Дисертації з теми "Choice-Based Conjoint Analysi"

Submitted by Marco Antônio de Ramos Chagas (mchagas@ufv.br) on 2016-01-20T10:10:28Z No. of bitstreams: 1 texto completo.pdf: 868133 bytes, checksum: fc299d68c5ac708f6318353d62153283 (MD5)
Made available in DSpace on 2016-01-20T10:10:28Z (GMT). No. of bitstreams: 1 texto completo.pdf: 868133 bytes, checksum: fc299d68c5ac708f6318353d62153283 (MD5) Previous issue date: 2015-02-25
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
A presente dissertação teve como objetivo principal demonstrar um enfoque Bayesiano para a metodologia Choice-Based Conjoint Analysis (CBCA). Apresenta-se no texto uma ampla revisão sobre a CBCA (Capítulo 1), sobre o modelo Logit Multinomial [desenvolvimento do modelo, procedimentos de estimação de parâmetros, probabilidades e razões de escolha (Capítulo 2)] e sobre o enfoque de estimação Bayesiano [distribuição a priori utilizada, aproximação de Laplace para a função de verossimilhança, distribuições a posteriori e detalhes sobre o algoritmo MCMC empregado (Capítulo 3)]. No Capítulo 4 apresenta-se um exemplo hipotético, no intuito de demonstrar os resultados e inferências que podem ser obtidos por meio desta recente abordagem (Bayesiana), sendo também apresentados os resultados do enfoque Frequentista. O tratamento em estudo foi um tipo de refrigerante e avaliou-se o efeito de três fatores (A, B e C) na intenção de compra de 96 consumidores, por meio de dados simulados. As análises estatísticas foram conduzidas no software livre R, cujos scripts encontram-se disponibilizados nos apêndices desta dissertação. Concluiu-se que a abordagem Bayesiana para CBCA apresentou resultados interessantes e satisfatórios, com estimativas similares às Frequentistas e mostrando-se uma alternativa metodológica viável para os estudos de CBCA. Adicionalmente, a abordagem proposta possibilitou ainda ao pesquisador construir intervalos de credibilidade (percentis das distribuições a posteriori) para as probabilidades e razões de escolha, no intuito de comparar estas quantidades ou testar hipóteses sobre estas. Quanto aos resultados práticos, a maior probabilidade de escolha estava associada ao tratamento 4, composto pelo nível do fator A, nível do fator B e nível do fator C.
This dissertation main goal is to demonstrate the Bayesian approach to Choice-Based Conjoint Analysis (CBCA). We present a comprehensive review of the CBCA methodology (Chapter 1), on the Multinomial Logit model [model development, parameter estimation procedures, probabilities of choice ratios (Chapter 2)] and on the Bayesian estimation approach [prior distribution, Laplace approach to the likelihood function, posterior distributions and details about the MCMC algorithm we applied (Chapter 3)]. In Chapter 4 we present a hypothetical example, in order to demonstrate the results and inferences that can be obtained through this recent approach (Bayesian), and we also present the results of the frequentist approach. The treatment for the study was a type of refrigerant (soda or soft drink) and we evaluated the effect of three factors (volume, type and color) on purchase intention of 96 consumers, using simulated data. Statistical analyzes were conducted with the free software R, whose scripts are provided in the appendices of this dissertation. It was concluded that the Bayesian approach to CBCA presented interesting and satisfactory results, with estimates similar to the frequentist ones, therefore proved to be a viable alternative methodology for CBCA studies. Additionally, the proposed approach also allows the researcher to build credibile intervals (percentiles of the posterior distributions) for the probabilities and choice ratios, in order to compare these quantities or test hypotheses about them. In terms of practical or applied results, the highest estimated probability of choice was obtained for treatment 4, with a1 level of factor A, b2 level of factor B and C1 level of factor C.

