore, it discusses the main issues with generating choice design for valuing health state utilities, and then presents an efficient methodology to construct an optimal choice design for valuing health state utilities using the most recent theoretical development in Bayesian optimal design literature. The use of the new design algorithm and the effect of the prior in the Bayesian design are demonstrated in this thesis by constructing Bayesian choice design for asthma quality of life classification system (AQL-5D).

Discrete choice experiments (DCEs) are a stated preference valuation method. As a ubiquitous component of healthcare delivery, risk is increasingly used as an attribute in DCEs. Risk is a complex concept that is open to misinterpretation; potentially undermining the robustness of DCEs as a valuation method. This thesis employed quantitative, qualitative and eye-tracking methods to understand if and how risk communication formats affected individuals’ choices when completing a DCE and the valuations derived. This thesis used a case study focussing on the elicitation of women’s preferences for a national breast screening programme. Breast screening was chosen because of its relevance to primary care and potential contribution to the ongoing debate about the benefits and harms of mammograms. A DCE containing three attributes (probability of detecting a cancer; risk of unnecessary follow-up; and cost of screening) was designed. Women were randomised to one of two risk communication formats: i) percentages only; or ii) icon arrays and percentages (identified from a structured review of risk communication literature in health).Traditional quantitative analysis of the discrete choices made by 1,000 women recruited via an internet panel revealed the risk communication format made no difference in terms of either preferences or the consistency of choices. However, latent class analysis indicated that women’s preferences for breast screening were highly heterogeneous; with some women acquiring large non-health benefits from screening, regardless of the risks, and others expressing complete intolerance for unnecessary follow-ups, regardless of the benefits. The think-aloud method, identified as a potential method from a systematic review of qualitative research alongside DCEs, was used to reveal more about DCE respondents’ decision-making. Nineteen face-to-face cognitive interviews identified that respondents felt more engaged with the task when risk was presented with an additional icon array. Eye-tracking methods were used to understand respondents’ choice making behaviour and attention to attributes. The method was successfully used alongside a DCE and provided valid data. The results of the eye-tracking study found attributes were visually attended to by respondents most of the time. For researchers seeking to use DCEs for eliciting individuals’ preferences for benefit-risk trade-offs, respondents were more receptive to risk communicated via an icon array suggesting this format is preferable. Policy-makers should acknowledge preference heterogeneity, and its drivers, in their appraisal of the benefits of breast screening programmes. Future research is required to test alternative risk communication formats and explore the robustness of eye-tracking and qualitative research methods alongside DCEs.

Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 37-38).
Incentivization is a powerful way to get independent agents to make choices that drive a system to a desired optimum. Simply offering compensation for making a certain choice is enough to change the behavior of some people. If you incentivize the right choices, you can get closer to your desired choice-dependent goal. Ways to optimize these choices in an environment with many choices and many users is essential for achieving goals for the least cost. I examine how a model that is aware of the utility function of each choice and for each user in a system can optimally allocate incentives in real time while considering opportunity cost, personalized incentive response behavior, and maximizing marginal results. This method is useful in systems that have direct and private communication with each user but are limited by having users enter the system at different times. The method must offer a menu of choices and incentives on demand while still considering users that are yet to come. I discuss several solutions and benchmark them on the TRIPOD traffic optimization system which aims to incentivize users to make energy efficient daily commute choices. The final model incorporates user personalized incentives and opportunity cost of each incentive to achieve the optimal incentive allocation on an ad-hoc basis.
by David A. Sukhin.
M. Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science

Travel demand models have long been used as tools by decision makers and researchers to analyse the effects of policies and infrastructure investments. The purpose of this thesis is to develop a travel demand model which is: sensitive to policies affecting timing of trips and time-space constraints; is consistent with microeconomics; and consistently treats the joint choice of the number of trips to perform during day as well as departure time, destination and mode for all trips. This is achieved using a dynamic discrete choice model (DDCM) of travel demand. The model further allows for a joint treatment of within-day travelling and between-day activity scheduling assuming that individuals are influenced by the past and considers the future when deciding what to do on a certain day. Paper I develops and provides estimation techniques for the daily component of the proposed travel demand model and present simulation results provides within sample validation of the model. Paper II extends the model to allow for correlation in preferences over the course of a day using a mixed-logit specification. Paper III introduces a day-to-day connection by using an infinite horizon DDCM. To allow for estimation of the combined model, Paper III develops conditions under which sequential estimation can be used to estimate very large scale DDCM models in situations where: the discrete state variable is partly latent but transitions are observed; the model repeatedly returns to a small set of states; and between these states there is no discounting, random error terms are i.i.d Gumble and transitions in the discrete state variable is deterministic given a decision. Paper IV develops a dynamic discrete continuous choice model for a household deciding on the number of cars to own, their fuel type and the yearly mileage for each car. It thus contributes to bridging the gap between discrete continuous choice models and DDCMs of car ownership. Infinite horizon DDCMs are commonly found in the literature and are used in, e.g., Paper III and IV in this thesis. It has been well established that the discount factor must be strictly less than one for such models to be well defined.Paper V show that it is possible to extend the framework to discount factors greater than one, allowing DDCM's to describe agents that: maximize the average utility per stage (when there is no discounting); value the future greater than the present and thus prefers improving sequences of outcomes implying that they take high costs early and reach a potential terminal state sooner than optimal.
Modeller för reseefterfrågan har länge använts av besultsfattare såväl somforskare för att analysera effekterna av transportpolitiska åtgärder. Avhandlingenshuvudsakliga syfte har varit att bidra till utvecklandet av modellerför reseefterfrågan som är: känsliga för åtgärder som påverkar tidsvalför resor eller tids-rums begränsningar; och konsistent behandlar valet avantalet resor, avresetid, destination och färdmedel för en individ. Dettauppnås genom användandet av en dynamisk diskret valmodell (DDCM) förreseefterfrågan. Modellen klarar vidare av att gemensamt modellera bådedagligt resande med hänsyn till hur det påverkar behovet av andra resoröver en längre tidshorisont, där individer antas ta hänsyn till både när desenaste utfört olika aktiviteter samt framtida effekter av sina besult. Papper I utvecklar den dagliga komponenten i den föreslagna modellenför reseefterfrågan, presenterar en estimeringsteknik samt resultat från simuleringarmed valideringsresultat. Papper II förbättrar modellen genom attinkludera korrelation i preferenser under dagen med hjälp av en mixed-logitspecifikation. Papper III introducerar en koppling mellan dagar genom enDDCM med oändlig tidshorisont. För att den kombinerade modellen skullevara möjlig att estimera härleddes vilkor under vilka sekvensiell estimeringvar möjlig. Dessa vilkor möjligör därmed estimering av en specific typ avstorskaliga DDCM modeller i situationer när: den diskreta tillståndsvariabelnär delvis latent men där val observeras; där modellen återkommer tillett mindre tillståndrum; och där det mellan återkomsten till detta mindretillståndrum inte sker någon diskontering, nyttofunktionernas feltermer gesav i.i.d Gumble termer och övergångarna mellan disrekta tillståndsvariablerär deterministisk givet valet. Papper IV utvecklar en dynamiskt diskret-kontinuerlig valmodell för etthushålls beslut gällande antalet bilar att äga, deras bränsletyp samt årligamiltal för varje bil. Det därmed till att komibinera dynamiska och diskretkontinulerligavalmodeller för bilägande. DDCM med oändliga tidshorisonter är vanligt förekommande och användsi bland annat Papper III och IV i den här avhandlingen. Det harvarit väl etablerat att diskonteringsfaktorn måste vara strikt mindre än ettför att sådana modeller ska vara väldefinerade. Papper V visar hur det ärmöjligt tillåta diskonteringsfaktorer större än eller lika med ett, och därmedbeskriva agenter som: maximerar den genomsnittliga nyttan per steg (närdet inte sker någon diskontering); värderar framtiden högre än nutiden ochdärmed föredrar förbättrande sekvenser vilket också implicerar att de tarhöga kostnader så tidigt som möjligt och når ett potentiellt sluttillståndtidigare än optimalt.

Thesis (Ph. D.)--Industrial and Systems Engineering, Georgia Institute of Technology, 2008.
Esogbue, Augustine, Committee Chair ; Griffin, Paul, Committee Member ; Lu, Jye-Chyi (JC), Committee Member ; Li, MinQiang, Committee Member ; McCarthy, Patrick, Committee Member.