Up to date, it is unclear how Choice-Based Conjoint (CBC) models perform in terms of forecasting (external) real world aggregate shop data. In this contribution, we measure the performance of a Latent Class CBC model - not with an experimental holdout sample - but with aggregate real world scanning data. We find that the CBC model does not accurately predict real world market shares. In order to improve the forecasting performance, we propose a correction scheme based on external scanner data. Our analysis based on 8 brands shows that the use of the proposed correction vector improves the performance measure considerably. (author's abstract)
Series: Working Papers SFB "Adaptive Information Systems and Modelling in Economics and Management Science"

Conjoint analysis is one of the most important tools to support product development, pricing and positioning decisions in management practice. For this purpose various models have been developed. It is widely accepted that models that take consumer heterogeneity into account, outperform aggregate models in terms of hold-out tasks. The aim of our study is to investigate empirically whether predictions of choice-based conjoint models which incorporate heterogeneity can successfully be generalized to a whole market. To date no studies exist that examine the real world performance of choice-based conjoint models by use of aggregate scanner panel data. Our analysis is based on four commercial choice-based conjoint pricing studies including a total of 43 stock keeping units (SKU) and the corresponding weekly scanning data for approximately two years. An aggregate model serves as a benchmark for the performance of two models that take heterogeneity into account, hierarchical Bayes and latent class. Our empirical analysis demonstrates that, in contrast to the performance using hold-out tasks, the real world performance of hierarchical Bayes and latent class is similar to the performance of the aggregate model. Our results indicate that heterogeneity cannot be generalized to a whole market and suggest that aggregate models are sufficient to predict market shares. (author's abstract)
Series: Report Series SFB "Adaptive Information Systems and Modelling in Economics and Management Science"

One of the major demand related risks for companies that produce consumer electronics goods is change in consumer preferences over time as reflected in the weights they attach to the attributes of products. This contributes to the difficulty of predicting whether consumers will purchase a new product or not and the accuracy of such forecasts can have significant ramifications for companies’ strategies, profitability and even their chances of survival. Knowledge of attribute-weights and accurate forecasts of new products can give companies better insights during the product development stages, inform go-no-go decisions on whether to launch a developed product and also support decisions on whether a recently launched product should be withdrawn or not due to poor early stage sales. Despite the important implications of change in attribute-weights, no research has investigated the extent to which such changes occur and impact on the accuracy of forecasts of the future market share of these products. Prior to the current research, it was assumed that the weights are constant over time – even when the nature of the attributes was assumed to change. To investigate these concerns choice based conjoint (CBC) was applied to data gathered in a longitudinal survey of consumer choices relating a range of consumer electronic products, where innovation has different rates and the product life cycles are various. This allowed an assessment of the extent to which the weights of attributes of choice-based conjoint models change over a six months period for consumer durable products and the degree to which this variability is dependent on the nature of the product. It demonstrates that the change in weights is greater for products that have high technological complexity and shorter lifecycles and also links the changeability of weights to the characteristics of potential consumers. The results of thesis demonstrate that the assumption of constant weights can potentially lead to inaccurate market share forecast for high-tech, short life-cycle products that are launched several months after the choice-based modelling has been conducted.

Choice-Based Conjoint (CBC) models are often used for pricing decisions, especially when scanner data models cannot be applied. Up to date, it is unclear how Choice-Based Conjoint (CBC) models perform in terms of forecasting real-world shop data. In this contribution, we measure the performance of a Latent Class CBC model not by means of an experimental hold-out sample but via aggregate scanner data. We find that the CBC model does not accurately predict real-world market shares, thus leading to wrong pricing decisions. In order to improve its forecasting performance, we propose a correction scheme based on scanner data. Our empirical analysis shows that the hybrid method improves the performance measures considerably. (author's abstract)
Series: Report Series SFB "Adaptive Information Systems and Modelling in Economics and Management Science"

Background: Anecdotal accounts of stereotypes and/or generalisations about perceived generational differences within the workplace have become commonplace. Generational cohort theories are often used to identify generational cohorts of employees that are argued to be different, including having differing expectations, needs, preferences and even values. In addressing and/or accommodating such individual differences organisations are increasingly adopting strategies and interventions that take such generational differences amongst employees into account (Costanza & Finkelstein, 2015). Addressing generational differences within the workplace has particularly become popular in the design and implementation of total reward or remuneration and recognition strategies, policies and practices. Understanding generational and/or demographic characteristics, specifically differences, that create distinct cohorts allow organisations to design reward and recognition packages that create distinctly unique value for their employees. Offering tailored or more focused reward strategies and practices, designed with individual differences in mind are believed to enhance attraction, employee engagement and retention and so allow an organisation to bolster its competitive advantage and contribute to sustained organisational success (Snelgar, Renard, & Venter, 2013). In support of this notion, empirical studies are showing promising results for targeted reward strategies and practices. Rationale for the Research Study Effective talent management, i.e. attracting, engaging and retaining sought-after highly skilled employees is critical for the success of any organisation. However, organisations are increasingly experiencing challenges in recruiting, motivating and retaining scarce human capital, colloquially referred to as talent (Barkhuizen, 2014). Failure on the part of organisations to understand and adapt to differences in the workforce may result in them not being able to attract the talent required; keep employees motivated and engaged; and experience unintended employee turnover which is associated with notable direct and indirect costs for them (Westerman & Yamamura, 2007). Organisations, therefore, are constantly searching for new and innovative approaches to more effectively attract, retain and engage employees (Snelgar et al., 2013). There is a growing body of research (Haynes, 2011; Snelgar, Renard, & Venter, 2013) that has shown that identifying distinct reward and recognition preferences amongst cohorts of employees and targeting reward and recognition strategies accordingly, is showing promising potential in this regard. When designing and implementing targeted approaches to reward and recognition, employee cohorts are most often identified using generational cohort theory, i.e. using various established guidelines to group employees into generational cohorts that are believed to be distinctly different to one another, while those within these groups being more similar than not. Results obtained from studies using these various employee cohorts as a framework have been used to inform the design of targeted reward and recognition practices and policies. Generational cohort theory is, however, mostly grounded on a set of historical events that took place in the United States of America (USA). Despite this, the American-based framework used to identify individuals belonging to various generations has been adopted globally, both within organisations and even used in research studies published in peer-reviewed literature. However, several authors have criticised the indiscriminate use of a popular American-based generational framework, i.e. focusing on events affecting Americans arguing that this has resulted in a somewhat narrow or even skewed view generational cohorts. These authors have gone as far as to argue that the American-based generational framework may not be appropriate or ineffective outside of the USA at all (Close, 2015). Following this reasoning, they have called for alternative frameworks that create distinct generational cohorts relevant in contexts outside of America, i.e. based on different events and criteria more applicable to those contexts. Aim of the research study The aim of the present study was to investigate the reward preferences of a broad range of employees in an effort to assess whether the popular generational model of Strauss and Howe (1991) is relevant and/or as effective in a non-American context, as well as to possibly find support for alternative perspectives or approaches to identify distinct generational cohorts in organisations that may be more appropriate and/or effective when designing reward offerings for different cohorts of employees. Given time and cost constraints, South Africa was chosen to investigate this claim given that it is a developing economy (vs the USA being a developed economy) and has a different set of notable events that have shaped its history to that which is applicable to the USA. Given the aim of the present study, an exploratory research design was considered most appropriate to investigate generational cohort theory within a non-American context as a framework to identify employee groups/cohorts that have distinctly different total reward preferences. For the purposes of the present study, it was decided that a quantitative approach would be followed as it is most useful to draw conclusions or inferences related to the total reward preferences of employee groups/cohorts. The present study followed a non–probability or convenience sampling approach with a realised sample of 169 respondents. The majority of respondents were Coloured and were further female, with majority of attaining a qualification post matric. Main results and findings A one-way Analysis of Variance (ANOVA) revealed no statistically significant difference between the generational groups based on the popular generational model of Strauss and Howe (1991), nor for a proposed generational cohort framework that was designed for the purposes of the present study and which was based on notable South African historical events. Following a data-driven exploratory approach, cluster analysis, on the other hand, yielded three distinct generational cohorts based on their perceived reward preferences for typical total rewards elements. Significant differences in the total reward preferences of respondents born after 1994 and those before 1994. Choice-based modelling (choice-based conjoint analysis) revealed that most respondents considered financial rewards as being the two most preferred total reward elements for them, including remuneration (guaranteed pay) followed by benefits and then non-financial rewards (work-life balance being the most preferred non-financial reward preference). Theoretical and Practical Implications Numerous research studies have made use of the popular American-based generational model to identify the reward preferences of cohort groups, without taking into account context-specific variables. There is further a dearth of empirical research that has been conducted to investigate generational cohort theory specifically, while none were found that were conducted in developing economies, such as South Africa. The present study address this gap in current literature. The use of choice-based modelling or choice-based conjoint analysis, furthermore, makes a methodological contribution given that this method is seldom found in total reward preference studies. This method was shown to identify total reward preferences that could not be determined using a field-survey or questionnaire. Choice-based modelling is different to typical survey approaches in that it is better able to replicate human decision making, i.e. assessing relative importance of attributes and levels based on combinations of choices and related sacrifices that humans deal with when making a choice-decision. In terms of the practical contribution of the present study, the results provide insights for organisations that may be incorporated when designing differentiated total reward strategies to accommodate and/or address the needs of the different generational groups.