This D.Phil. thesis develops a new agent-based simulation model to improve the results of analysis, which solely uses discrete choice modelling, as well as to analyse the effects of a road user charging scheme for the Upper Derwent Valley in the Peak District National Park. The advantages of discrete choice analysis are well known. However, results with these conventional conventional approaches, which conduct analysis solely with discrete choice models, can be biased if interaction and learning effects are significant. The Minority Game, in which agents try to choose the option of the minority side, is an appropriate tool to deal with these problems. The situation in the Upper Derwent Valley can be explained with economic game theories and the Minority Game. The two approaches mutually help to analyse the situation in the Upper Derwent Valley leading to the development of a stochastic Minority Game. The stochastic Minority Game was tested with an online game (questionnaire), which was played 3,886 times by response in all around the world. The practical part of this thesis examines the components of the stochastic Minority Game with the data collected around the Upper Derwent Valley. The main data was collected using a stated preference survey. Overall, 700 questionnaires were distributed and 323 of them were returned (i.e. a return rate of 46.1 %). In the practical part, the agent-based model has four sub modules: 1) Multinomial mixed logit model for mode choice, 2) Binary logit model for parking location choice, 3) Markov queue model for parking network, and 4) the Minority Game for parking congestion and learning. This simulation model produces comprehensive outputs including mode choices, congestion levels, and user utilities. The results show that the road user charging scheme reduces car demand in the Upper Derwent Valley and ensures a reduction in congestion at the parking areas. The model also shows that an exemption will increase the utilities of elderly visitors without substantially sacrificing those of younger visitors. In conclusion, the simulation model demonstrated that oversimplification in conventional approaches solely using discrete choice models gave significant biases when real world problems were analysed.

The main theme of my dissertation is the analysis of several interactive decision making situations with multiple decision makers whose interests do not fully coincide. Non-cooperative game theory is invoked to carry on this analysis.The first chapter describes an experimental study of volunteer's dilemmas that evolve over time. Only a single volunteer is required for the public good to be provided. Because volunteering is costly, each prefers that some other players bear the full costs of volunteering. Reflecting on the observation that in many naturally occurring social dilemmas it is beneficial to volunteer earlier than later, I assume that the payoff to the volunteer and the (higher) payoff to each of the non-volunteers decrease monotonically over time. I derive symmetric and asymmetric subgame perfect equilibria. The experimental results provide little support to asymmetric equilibria in which only a single subject volunteers immediately. In comparison to the symmetric subgame perfect equilibrium, they show that subjects volunteer, on average, earlier than predicted.The second chapter explores a new type of online auction, called the unique bid auction, that has recently emerged on the Internet and gained widespread popularity in many countries. In a sharp contrast to traditional auctions, the winner in this class of auctions is the bidder who submits the lowest (highest) unique bid; all ties are discarded. I propose an algorithm to numerically compute the symmetric mixed-strategy Nash equilibrium solution and then conduct a series of experiments to assess the predictive power of the equilibrium solution. The experimental results show that the solution accounts quite well for the subjects' bidding behavior on the aggregate level, but not on the individual level.The last chapter proposes a discrete version of William Vickrey's model of traffic congestion on a single road with a single bottleneck. In my model, both the strategy space and number of commuters are finite. An algorithm similar to the one used in the second chapter is proposed to numerically calculate the symmetric mixed-strategy Nash equilibrium. The discrete model is then compared with the original continuous model of Vickrey in terms of the equilibrium solution and its implications.

Whilst discrete choice experiments (DCEs) are now widely used in health economics, their application within cost benefit framework has been limited. Studies that have conducted cost benefit analysis (CBA) using DCEs have not taken into account the joint uncertainty surrounding the outcomes using decision analytic methods and a Bayesian approach to statistical inference and estimation.

Chapter 1 of the thesis is divided into 5 sections. Section A begins by defining a Discrete Choice Experiment (DCE), and outlines the key stages involved in conducting a DCE. Sections B and C outline theories underpinning DCE analysis. Section B outlines the characteristics theory of demand, whilst section C, explains random utility theory (RUT), compensating variation (CV), marginal willingness to pay (MWTP), and willingness to pay (WTP) analysis. Section D of the thesis provides a review of the DCE literature. Section E outlines the research questions addressed in the thesis including calculating WTP and hypothetical bias; the description of the cost attribute; preference heterogeneity; and altruism. Chapter 2 shows how DCEs can be used to calculate WTP, using a DCE relating to Deep Vein Thrombosis (DVT). Chapter 3 uses data from a DCE applied to Menstrual disorder and Gynaecology patients. It evaluates an experimental method I developed to establish whether respondents might fail to factor in the monetary attribute into their DCE decision making, leading to hypothetical bias. Chapter 4 applies essentially the same DCE design but only analyses data from Gynaecology patients. Chapters 4-8 all use data obtained from a DCE relating to preferences for different allocation criteria for allocating kidneys for transplantation. Chapters 5 and 6 look at preference heterogeneity which is observable using interaction dummy variables (the issue of unobserved preference heterogeneity is considered in chapter 7). Chapter 5 establishes how marginal rates of substitution (MRS) differ between different respondent groups including renal patients, healthcare professionals, live donors / relatives of deceased donors, carers, and ethnic minority versus non-ethnic minority patients. Chapter 6 establishes how MRS differs between non-white ethnic minority patients versus other patients; South Asian patients versus other patients; and according to respondent gender. Chapter 7 of the thesis compares results from models which do not cater for unobserved preference heterogeneity, with results from models which do. Initially 2 basic models which do not cater for preference heterogeneity at all (because they do not include dummy variables) are applied including random effects logit and conditional logit. Then models catering for unobserved preference heterogeneity including Mixed Logit and a Latent Class Model (LCM) are used. Finally there is an analysis involving the application of conditional logit with interaction dummy variables. Chapter 8 of the thesis explores how preferences might differ according to how altruistic respondents are. It establishes how respondent preferences differ according to respondent self-disclosed perspective when answering DCEs. In other words whether they claimed to answer the DCE in terms of what would be best for me; what would be best for me and others; or what is best for others. Finally chapter 9 involves a discussion of the findings emerging from the thesis, and draws conclusions about the merits of material contained in it.

Discrete choice experiments (DCEs) are widely used across economic disciplines to value multi-attribute commodities. DCEs ask survey-respondents to choose between mutually exclusive hypothetical alternatives that are described by a set of common attributes. The analysis of DCE data assumes that respondents consider and trade all attributes before making these choices. However, several studies show that many respondents ignore attributes. Respondents might choose not to consider all attributes to simplify choices or as a preference, because some attributes are not important to them. However, empirical approaches that account for attribute non-consideration only assume simplifying choice behaviour. This thesis shows that this assumption may lead to misleading welfare conclusions and therefore suboptimal policy advice. The analysis explores 'why' attribute are ignored using statistical analysis or by asking respondents. Both approaches are commonly used to identify attribute non-consideration in DCEs. However, the results of this thesis suggest that respondents struggle to recall ignored attributes and their reasons for non-consideration unless attributes are ignored due to non-valuation. This questions the validity of approaches in the literature that rely on respondents' ability to reflect on their decision rule. Further analysis explores how the complexity of choices affects the probability that respondents do not consider all attributes. The results show that attribute consideration first increases and then decreases with complexity. This raises questions about the optimal design complexity of DCEs. The overall findings of the thesis challenge the applicability of current approaches that account for attribute non-consideration in DCEs to policy analysis and emphasis the need for further research in this area.

Insufficient knowledge of residential preferences represents a major obstacle to achieving residential satisfaction and quality of life. This obstacle is even greater in the case of transit-oriented developments (TODs), as their success depends, in part, on the degree to which people's preferences are consistent with their residential environments. This study employed a visual choice experiment, which combines the benefits of visual preference surveys and discrete choice experiments, to elicit residential preference for TODs in Riyadh, Saudi Arabia, before the opening of its citywide public transportation system. Using a seemingly homogeneous sample of participants, the analysis incorporated three analytical methods to elicit residential preference: a multinomial logit model, a mixed logit model, and a latent class model. The results indicated the presence of preference heterogeneity and the emergence of four lifestyle classes that could explain and predict residential preference patterns. People with similar sociodemographic characteristics may have different lifestyles based on their choice behavior, marital status, and public transit attitudes. Additionally, the results showed a strong preference for low-density housing, even among those who favor living in a TOD; however, increasing density could be mitigated through the presence of other TOD attributes. The findings of this research point to the diversity of residential preferences and suggest that providing a variety of residential environments increases the likelihood that people will find their preferred environment. Additionally, planning efforts to convert all developments near transit, particularly in suburban locations, to TODs might be unsuitable in cities where public transportation has been introduced only recently. Instead, deferring TOD conversion efforts until public transportation and its use are mature may attract people to live near transit and encourage the gradual development of transit affinity in residents who may otherwise reject TOD living completely. Lastly, the successful application of a visual choice experiment in this research opens up a variety of potential analytical methods that are used commonly in other fields and have the potential to move visual preference research into the realm of robust empirical investigation.
Ph. D.
The work of urban planners, urban designers, architects, and policy makers centers on improving the built environment and increasing the quality of people’s lives. However, their work entails making decisions that are not always in tandem with people’s preferences (e.g., increasing housing density, proposing a mix of land uses in residential neighborhoods, introducing public transportation close to where people live and work, to name a few). Due to the uncertainty surrounding people’s acceptance of modifications of the built environment, especially when it entails introducing residential attributes for the first time, this dissertation focused on 1) assessing residential preference near public transportation nodes in Riyadh, Saudi Arabia before operation of the public transportation system, and 2) assessing the extent to which advanced analytical methods are capable of providing a better understanding of residential preference differences among a seemingly homogenous sample of participants. The work in this dissertation was motivated by the increasing use of manipulated images in choice tasks, where participants are presented with multiple images, each depicting a residential scenario, as bundles to choose from, and their choice patterns then recorded and analyzed. The results showed that among the relatively homogenous sample of participants that was recruited, four significant residential preference patterns have emerged, which could be used to describe and predict residential preference and choice with great accuracy. This dissertation laid out several policy implications that could be useful in providing a built environment that matches with what people want. It also provided research implications and suggestions on the use of visual choice experiments for urban planners and designers that are well-developed in other fields of inquiry.