Orientation: Organisations operating in multiple countries and continents, referred to as multinationals, often experience cultural barriers when interacting with employees from the host county. These barriers, in turn, frequently result in counterproductive outcomes for the organisation. Being able to adapt Human Resource (HR) policies and practices to the cultural values and norms of the host country, multinationals will be better able to attract, motivate and retain their host country employees and achieve the strategic objectives they have set. Research purpose: The aim of the current study was to investigate the relationship between an individual's reward preference and his/her cultural orientation by means of a novel methodological approach, while further investigating this relationship in two culturally distinct countries to allow for a comparison to be made. Motivation for the study: Research linking rewards to cultural orientation is characterised by mixed findings, which could be related to cross-cultural measurement issues (for example, issues of level of analysis and the reference-group effect). By measuring at an individual level of analysis and exploring the use of choice-based conjoint analysis, the present study aimed to advance the field of cross-cultural remuneration research. The study aimed to show that, by linking cultural orientation and reward preference, multinationals can be helped to optimize their remuneration policies and practices in a way that brings about desired organisational outcomes. Research design: A descriptive research design using quantitative methods was employed. Data was collected from employees in both South Africa (n = 132) and the Netherlands (n = 152). Survey items, responded to on a Likert-type response scale were used to measure an individual's reward preference and cultural orientation. To explore the potential bias introduced by the reference-group effect in cross-cultural reward research, a choice-based conjoint analysis was included to measure reward preference. Data from the field survey was analysed using descriptive and inferential statistics. Choice-based conjoint analysis was used to determine the relative importance of each reward element. Main findings: The results of the Multiple Regression analysis revealed that certain cultural orientations were significantly positively related to reward preference. These included the relationship between collectivism and group bonuses; uncertainty avoidance and job security; uncertainty avoidance and base pay; and long-term orientation and future oriented rewards. Uncertainty avoidance and long-term orientation were positively related to financiallyoriented reward elements. The conjoint analysis allowed for further differentiation between these elements. Practical implications: Multinationals will be able to better align their reward policies and practices with the preferences of employees who come from different cultures and who therefore possess differing cultural orientations. By doing so, multinationals will be able to improve their capability to attract, motivate and retain employees that come from distinct cultural backgrounds. Research contributions: By taking a different methodological approach using choice-based conjoint analysis, this study showed that the preference for particular reward packages can not be solely reduced to linear relationships. In contrast to previous studies, this study was able to incorporate a single sample for both the dependent and the independent variables by measuring the cultural orientations at an individual level of analysis.

A substantial proportion of older adults with non-inflammatory joint pain do not consult their general practitioner (GP) despite apparent clinical need. This thesis describes the development, execution, and interpretation of an original study using conjoint analysis – a fairly novel approach with some advantages over conventional observational and qualitative studies - to understand the relative importance of need-related and service-related factors on the decision to consult the GP. Background reading, a systematic review of previously published conjoint analysis studies, and a series of developmental studies involving patients and members of the public informed the design of the main study. A partial-profile choice-based conjoint (PPCBC) questionnaire was chosen, comprising 10 choice tasks using a combination of selected attributes (pain characteristics, pain disruption to everyday life, comorbidity, assessment and investigations available, available treatment options, and perceived GP attitude). The PPCBC questionnaire was postally-administered to 1170 adults aged 50 years and over with hip, knee, or hand pain identified from an existing population cohort study in North Staffordshire. 863 questionnaires were returned (adjusted response rate 74%; mean age: 70 years; 55% female) and well-completed ( < 5% missing data). The extent to which pain disrupted everyday life (1.10 logits) and perceived GP attitude (0.86 logits) were the most important determinants of the decision to consult the GP. Service factors were highly influential with a ‘negative’ GP attitude potentially outweighing the perceived value of optimal assessment and management. Latent class analysis identified possible subgroups with differing strengths of preference. Conjoint analysis is feasible and offers unique insights into the relative importance of actual and hypothetical services. While it presents many challenges - extensive developmental testing, complex design and analysis procedures, ability to integrate findings from a range of different methods – it can provide important information on patients’ preferences for existing and emerging treatments and models of care.