A sustainable development becomes more and more important with an increasing number of catastrophic and long-term changes to the environment due to global warming. This also means that all the actors in the society needs to take their responsibility to combat this development. One of these actors are the private sector where the investors plays a large part in which companies that gets to develop their ideas and make a difference in the world. So, the question is: are investors taking that responsibility today and invest in start-ups with a focus on sustainable development in their business plans. This thesis aims to study how inclined investors are to invest in start-ups with a focus on sustainable development in their business plan. This is tested though Discrete Choice Experiments where 14 investors got to choose between three different companies with different levels of focus on sustainable development. Company A with the least amount of sustainability, company B with some focus and company C with a high focus on sustainable development. The Discrete Choice Experiments were distributed through a survey format where the companies were represented with a Business Model Canvas each and the investors first got to choose between company A & B, then A & C, and then company B & C. The results show that investors chose company A with the least amount of focus on sustainable development in 26 percent of the cases, company B with some focus in 45 percent, and company C with a high amount of focus in 29 percent of the cases. The study also shows a variation between different groups of investors, i.e. the investors who identified themselves as women were more inclined on investing in more sustainable options then men, and angel investors showed a clear willingness to invest in sustainability compared to venture capitals. The conclusions of the study are that its purpose was fulfilled and that the research questions was answered, investors showed an inclination to investing in companies with some focus on sustainable development but not too much. The results of the study can be used by companies in need of investments since they can see what group they should focus on to increase their chances. It is despite this also important to remember that the reliability and the validity of the study can be criticised with flaws for example in the reputability of the results. Future research within the area should study larger populations of investors to see if the same patterns repeat itself in other groups. It should also split the different attributes of the business model to see if different attributes play a larger part when investors decide which company to invest in.
Då hållbar utveckling blir allt mer viktigt så behöver alla aktörer i samhället göra sin del för att minska de ibland katastrofala och långvariga klimatförändringarna som blir på grund av exempelvis en högre medeltemperatur på jorden. En av dessa aktörer är den privata sektorn där investerare har en stor påverkan i vilka företag som får möjlighet att testa sina idéer och göra skillnad i världen. Frågan är dock om investerare tar det ansvaret och investerar i start-up företag med fokus på hållbar utveckling i sin affärsmodell. Denna studie syftar till att undersöka hur benägen investerarna är att faktiskt göra detta. Detta testas genom ett Discrete Choice Experiment där 14 investerare fick välja mellan tre olika företag som har olika stort fokus på hållbar utveckling i sin affärsmodell. Företag A har minst fokus på hållbar utveckling, företag B har viss fokus och företag B har stort fokus på hållbar utveckling. Discrete Choice Experimentet distribuerades i enkätformat där företagen representerades av en Business Model Canvas vardera och investerarna fick först välja mellan företag A & B, sedan företag A & C, och till sist företag B & C. Resultatet från studien visar på att investerare vid 26 procent av gångerna skulle välja en start-up utan fokus på hållbar utveckling, 45 procent av gångerna en med visst fokus på hållbar utveckling och 29 procent av gångerna en start-up med stort fokus på hållbar utveckling. Undersökningen visar också på en differens mellan olika grupperingar då exempelvis de som identifierade sig som kvinnor var mer benägna att investera på hållbar alternativ än män. Dessutom visar ängelinvesterare tydligt på en större benägenhet att investera i start-ups med fokus på hållbar utveckling än riskkapitalister. Slutsatserna av studien är att dess syfte uppfyllts och forskningsfrågan besvarats med att investerare har en benägenhet att investera i start-ups med en visst fokus på hållbar utveckling men det fick inte bli för mycket fokus. Resultatet av undersökningen kan användas av företag som befinner sig i faser där de behöver investeringar samt att de kan se vilket typ av investerare de bör vända sig till för att få störst möjlighet till positivt resultat. Viktigt att ta med sig från undersökningen är att dess reliabilitet och validitet kan kritiseras med brister exempelvis inom upprepbarheten i resultaten. Fortsatt forskning inom området bör studera större populationer av investerare för att se om samma mönster upprepar sig inom andra grupperingar samt att attributen hos affärsmodellerna kan delas upp mer för att undersöka om vissa attribut har större betydelse än andra när investerare väljer vilka start-ups de ska investera i.

Eine zentrale Aufgabe des Marketings ist es, die Präferenzen von Konsumenten zu verstehen und die Heterogenität dieser aufzudecken. Eine Reihe kritischer Entscheidungen, z.B. bei der Neuproduktentwicklung, der Marktsegmentierung und dem Targeting oder der Preisgestaltung, beruhen auf der genauen Einschätzung der Konsumentenpräferenzen. Die Marketingliteratur hat sich bisher auf die Entwicklung von Modellen und Schätzverfahren konzentriert, die es ermöglichen, die Heterogenität von Konsumentenpräferenzen aufzudecken. Konsumenten unterscheiden sich jedoch auch in der Art und Weise, wie sie Kaufentscheidungen treffen und welche verfügbaren Informationen sie nutzen. Das Ziel dieser Dissertation ist es, unser Verständnis für die Unaufmerksamkeit der Konsumenten gegenüber Produkteigenschaften bezüglich Entscheidungen zu verbessern. Es geht darum, 1) die Verbreitung einer solchen Unaufmerksamkeit in verschiedenen Kontexten zu untersuchen, 2) die Methoden, die ein solches Verhalten explizit berücksichtigen, zu untersuchen und zu erweitern, 3) potenzielle Verzerrungen in Parametern zu verstehen und 4) Implikationen für das Management abzuleiten. Die Ergebnisse aus einer umfassenden Reihe von Anwendungen legen nahe, dass Konsumenten in verschiedenen Kontexten (z.B. Produktkategorien) und Settings (z.B. von hoher oder niedriger Komplexität) eine Menge an verfügbaren Informationen bezüglich Produkteigenschaften ignorieren. Zweitens, Entscheidungsmodelle, die ein solches Verhalten explizit berücksichtigen und zusätzlich weitere Daten wie z.B. Eye-Tracking nutzen, zu einem besseren In- und Out-of-Sample-Fit führen. Drittens führt die Missachtung eines solchen Verhaltens zu Verzerrungen, deren Richtung und Größe von der Art des Merkmals (d.h., ob eine bestimmte Richtung der Präferenzen erwartet werden kann) und dem Anteil der Konsumenten, die dieses Merkmal ignorieren, abhängt. Infolgedessen kann es dazu kommen, dass Manager keine optimalen Preis- und Targeting-Entscheidungen treffen.
A central task of marketing is understanding consumer preferences and uncovering consumer heterogeneity. A range of critical decisions, e.g., new product development, market segmentation and targeting, or pricing, rest upon accurate estimation of consumer preferences. Marketing literature has mainly focused on the development of models and estimation procedures that allow uncovering heterogeneity in consumer preference. However, consumers differ not only in their tastes but also in the way they make purchase decisions and the information they use. The overall objective of this dissertation is to enhance our understanding of consumers' inattention to attributes when making choices. It aims to 1) examine the prevalence of such inattention across numerous contexts and settings, 2) investigate and extend the approaches that explicitly accommodate such behavior, 3) understand potential biases that may arise, and 4) demonstrate managerial implications when such behavior is neglected. The findings from a broad set of applications suggest that consumers ignore a substantial amount of available attribute information across various contexts (e.g., product categories) and settings (e.g., of high or low complexity). Second, we establish that choice models explicitly accounting for such behavior and, additionally, leveraging supplementary data such as eye tracking, result in better in- and out-of-sample fit. Third, neglecting such behavior leads to significant biases, the direction and the magnitude of which depend on the type of the attribute (i.e., whether a particular direction of preferences can be expected) and the share of consumers ignoring this attribute. As a result, managers may make suboptimal pricing and targeting decisions.