In many studies, choice based conjoint analysis is used to build a market simulator to develop marketing strategies; i.e., shares-of-preference are taken as market share forecasts. However, conjoint data are collected in interview situations, which may differ considerably from real shopping behavior. In this paper, we test the internal and external validity of four commercial choice based conjoint pricing studies including a total of 43 brands. We use conjoint and sales data to assess the relative performance of two modern approaches to estimate conjoint parameters: the segmentation based Latent Class model and the individual level Hierarchical Bayes approach. Our paper confirms previous results of the internal superiority of the Hierarchical Bayes approach. The main result of our investigation is that internal validity does not predict external validity and that Latent Class shows the same real world performance as Hierarchical Bayes. Both models show an average error of 4.2% in market share level prediction and a correlation of 69% between conjoint forecasts and real market shares. (author's abstract)
Series: Working Papers SFB "Adaptive Information Systems and Modelling in Economics and Management Science"

Widespread car usage of around 800 million of cars travelling 30 billion of kilometres on a daily basis has led to many benefits but also to significant environmental and societal impacts such as congestion, air and noise pollution and urban sprawl. This thesis aims to investigate the stakeholder values of car parking in order to support and inform the decision makers who are tasked with how best to resolve challenging car parking dilemmas. A two phase progressive methodology is involved. Phase one begins with conducting a series of in-depth semi-structured interviews with eight academics to identify whom the stakeholders are that are affected by car parking. Then a second series of 20 interviews are conducted with sector leaders of stakeholder groups to establish how the stakeholders are affected by car parking and importantly, how they value car parking. Finally a third series of nine interviews are conducted with nine different experts to help to bridge the gap between phase one and phase two. Phase one found that a broader reach of stakeholders (classified into four different groups) are affected by car parking than the literature might imply, and that they value car parking in eight different key ways. It also found that the values emerged from a context of governmental, social and consumer concerns. Phase two of the methodology was quantitative and used the findings from phase one to develop four additional attributes considered meaningful across all four stakeholder groups, namely: safety, politics, public spaces and weekly household council tax. Choice based conjoint analysis was used to incorporate the attributes into three hypothetical scenarios namely; driver, strategy and social, as these were considered to be reflective of the value context unearthed previously in phase one. The scenarios were disseminated across England as part of a wider survey and achieved a sample size of 1107 responses. The results of which were then interpreted through willingness to pay (WTP) values. Key findings included: how a persistent political undertone can impact on car parking policy setting; that the car parking industry is under pressure to provide a service chiefly motivated by a perceived consumer intolerance of market prices; and that stakeholders can not only appreciate but also experience the impact of car parking choices on other stakeholder groups. Conclusions drawn included that the different stakeholder groups took issue with national government leadership believing it to currently be deficient in setting the standards for British car parking. Moreover, decision makers wrongly perceive that consumers of car parking do not pass between the groups and are therefore hostile to policies which do not directly benefit them. The key implication being that decision makers are cautious to implement policies which are not necessarily advantageous to consumers but which may lead to gains for the remaining stakeholder groups. In short, this thesis recommends amongst others that the governmental stakeholder group should seek to provide direction and guidelines for tariff setting which is reflective of the provision of a service that is conscious of the range of parking industry stakeholder values. Furthermore, as safety is an industry held value, practitioners should seek to better understand how it impacts their market. They should explore the relevance of schemes such as Park Mark to operators and their customers, by fundamentally investigating to what extent safety exists as a valid concern inside car parks and how it applies to personal safety, vehicle safety or general perceptions of safety. In addition, where the governmental stakeholder group remain mindful of the significance of securing political backing, the car parking industry would benefit from appreciating the sensitivities of political challenges faced by the governmental group when lobbying for any changes in parking policy programmes. Indeed, the parking industry should collaborate between the two parties and seek to unite in finding agreeable solutions which benefit constituents either directly or indirectly. As car parking values might differ according to their geopolitical context and lead to the extraction of a different set of attributes, further work would include looking beyond England to first the UK and then to abroad to explore the effects of potential cultural differences and learn the relevant lessons.