Esta tese é composta por três ensaios sobre Economia do Empreendedorismo. O primeiro deles trata sobre os determinantes do empreendedorismo no Brasil a partir de modelos de escolha ocupacional, usando os microdados da Pesquisa Nacional por Amostra por Domicílios (PNAD) do ano de 2012. A estratégia empírica adotada empregou os modelos de escolha discreta na estimação da escolha ocupacional. Os resultados demonstraram que existem efeitos significativos para as variáveis: anos de estudos iniciais, sexo, estado civil assim como pensionista e aposentado. Para completar a análise foram estimadas as equações de rendimento, as quais explicam a escolha pela ocupação empreendedora em função dos ganhos relativos ao trabalho assalariado. Já o segundo ensaio tem como objetivo apresentar uma evidência empírica para a relação existente entre empreendedorismo e corrupção nos estados brasileiros, utilizando uma abordagem teórica e empírica. Este artigo utiliza um indicador objetivo de corrupção governamental estadual baseado no Cadastro de Contas Irregulares do Tribunal de Contas da União (CADIRREG) como proxy para a corrupção regional e a abertura de novas empresas per capita como medida para a atividade empreendedora. Foram utilizados o método de dados de painel estático, dinâmico e o método GMMSYS, estes últimos empregados para corrigir possíveis problemas de endogeneidade. Os resultados encontrados mostraram-se coerentes com a hipótese teórica “grease in the wheels”, na qual a corrupção influencia positivamente a atividade empreendedora em países em desenvolvimento com elevada burocracia. Por fim, o terceiro ensaio avalia os impactos do empreendedorismo via inovação a partir do Global Trade Analysis Project – GTAP, um modelo de equilíbrio geral computável (EGC), destacando os impactos no crescimento econômicoe no bem-estar geral da economia. Os resultados mostraram-se coerentes com a literatura da Economia do Empreendedorismo, mostrando que aumento no empreendedorismo conduz a uma elevação no crescimento econômico e bem-estar.
This thesis consists of three essays on the Economics Entrepreneurship. The first deals with the determinants of entrepreneurship in Brazil from occupational choice models, using the data from the National Household Sample Survey (PNAD) of 2012. The empirical strategy adopted has employed discrete choice models in the estimation of occupational choice. The results showed that there are significant effects on the variables: years of initial studies, gender, marital status as well as pensioners and retired. To complete the analysis were estimated earnings equations, which explains the choice by the entrepreneurial occupation in terms of earnings for paid employment. The second test aims to present empirical evidence for the relationship between entrepreneurship and corruption in the Brazilian states, using a theoretical and empirical approach. This article uses an objective indicator of state government corruption based on the Register of Irregular accounts of the Court of Audit (CADIRREG) as a proxy for regional corruption and the opening of new companies per capita as a measure for regional entrepreneurial activity. They used the method of static panel data, dynamic and GMM-SYS method to correct the endogeneity problem. The results proved to be consistent with the theoretical hypothesis "grease in the wheels" in which corruption positively influence the entrepreneurial activity in developing countries with high bureaucracy. Finally, the third test evaluates the impacts of entrepreneurship via innovation from the Global Trade Analysis Project - GTAP, a model of computable general equilibrium (CGE), highlighting the impacts on economic growth and overall well-being economy. The results were consistent with the literatureof Entrepreneurship Economics, showing that increased entrepreneurship leads to a rise in economic growth and well-being.

Thesis advisor: Andrew Beauchamp
Thesis advisor: Peter Gottschalk
This dissertation examines how caregiving for an elderly parent affects an adult child's labor supply and wages. In the first chapter (co-authored with Courtney H. Van Houtven and Norma B. Coe) we identify the relationship between informal care and labor force participation in the United States, both on the intensive and extensive margins, and examine wage effects. We control for time-invariant individual heterogeneity; rule out or control for endogeneity; examine effects for men and women separately; and analyze heterogeneous effects by task and intensity. We find modest decreases--1.4-2.4 percentage points--in the likelihood of working for caregivers providing personal care. Male and female chore caregivers, meanwhile, are more likely to retire. For female care providers who remain working, we find evidence that they decrease work by 3-10 hours per week and face a 2.3-2.6 percent wage penalty. We find little effect of caregiving on working men's hours or wages except for a wage premium for male intensive caregivers. In the second chapter I formulate and estimate a dynamic discrete choice model of elder parent care and work to analyze how caregiving affects a woman's current and future labor force participation and wages. Intertemporal tradeoffs, such as decreased future earning capacity due to a current reduction in labor market work, are central to the decision to provide care. The existing literature, however, overlooks such long-term considerations. I depart from the previous literature by modeling caregiving and work decisions in an explicitly intertemporal framework. The model incorporates dynamic elements such as the health of the elderly parent, human capital accumulation and job offer availability. I estimate the model on a sample of women from the Health and Retirement Study by efficient method of moments. The estimates indicate that intertemporal tradeoffs matter considerably. In particular, women face low probabilities of returning to work or increasing work hours after a caregiving spell. Using the estimates, I simulate several government sponsored elder care policy experiments: a longer unpaid leave than currently available under the Family and Medical Leave Act of 1993; a paid work leave; and a caregiver allowance. The leaves encourage more work among intensive care providers since they guarantee a woman can return to her job, while the caregiver allowance discourages work. A comparison of the welfare gains generated by the policies shows that half the value of the paid leave can be achieved with the unpaid leave, and the caregiver allowance generates gains comparable to the unpaid leave
Thesis (PhD) — Boston College, 2012
Submitted to: Boston College. Graduate School of Arts and Sciences
Discipline: Economics

In both developed and emerging-economies, major cities continue to experience increasing traffic congestion. To address this issue, complex Traffic Management Systems (TMS) are employed in recent years to help manage traffic. These systems fuse traffic-surveillance-related information from a variety of sensors deployed across traffic networks. A TMS requires real-time information to make effective control decisions and to deliver trustworthy information to users, such as travel time, congestion level, etc. There are three fundamental inputs required by TMS, namely, traffic volume, vehicular speed, and traffic density. Using conventional traffic loop detectors one can directly measure flow and velocity. However, traffic density is more difficult to measure. The situation becomes more difficult for multi-lane motorways due to drivers lane-change behaviour. This research investigates statistical modelling and analysis of traffic flow. It contributes to the literature of transportation and traffic management and research in several aspects. First, it takes into account lane-changes in traffic modelling through incorporating a Markov chain model to describe the drivers lane-change behaviour. Secondly, the lane change probabilities between two adjacent lanes are not assumed to be fixed but rather they depend on the current traffic condition. A discrete choice model is used to capture drivers lane choice behaviour. The drivers choice probabilities are modelled by several traffic-condition related attributes such as vehicle time headway, traffic density and speed. This results in a highly nonlinear state equation for traffic density. To address the issue of high nonlinearity of the state space model, the EKF and UKF is used to estimate the traffic density recursively. In addition, a new transformation approach has been proposed to transform the observation equation from a nonlinear form to a linear one so that the potential approximation in the EKF & UKF can be avoided. Numerical studies have been conducted to investigate the performance of the developed method. The proposed method outperformed the existing methods for traffic density estimation in simulation studies. Furthermore, it is shown that the computational cost for updating the estimate of traffic densities for a multi-lane motorway is kept at a minimum so that online applications are feasible in practice. Consequently the traffic densities can be monitored and the relevant information can be fed into the traffic management system of interest.

This thesis presents an economic assessment of microalgae biofuels as a substitute in the Australian transport fuel market. The studies systematically reviewed the current state of microalgae biofuels among its predecessors, analysed a novel production pathway integrated with existing industries, and estimated the economic value of its external benefits over agricultural-based biofuels. These findings informed a discussion on how a long-term, policy-led transition away from fossil fuels can be achieved through support for the development of integrated microalgae industries and more importantly, capturing the economic value of biofuels that will lead to a more diversified and socially-efficient transport fuel market.

This thesis is a study of tourism demand and supply with the objective of revealing the optimal management of resources used in tourism. The first part investigates consumer preferences with respect to nature-based tourism together with a study of the manner in which tourists’ experiences impact on non-market valuations. The second part describes an efficiency evaluation of the hotel industry which focuses on the impact of eco-friendly practices on hotel operations. The analytical techniques used include discrete choice modelling, structural choice modelling and data envelopment analysis. The findings contribute to the important goal of creating a sustainable tourism industry in Sri Lanka and similar destinations.

My dissertation consists of three essays on labor supply responses, along the extensive margin (participation into the labor force) and along the intensive margin (intensity of work on the job). The first two essays focus on the labor supply responsiveness of single women with children to taxation and welfare programs. The third essay investigates the effects of marriage, the wage rate, and the associated tax rate on men's labor supply. In the first essay, to avoid bias from the fact that labor supply outcomes are being driven by self-selection, I build a dynamic stochastic discrete choice model to investigate the long run effects of the earned income tax credit and welfare policies on single mothers' labor supply. Simulated method of moments is used to estimate parameters of this dynamic model, based on March CPS data files from 1964 to 2013. I compare the performance of the dynamic stochastic discrete choice model, a static model, and a reduced-form model. My analysis concludes that the dynamic stochastic discrete choice model captures the simultaneous impact of the state variables on the predicted employment decision. My study provides evidence of the long-run positive effect of public policy on low income families in a life-cycle setting. This essay also emphasizes the importance of education in increasing single mothers' labor supply. The second essay is designed to identify factors that help single mothers leave TANF within a short span of time. I find strong evidence for the importance of child support assistance to single mothers' success in exiting TANF with a job. I uncover evidence that work-related activities do not induce TANF participants to leave within a short span of time. My analysis also suggests that health issues significantly limit the ability of single mothers to exit TANF. In the third essay, the main research question is how marital status affects the elasticity of the labor supply of males with respect to wages and taxes, in a life-cycle setting. A dynamic panel data model, which extends the literature on dynamic labor supply, indicates that the elasticity of men's labor supply with respect to wages and taxes is affected by marital status. The empirical results using the Panel Study of Income Dynamics (PSID) data show that men who are continuously married to the same wife have a lower average Frisch elasticity than others.
Ph. D.

El mundo de las telecomunicaciones está cambiando de un escenario donde únicamente las personas estaban conectadas a un modelo donde prácticamente todos los dispositivos y sensores se encuentran conectados, también conocido como Internet de las cosas (IoT), donde miles de millones de dispositivos se conectarán a Internet a través de conexiones móviles y redes fijas. En este contexto, hay muchos retos que superar, desde el desarrollo de nuevos estándares de comunicación al estudio de la viabilidad económica de los posibles escenarios futuros. En esta tesis nos hemos centrado en el estudio de la viabilidad económica de diferentes escenarios mediante el uso de conceptos de microeconomía, teoría de juegos, optimización no lineal, economía de redes y redes inalámbricas. La tesis analiza la transición desde redes centradas en el servicio de tráfico HTC a redes centradas en tráfico MTC desde un punto de vista económico. El primer escenario ha sido diseñado para centrarse en las primeras etapas de la transición, en la que ambos tipos de tráfico son servidos bajo la misma infraestructura de red. En el segundo escenario analizamos la siguiente etapa, en la que el servicio a los usuarios MTC se realiza mediante una infraestructura dedicada. Finalmente, el tercer escenario analiza la provisión de servicios basados en MTC a usuarios finales, mediante la infraestructura analizada en el escenario anterior. Gracias al análisis de todos los escenarios, hemos observado que la transición de redes centradas en usuarios HTC a redes MTC es posible y que la provisión de servicios en tales escenarios es viable. Además, hemos observado que el comportamiento de los usuarios es esencial para determinar la viabilidad de los diferentes modelos de negocio, y por tanto, es necesario estudiar el comportamiento y las preferencias de los usuarios en profundidad en estudios futuros. Específicamente, los factores más relevantes son la sensibilidad de los usuarios al retardo en los datos recopilados por los sensores y la cantidad de los mismos. También hemos observado que la diferenciación del tráfico en categorías mejora el uso de las redes y permite crear nuevos servicios empleando datos que, de otro modo, no se aprovecharían, lo cual nos permite mejorar la monetización de la infraestructura. También hemos demostrado que la provisión de capacidad es un mecanismo válido, alternativo a la fijación de precios, para la optimización de los beneficios de los proveedores de servicio. Finalmente, se ha demostrado que es posible crear roles específicos para ofrecer servicios IoT en el mercado de las telecomunicaciones, específicamente, los IoT-SPs, que proporcionan servicios basados en sensores inalámbricos utilizando infraestructuras de acceso de terceros y sus propias redes de sensores. En resumen, en esta tesis hemos intentado demostrar la viabilidad económica de modelos de negocio basados en redes futuras IoT, así como la aparición de nuevas oportunidades y roles de negocio, lo cual nos permite justificar económicamente el desarrollo y la implementación de las tecnologías necesarias para ofrecer servicios de acceso inalámbrico masivo a dispositivos MTC.
The communications world is moving from a standalone devices scenario to a all-connected scenario known as Internet of Things (IoT), where billions of devices will be connected to the Internet through mobile and fixed networks. In this context, there are several challenges to face, from the development of new standards to the study of the economical viability of the different future scenarios. In this dissertation we have focused on the study of the economic viability of different scenarios using concepts of microeconomics, game theory, non-linear optimization, network economics and wireless networks. The dissertation analyzes the transition from a Human Type Communications (HTC) to a Machine Type Communications (MTC) centered network from an economic point of view. The first scenario is designed to focus on the first stages of the transition, where HTC and MTC traffic are served on a common network infrastructure. The second scenario analyzes the provision of connectivity service to MTC users using a dedicated network infrastructure, while the third stage is centered in the analysis of the provision of services based on the MTC data over the infrastructure studied in the previous scenario. Thanks to the analysis of all the scenarios we have observed that the transition from HTC users-centered networks to MTC networks is possible and that the provision of services in such scenarios is viable. In addition, we have observed that the behavior of the users is essential in order to determine the viability of a business model, and therefore, it is needed to study their behavior and preferences in depth in future studios. Specifically, the most relevant factors are the sensitivity of the users to the delay and to the amount of data gathered by the sensors. We also have observed that the differentiation of the traffic in categories improves the usage of the networks and allows to create new services thanks to the data that otherwise would not be used, improving the monetization of the infrastructure and the data. In addition, we have shown that the capacity provision is a valid mechanism for providers' profit optimization, as an alternative to the pricing mechanisms. Finally, it has been demonstrated that it is possible to create dedicated roles to offer IoT services in the telecommunications market, specifically, the IoT-SPs, which provide wireless-sensor-based services to the final users using a third party infrastructure. Summarizing, this dissertation tries to demonstrate the economic viability of the future IoT networks business models as well as the emergence of new business opportunities and roles in order to justify economically the development and implementation of the new technologies required to offer massive wireless access to machine devices.
El món de les telecomunicacions està canviant d'un escenari on únicament les persones estaven connectades a un model on pràcticament tots els dispositius i sensors es troben connectats, també conegut com a Internet de les Coses (IoT) , on milers de milions de dispositius es connectaran a Internet a través de connexions mòbils i xarxes fixes. En aquest context, hi ha molts reptes que superar, des del desenrotllament de nous estàndards de comunicació a l'estudi de la viabilitat econòmica dels possibles escenaris futurs. En aquesta tesi ens hem centrat en l'estudi de la viabilitat econòmica de diferents escenaris per mitjà de l'ús de conceptes de microeconomia, teoria de jocs, optimització no lineal, economia de xarxes i xarxes inalàmbriques. La tesi analitza la transició des de xarxes centrades en el servici de tràfic HTC a xarxes centrades en tràfic MTC des d'un punt de vista econòmic. El primer escenari ha sigut dissenyat per a centrar-se en les primeres etapes de la transició, en la que ambdós tipus de tràfic són servits davall la mateixa infraestructura de xarxa. En el segon escenari analitzem la següent etapa, en la que el servici als usuaris MTC es realitza per mitjà d'una infraestructura dedicada. Finalment, el tercer escenari analitza la provisió de servicis basats en MTC a usuaris finals, per mitjà de la infraestructura analitzada en l'escenari anterior. Als paràgrafs següents es descriu amb més detall cada escenari. Gràcies a l'anàlisi de tots els escenaris, hem observat que la transició de xarxes centrades en usuaris HTC a xarxes MTC és possible i que la provisió de servicis en tals escenaris és viable. A més a més, hem observat que el comportament dels usuaris és essencial per a determinar la viabilitat dels diferents models de negoci, i per tant, és necessari estudiar el comportament i les preferències dels usuaris en profunditat en estudis futurs. Específicament, els factors més rellevants són la sensibilitat dels usuaris al retard en les dades recopilats pels sensors i la quantitat dels mateixos. També hem observat que la diferenciació del tràfic en categories millora l'ús de les xarxes i permet crear nous servicis emprant dades que, d'una altra manera, no s'aprofitarien, la qual cosa ens permet millorar la monetització de la infraestructura. També hem demostrat que la provisió de capacitat és un mecanisme vàlid, alternatiu a la fixació de preus, per a l'optimització dels beneficis dels proveïdors de servici. Finalment, s'ha demostrat que és possible crear rols específics per a oferir servicis IoT en el mercat de les telecomunicacions, específicament, els IoT-SPs, que proporcionen servicis basats en sensors inalàmbrics utilitzant infraestructures d'accés de tercers i les seues pròpies xarxes de sensors. En resum, en aquesta tesi hem intentat demostrar la viabilitat econòmica de models de negoci basats en xarxes futures IoT, així com l'aparició de noves oportunitats i rols de negoci, la qual cosa ens permet justificar econòmicament el desenrotllament i la implementació de les tecnologies necessàries per a oferir servicis d'accés inalàmbric massiu a dispositius MTC.
Sanchis Cano, Á. (2018). Economic analysis of wireless sensor-based services in the framework of the Internet of Things. A game-theoretical approach [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/102642
TESIS

Although data collection through discrete choice experimentsconducted using surveys are commonly used in research, aimingto improve data quality is still serviceable and necessary. Three distinct experiments were conducted with the objectives of improving data quality by better tailoring experiments to market conditionsas well as decreasing complexity and fatigue. First, consumer willingness-to-pay(WTP) for yogurt attributes was estimatedusing a survey targeted to be nationally representative of the US.A novel approach was used to allow for self-selection into the choice experiment for commonly purchased types of yogurt.On average, respondentswere willing-to-paya positive amount for requiring pasture access and not permitting dehorning/disbudding for both traditional and Greek yogurt. Respondents had positive WTPfor Greek yogurt labeled free of high fructose corn syrup, and were willing-to-pay morefor low-fat yogurt when compared to nonfat for both yogurt types.

Tese de doutoramento em Economia
The wine industry faces an increasingly competitive environment, and the emergence of new producers and consumers reinforced the global dimension of this market. Despite its traditional nature, this industry is rapidly changing, while wine becomes a particular product linking tradition with innovation. Producers are increasingly searching for new opportunities to differentiate their products, hence understanding consumer preferences is crucial. The present dissertation represents an insightful contribution to understand wine choice and the decisionmaking process, in the international market. Moreover, it addresses important methodological issues related to discrete choice experiments and the underlying assumptions that individuals are rational utility maximizers and they choose their preferred option taking into account all available information. However, increasing evidence shows that people use simplifying heuristics to make choices, supporting the alternative of bounded rational behavior which is likely to increase when the good is complex and unfamiliar. The four articles that constitute this dissertation cover some of the challenges that researchers face when valuing a complex good, such as the one under study - wine, by identifying two critical properties of discrete choice models: (i) consumers heterogeneity, both in the scale and in preference, and (ii) the use of heuristics, namely attribute non-attendance, in two different ways, using stated and inferred approaches. On one hand, results show the importance of accounting for both sources of heterogeneity, while the use of latent class model allows the identification of distinct market segments in terms of preference heterogeneity. On the other hand, it provides evidence of attribute non-attendance both in the stated and inferred approaches, showing biased willingness to pay measures when attribute non-attendance is neglected. However, there is little concordance between the rates of non-attendance, which suggests that respondents stated a higher level of attendance than inferred by the model. Finally, we develop an inferred method in a stepwise approach finding all possible combination patterns between attendance and nonattendance. Results show the potential benefits of using this approach combined with other patterns assuming extreme behavior. The improvements considered in each study lead to a better understanding of consumers’ preferences and the choice process in general, showing the adaptability of choice models and their potential as tools for modelling preferences and conduct welfare analysis.
A indústria do vinho enfrenta um ambiente cada vez mais competitivo, pelo que a emergência de novos produtores e consumidores veio reforçar a dimensão global deste mercado. Apesar da sua natureza tradicional, esta indústria tem vindo a mudar rapidamente, enquanto o vinho se torna um produto singular unindo a tradição à inovação. Cada vez mais os produtores procuram novas oportunidades para diferenciar os seus produtos sendo, por isso, crucial conhecer as preferências do consumidor. A presente tese contribui para a compreensão do processo de decisão e escolha de vinho, no âmbito internacional. Metodologicamente, aborda importantes questões associadas à aplicação da técnica de escolhas discretas e, sobretudo, ao pressuposto de que os indivíduos escolhem a sua alternativa preferida tendo em conta toda a informação disponível. Contudo, evidências crescentes mostram que as pessoas usam estratégias simplificadoras quando escolhem, o que indicia um comportamento racional limitado, suscetível de aumentar quando o bem é complexo e desconhecido. Os quatro artigos que constituem esta tese abordam alguns dos desafios quando se estuda um bem complexo, como o vinho, identificando duas propriedades críticas da técnica de escolhas discretas: (i) tratar a heterogeneidade do consumidor, na consistência (escala) e nas preferências e (ii) incluir o uso de heurísticas, nomeadamente o ignorar certos atributos, através das abordagens declarada e inferida. Por um lado, os resultados mostram a importância de considerar ambas as fontes de heterogeneidade, enquanto o modelo de classes latentes permite definir segmentos de consumidores de vinho distintos em termos de diferenças preferenciais. Por outro lado, ambas as abordagens, declarada e inferida, evidenciam a omissão de atributos na escolha, gerando medidas de disposição a pagar enviesadas. No entanto, a concordância entre a intensidade deste comportamento é baixa, o que sugere que os respondentes declararam um nível de atenção aos atributos maior do que o inferido pelo modelo. Por fim, desenvolvemos a técnica inferida que identifica, de forma gradual, todas as combinações possíveis entre ignorar/atender atributos. Os resultados mostram os potenciais benefícios desta metodologia combinada com outros padrões de modelos que assumem comportamentos extremos. Os avanços considerados em cada estudo permitem uma melhor compreensão das preferências dos consumidores e do processo de escolha em geral, revelando a capacidade de adaptação dos modelos de escolha e o seu potencial como ferramentas de modelização de preferências e análise de bem-estar.
I would like to thank the entities that supported this work financially, namely the project INNOVINE & WINE – Innovation Platform of Vine & Wine, Portugal (NORTE-01-0145-FEDER-000038) and the Portuguese Foundation for Science and Technology under the projects UID/SOC/04011/2019 and UID/ECO/03182/2019.

People go through their life making all kinds of decisions, and some of these decisions affect their demand for transportation, for example, their choices of where to live and where to work, how and when to travel and which route to take. Transport related choices are typically time dependent and characterized by large number of alternatives that can be spatially correlated. This thesis deals with models that can be used to analyze and predict discrete choices in large-scale networks. The proposed models and methods are highly relevant for, but not limited to, transport applications. We model decisions as sequences of choices within the dynamic discrete choice framework, also known as parametric Markov decision processes. Such models are known to be difficult to estimate and to apply to make predictions because dynamic programming problems need to be solved in order to compute choice probabilities. In this thesis we show that it is possible to explore the network structure and the flexibility of dynamic programming so that the dynamic discrete choice modeling approach is not only useful to model time dependent choices, but also makes it easier to model large-scale static choices. The thesis consists of seven articles containing a number of models and methods for estimating, applying and testing large-scale discrete choice models. In the following we group the contributions under three themes: route choice modeling, large-scale multivariate extreme value (MEV) model estimation and nonlinear optimization algorithms. Five articles are related to route choice modeling. We propose different dynamic discrete choice models that allow paths to be correlated based on the MEV and mixed logit models. The resulting route choice models become expensive to estimate and we deal with this challenge by proposing innovative methods that allow to reduce the estimation cost. For example, we propose a decomposition method that not only opens up for possibility of mixing, but also speeds up the estimation for simple logit models, which has implications also for traffic simulation. Moreover, we compare the utility maximization and regret minimization decision rules, and we propose a misspecification test for logit-based route choice models. The second theme is related to the estimation of static discrete choice models with large choice sets. We establish that a class of MEV models can be reformulated as dynamic discrete choice models on the networks of correlation structures. These dynamic models can then be estimated quickly using dynamic programming techniques and an efficient nonlinear optimization algorithm. Finally, the third theme focuses on structured quasi-Newton techniques for estimating discrete choice models by maximum likelihood. We examine and adapt switching methods that can be easily integrated into usual optimization algorithms (line search and trust region) to accelerate the estimation process. The proposed dynamic discrete choice models and estimation methods can be used in various discrete choice applications. In the area of big data analytics, models that can deal with large choice sets and sequential choices are important. Our research can therefore be of interest in various demand analysis applications (predictive analytics) or can be integrated with optimization models (prescriptive analytics). Furthermore, our studies indicate the potential of dynamic programming techniques in this context, even for static models, which opens up a variety of future research directions.
Les gens consacrent une importante part de leur existence à prendre diverses décisions, pouvant affecter leur demande en transport, par exemple les choix de lieux d'habitation et de travail, les modes de transport, les heures de départ, le nombre et type de voitures dans le ménage, les itinéraires ... Les choix liés au transport sont généralement fonction du temps et caractérisés par un grand nombre de solutions alternatives qui peuvent être spatialement corrélées. Cette thèse traite de modèles pouvant être utilisés pour analyser et prédire les choix discrets dans les applications liées aux réseaux de grandes tailles. Les modèles et méthodes proposées sont particulièrement pertinents pour les applications en transport, sans toutefois s'y limiter. Nous modélisons les décisions comme des séquences de choix, dans le cadre des choix discrets dynamiques, aussi connus comme processus de décision de Markov paramétriques. Ces modèles sont réputés difficiles à estimer et à appliquer en prédiction, puisque le calcul des probabilités de choix requiert la résolution de problèmes de programmation dynamique. Nous montrons dans cette thèse qu'il est possible d'exploiter la structure du réseau et la flexibilité de la programmation dynamique afin de rendre l'approche de modélisation dynamique en choix discrets non seulement utile pour représenter les choix dépendant du temps, mais également pour modéliser plus facilement des choix statiques au sein d'ensembles de choix de très grande taille. La thèse se compose de sept articles, présentant divers modèles et méthodes d'estimation, leur application ainsi que des expériences numériques sur des modèles de choix discrets de grande taille. Nous regroupons les contributions en trois principales thématiques: modélisation du choix de route, estimation de modèles en valeur extrême multivariée (MEV) de grande taille et algorithmes d'optimisation non-linéaire. Cinq articles sont associés à la modélisation de choix de route. Nous proposons différents modèles de choix discrets dynamiques permettant aux utilités des chemins d'être corrélées, sur base de formulations MEV et logit mixte. Les modèles résultants devenant coûteux à estimer, nous présentons de nouvelles approches permettant de diminuer les efforts de calcul. Nous proposons par exemple une méthode de décomposition qui non seulement ouvre la possibilité d'estimer efficacement des modèles logit mixte, mais également d'accélérer l'estimation de modèles simples comme les modèles logit multinomiaux, ce qui a également des implications en simulation de trafic. De plus, nous comparons les règles de décision basées sur le principe de maximisation d'utilité de celles sur la minimisation du regret pour ce type de modèles. Nous proposons finalement un test statistique sur les erreurs de spécification pour les modèles de choix de route basés sur le logit multinomial. Le second thème porte sur l'estimation de modèles de choix discrets statiques avec de grands ensembles de choix. Nous établissons que certains types de modèles MEV peuvent être reformulés comme des modèles de choix discrets dynamiques, construits sur des réseaux de structure de corrélation. Ces modèles peuvent alors être estimées rapidement en utilisant des techniques de programmation dynamique en combinaison avec un algorithme efficace d'optimisation non-linéaire. La troisième et dernière thématique concerne les algorithmes d'optimisation non-linéaires dans le cadre de l'estimation de modèles complexes de choix discrets par maximum de vraisemblance. Nous examinons et adaptons des méthodes quasi-Newton structurées qui peuvent être facilement intégrées dans des algorithmes d'optimisation usuels (recherche linéaire et région de confiance) afin d'accélérer le processus d'estimation. Les modèles de choix discrets dynamiques et les méthodes d'optimisation proposés peuvent être employés dans diverses applications de choix discrets. Dans le domaine des sciences de données, des modèles qui peuvent traiter de grands ensembles de choix et des ensembles de choix séquentiels sont importants. Nos recherches peuvent dès lors être d'intérêt dans diverses applications d'analyse de la demande (analyse prédictive) ou peuvent être intégrées à des modèles d'optimisation (analyse prescriptive). De plus, nos études mettent en évidence le potentiel des techniques de programmation dynamique dans ce contexte, y compris pour des modèles statiques, ouvrant la voie à de multiples directions de recherche future.

In the first chapter of this dissertation, I outline a hedonic equilibrium model that explicitly controls for moving costs and forward-looking behavior. Hedonic equilibrium models allow researchers to recover willingness to pay for spatially delineated amenities by using the notion that individuals "vote with their feet." However, the hedonic literature and, more recently, the estimable Tiebout sorting model literature, has largely ignored both the costs associated with migration (financial and psychological), as well as the forward-looking behavior that individuals exercise in making location decisions. Each of these omissions could lead to biased estimates of willingness to pay. Building upon dynamic migration models from the labor literature, I estimate a fully dynamic model of individual migration at the national level. By employing a two-step estimation routine, I avoid the computational burden associated with the full recursive solution and can then include a richly-specified, realistic state space. With this model, I am able to perform non-market valuation exercises and learn about the spatial determinants of labor market outcomes in a dynamic setting. Including dynamics has a significant positive impact on the estimates of willingness to pay for air quality. In addition, I find that location-specific amenity values can explain important trends in observed migration patterns in the United States.

The second chapter of this dissertation describes a model which estimates willingness to pay for air quality using property value hedonics techniques. Since Rosen's seminal 1974 paper, property value hedonics has become commonplace in the non-market valuation of environmental amenities, despite a number of well-known methodological problems. In particular, recovery of the marginal willingness to pay function suffers from important endogeneity biases that are difficult to correct with instrumental variables procedures [Epple (1987)]. Bajari and Benkard (2005) propose a "preference inversion" procedure for recovering heterogeneous measures of marginal willingness to pay that avoids these problems. However, using cross-sectional data, their approach imposes unrealistic constraints on the elasticity of marginal willingness to pay. Following Bajari and Benkard's suggestion, I show how data describing repeat purchase decisions by individual home buyers can be used to relax these constraints. Using data on ozone pollution in the Bay Area of California, I find that endogeneity bias and flexibility in the shape of the marginal willingness to pay function are both important.

Finally, in the third chapter of this dissertation, I combine the insights of the Bajari-Benkard inversion approach employed in second chapter with more standard estimation techniques (i.e., Rosen (1974)) to arrive at a new hedonic methodology that allows for flexible and heterogeneous preferences while avoiding the endogeneity problems that plague the traditional Rosen two-stage model. Implementing this estimator using the Bay Area ozone data, I again find evidence of considerable heterogeneity and of endogeneity bias. In particular, I find that a one unit deterioration in air quality (measured in days in which ozone levels exceed the state standards) raises marginal willingness to pay by $145.18 per year. The canonical two-stage Rosen model finds, counter-intuitively, that this same change would reduce marginal willingness to pay by $94.24.

Dissertation

This dissertation consists of three separate essays that use dynamic models to better understand the human capital accumulation process. First, I analyze the role of migration in human capital accumulation and how migration varies over the business cycle. An interesting trend in the data is that, over the period of the Great Recession, overall migration rates in the US remained close to their respective long-term trends. However, migration evolved differently by employment status: unemployed workers were more likely to migrate during the recession and employed workers less likely. To isolate mechanisms explaining this divergence, I estimate a dynamic, non-stationary search model of migration using a national longitudinal survey from 2004-2013. I focus on the role of employment frictions on migration decisions in addition to other explanations in the literature. My results show that a divergence in job offer and job destruction rates caused differing migration incentives by employment status. I also find that migration rates were muted because of the national scope of the Great Recession. Model simulations show that spatial unemployment insurance in the form of a moving subsidy can help workers move to more favorable markets.

In the second essay, my coauthors and I explore the role of information frictions in the acquisition of human capital. Specifically, we investigate the determinants of college attrition in a setting where individuals have imperfect information about their schooling ability and labor market productivity. We estimate a dynamic structural model of schooling and work decisions, where high school graduates choose a bundle of education and work combinations. We take into account the heterogeneity in schooling investments by distinguishing between two- and four-year colleges and graduate school, as well as science and non-science majors for four-year colleges. Individuals may also choose whether to work full-time, part-time, or not at all. A key feature of our approach is to account for correlated learning through college grades and wages, thus implying that individuals may leave or re-enter college as a result of the arrival of new information on their ability and/or productivity. We use our results to quantify the importance of informational frictions in explaining the observed school-to-work transitions and to examine sorting patterns.

In the third essay, my coauthors and I investigate the evolution over the last two decades in the wage returns to schooling and early work experience.

Using data from the 1979 and 1997 panels of the National Longitudinal Survey of Youth, we isolate changes in skill prices from changes in composition by estimating a dynamic model of schooling and work decisions. Importantly, this allows us to account for the endogenous nature of the changes in educational and accumulated work experience over this time period. We find an increase over this period in the returns to working in high school, but a decrease in the returns to working while in college. We also find an increase in the incidence of working in college, but that any detrimental impact of in-college work experience is offset by changes in other observable characteristics. Overall, our decomposition of the evolution in skill premia suggests that both price and composition effects play an important role. The role of unobserved ability is also important.

Dissertation

This dissertation considers incentives arising from equilibrium influences that affect the sequence of decisions that lead to family formation. The first chapter examines how state regulations directly aimed at abortion providers affect the market for abortion in the United States. Estimates from a dynamic model of competition among abortion providers show that regulations' main impact is on the fixed costs of entry for providers. Simulations indicate that the removal of regulations would promote entry and competition among abortion providers, and because abortions are found to be price sensitive, this would lead to increases in the number of abortions observed. The second chapter tests if an important negative externality of abortion access exists, namely whether abortion access makes prospective fathers more likely to leave pregnant women. Designing a number of empirical tests, I confirm that in some areas where abortion is more accessible women who give birth are more likely to be single mothers, rather than sharing parental responsibility with the biological father. The final chapter, which is joint work with Peter Arcidiacono and Marjorie McElroy, examines how gender ratios influence bargaining power in romantic relationships between men and women. Gender ratios, by influencing the prospects of matching, allow us to estimate preferences for various match characteristics and activities. We find men prefer sexual relationships more than women at high school ages, and that men and women trade off their preferred partner for an increased chance of matching.

Dissertation

The goal of this dissertation is to provide a coherent and computationally feasible basis for the analysis of the dynamics of both housing supply and demand from a microeconomics perspective. The dissertation includes two papers which incorporate unique micro data with new methodological approaches to examine housing market dynamics. The first paper models the development decisions of land owners as a dynamic discrete choice problem to recover the primitives of housing supply. The second paper develops a new methodology for dynamically estimating the demand for durable goods, such as housing, when the choice set is large.

In the first paper, using the new data set discussed above, I develop and estimate the first dynamic microeconometric model of supply. Parcel owners maximize the discounted sum of expected per-period profits by choosing the optimal time and nature of construction. In addition to current profits, the owners of land also take into account their expectations about future returns to development, balancing expected future prices against expected future costs. This forward looking behavior is crucial in explaining observed aggregate patterns of construction. Finally, the outcomes generated by the parcel owners' profit maximizing behavior, in addition to observable sales prices, allow me to identify the parameters of the per-period profit function at a fine level of geography.

By modeling the optimal behavior of land owners directly, I can capture important aspects of profits that explain both market volatility and geographic differences in construction rates. In particular, the model captures both the role of expectations and of more abstract costs (such as regulation) in determining the timing and volatility of supply in way that would not be possible using aggregate data. The model returns estimates of the various components of profits: prices, variable costs, and the fixed costs of building, which incorporate both physical and regulatory costs.

Estimates of the model suggest that changes in the value of the right-to-build are the primary cause of house price appreciation, that the demographic characteristics of existing residents are determinants of the cost environment, and that physical and regulatory costs are pro-cyclical. Finally, using estimates of the profit function, I explain the role of dynamics in determining the timing of supply by distinguishing the effects of expected future cost changes from the effects of expected future price changes. A counterfactual simulation suggest that pro-cyclical costs, combined with forward looking behavior, significantly dampen construction volatility. These results sheds light on one of the empirical puzzles of the housing market - what determines the volatility of housing construction?

In the second paper, I outline a tractable model of neighborhood choice in a dynamic setting along with a computationally straightforward estimation approach. The approach allows the observed and unobserved features of each neighborhood to evolve in a completely flexible way and uses information on neighborhood choice and the timing of moves to recover semi-parametrically: (i) preferences for housing and neighborhood attributes, (ii) preferences for the performance of the house as a financial asset, and (iii) moving costs. In order to accommodate a number of important features of housing market, this approach extends methods developed in the recent literature on the dynamic demand for durable goods in a number of key ways. The model and estimation approach are applicable to the study of a wide set of dynamic phenomena in housing markets and cities. These include, for example, the analysis of the microdynamics of residential segregation and gentrification within metropolitan areas. More generally, the model and estimation approach can be easily extended to study the dynamics of housing and labor markets in a system of cities.

Dissertation

This thesis studies the interaction between new and used durable goods without physical depreciation. In product categories such as CDs/DVDs and video games, the competition from used goods markets has been viewed as a serious problem by producers. These products physically depreciate negligibly, but owners' consumption values could depreciate quickly due to satiation. Consequently, used goods that are almost identical to new goods may become available immediately after a new product release. However, the existence of used goods markets also provides consumers with a selling opportunity. If consumers are forward-looking and account for the future resale value of a product in their buying decision, used goods markets could increase the sales of new goods. Thus, whether used good markets are harmful or beneficial to new-good producers is an empirical question. To tackle this question, I extend the previous literature in three ways. First, I assemble a new data set from the Japanese video game market. This unique data set includes not only the sales and prices of new and used goods, but also the resale value of used copies, the quantity of used copies retailers purchased from consumers, and the inventory level of used copies at retailers. Second, I develop a structural model of forward-looking consumers that incorporates (i) new and used goods buying decisions, (ii) used goods selling decisions, (iii) consumer expectations about future prices of new and used goods as well as resale values of used goods, and (iv) the depreciation of both owners' and potential buyers' consumption values. Third, I develop a new Bayesian estimation method to estimate my model. In particular, my method can alleviate the computational burden of estimating non-stationary discrete choice dynamic programming models with continuous state variables that evolve stochastically over time. The estimation results suggest that consumers are forward-looking in the Japanese video game market and the substitutability between new and used video games is quite low. Using the estimates, I quantify the impact of eliminating the used video game market on new-game revenues. I find that the elimination of used video game market could reduce the revenue for a new game.

This dissertation consists of three chapters relating to

identification and inference in dynamic microeconometric models

including dynamic discrete games with many players, dynamic games with

discrete and continuous choices, and semiparametric binary choice and

duration panel data models.

The first chapter provides a framework for estimating large-scale

dynamic discrete choice models (both single- and multi-agent models)

in continuous time. The advantage of working in continuous time is

that state changes occur sequentially, rather than simultaneously,

avoiding a substantial curse of dimensionality that arises in

multi-agent settings. Eliminating this computational bottleneck is

the key to providing a seamless link between estimating the model and

performing post-estimation counterfactuals. While recently developed

two-step estimation techniques have made it possible to estimate

large-scale problems, solving for equilibria remains computationally

challenging. In many cases, the models that applied researchers

estimate do not match the models that are then used to perform

counterfactuals. By modeling decisions in continuous time, we are able

to take advantage of the recent advances in estimation while

preserving a tight link between estimation and policy experiments. We

also consider estimation in situations with imperfectly sampled data,

such as when we do not observe the decision not to move, or when data

is aggregated over time, such as when only discrete-time data are

available at regularly spaced intervals. We illustrate the power of

our framework using several large-scale Monte Carlo experiments.

The second chapter considers semiparametric panel data binary choice

and duration models with fixed effects. Such models are point

identified when at least one regressor has full support on the real

line. It is common in practice, however, to have only discrete or

continuous, but possibly bounded, regressors. We focus on

identification, estimation, and inference for the identified set in

such cases, when the parameters of interest may only be partially

identified. We develop a set of general results for

criterion-function-based estimation and inference in partially

identified models which can be applied to both regular and irregular

models. We apply our general results first to a fixed effects binary

choice panel data model where we obtain a sharp characterization of

the identified set and propose a consistent set estimator,

establishing its rate of convergence under different conditions.

Rates arbitrarily close to n-1/3 are

possible when a continuous, but possibly bounded, regressor is

present. When all regressors are discrete the estimates converge

arbitrarily fast to the identified set. We also propose a

subsampling-based procedure for constructing confidence regions in the

models we consider. Finally, we carry out a series of Monte Carlo

experiments to illustrate and evaluate the proposed procedures. We

also consider extensions to other fixed effects panel data models such

as binary choice models with lagged dependent variables and duration

models.

The third chapter considers nonparametric identification of dynamic

games of incomplete information in which players make both discrete

and continuous choices. Such models are commonly used in applied work

in industrial organization where, for example, firms make discrete

entry and exit decisions followed by continuous investment decisions.

We first review existing identification results for single agent

dynamic discrete choice models before turning to single-agent models

with an additional continuous choice variable and finally to

multi-agent models with both discrete and continuous choices. We

provide conditions for nonparametric identification of the utility

function in both cases.

Dissertation

In this dissertation, I discuss two important factors in individuals' decision-making processes: subjective expectation bias and time-inconsistent preferences. In Chapter I, I look at how individuals' own subjective expectations about certain future events are different from what actually happens in the future, even after controlling for individuals' private information. This difference, which is defined as the expectation bias in this paper, is found to have important influence on individuals' choices. Specifically, I look into the relationship between US elderly's subjective longevity expectation biases and their smoking choices. I find that US elderly tend to over-emphasize the importance of their genetic makeup but underestimate the influence of their health-related choices, such as smoking, on their longevity. This finding can partially explain why even though US elderly are found to be more concerned with their health and more forward-looking than we would have concluded using a model which does not allow for subjective expectation bias, we still observe many smokers. The policy simulation further confirms that if certain public policies can be designed to correct individuals' expectation biases about the effects of their genes and health-related choices on their longevity, then the average smoking rate for the age group analyzed in this paper will go down by about 4%.

In Chapter II, my co-author, Hanming Fang, and I look at one possible explanation to the under-utilization of preventive health care in the United States: procrastination. Procrastination, the phenomenon that individuals postpone certain decisions which incur instantaneous costs but bring long-term benefits, is captured in economics by hyperbolic discount factors and the corresponding time-inconsistent preferences. This chapter extends the semi-parametric identification and estimation method for dynamic discrete choice models using Hotz and Miller's (1993) conditional choice probability approach to the setting where individuals may have hyperbolic discounting time preferences and may be naive about their time inconsistency. We implement the proposed estimation method to US adult women's decisions of undertaking mammography tests to evaluate the importance of present bias and naivety in the under-utilization of mammography, controlling for other potentially important explanatory factors such as age, race, household income, and marital status. Preliminary results show evidence for both present bias and naivety in adult women's decisions of undertaking mammography tests. Using the parameters estimated, we further conduct some policy simulations to quantify the effects of the present bias and naivety on the utilization of preventive health care in the US.

Dissertation