Business Administration/Marketing
D.B.A.
Thought leadership is a term that has been around for more than a decade. Little research has been done on exactly what thought leadership is or how to become a thought leader. Yet the business press is full or articles touting the importance of becoming a thought leader along with a variety of benefits. Additionally, social media has become an increasingly important part of any marketing strategy. This paper begins by developing a typology of business to business CEO social media presence, it clearly defines the three key attributes of a thought leader and concludes with identifying which attributes are the most important in CEO thought leadership. Chief Executive Officers (CEOs) are generally expected to represent the public face of the company, and their leadership is critical to success in product-service markets. Social media platforms offer CEOs the opportunity to benefit their companies by demonstrating leadership, communicating ideas, and motivating others, often with a personalized touch. Yet, many CEOs, particularly in business-to-business (B2B) firms, are relatively new to social media and do not have a clear social media strategy. A typology of B2B CEO social media presence was developed by utilizing cluster analysis to analyze a cross-section of B2B CEOs’ social media activity. Results shows that the Reluctants, constituting 74% of the sample, have little or no social media presence. Of CEOs with some social media presence, the main types are LinkedIn Leveragers who have a substantial LinkedIn presence only, and TweetStars, who are active only on Twitter. A CEO who is a thought leader is a business leader who communicates ideas in a way that motivates others to develop them and is recognized by others outside of their organization. Using the three attributes of thought leadership – communication, motivation of others, and public recognition, a survey was conducted to identify which of these attributes were the most important in increasing perceived thought leadership. Using choice based conjoint analysis to test the level of perceived thought leadership, public recognition followed closely by motivation were most important in contributing to perceived thought leadership. The typology developed in this paper leads to the development of a set of empirical propositions for future research. Insights gained from this analysis can help companies and their CEOs make informed decisions on their social media options and strategies. The identification of what attributes are most important to increase levels of perceived thought leadership lays the foundation for additional research. Recommendations offered in this paper can help companies and CEOs invest their resources in a marketing strategy appropriate to their goals.
Temple University--Theses

Environment and its conservation is one of the key issues across the globe these days. It is even more important in the Scandinavian region.Swedenis one of the leading pro-environment nations in the world when it comes to environment-friendly or green automobiles. Introducing emissions tax, green car rebate, and congestion tax exemption for green cars on large cities have resulted in a surge of green car sales inSwedenover the past few years. The preferences of the Swedish green car consumers are examined in this study.   Consumer decision process and preferences related theories have been used for the theoretical understanding of this study and based on these understandings, the Adaptive Choice Based Conjoint Analysis has been selected to measure and understand the consumer preferences towards green cars. The Swedish green car market has been explained and understood as a prerequisite to conduct this study. Examinations of previous related studies, a small scale pre-screening survey, and expert interviews were carried out prior to formulating the conjoint experiment to ensure the inclusion of significant components into the study. The collected data were analyzed using advanced analysis software such as, SSI Web, SMRT, and SPSS, to understand and measure consumer preferences. The findings provide answers to the importance of different attributes in the purchase decision-making for green cars, the effect of each attribute to the decision-making process, the effect of prior purchase experience on the formation of preference, and the relationship between consumer’s green consciousness level and green decision-making process.   This study contributes to the theoretical field of green consumer behavior and to the practical field of marketing of green cars. The study also identifies and recommends key areas of interest that warrant further research.   Key Words: High Involvement Purchase, Green Consumer Behavior, Conjoint Analysis, Adaptive Choice Based Conjoint Analysis (ACBC), Green Preference, Green Car.

Conjoint analysis is a popular method in consumer preferences research. One of the factors that caused the increasing popularity of this method in recent years is wide use of hierarchical Bayesian models which has been found invaluable in solving the problem of how to obtain reliable estimates of individual preferences without need for overloading respondents with too many conjoint tasks. First goal of my dissertation was to confirm whether the use of Bayesian models is the best choice under all circumstances or whether there are some limitations of this approach. For this purpose I conducted a study based on simulated datasets. Algorithm used enabled generation of datasets that differed in several parameters of interest but which were most comparable in other aspects. Results show that hierarchical models represent choice leading to highest accuracy in predicting respondents' choices in holdout tasks. Use of hierarchical models is most beneficial in the situation of strongly heterogeneous population yet limited amount of available data. In these cases we are able to capture the structure of heterogeneity with significantly lower number of choice task necessary from each respondent. Second goal of the dissertation was to answer the question whether we can increase also the effectiveness of the questioning in conjoint analysis by adding several direct questions. Suggested hybrid choice-based conjoint method (HCBC) combines conjoint analysis tasks with direct questions regarding the preference of levels for each attribute. These are used during the estimation of the model and for increasing the effectiveness if the conjoint analysis tasks design. The HCBC was compared with traditional choice-based conjoint (CBC) and adaptive choice-based conjoint (ACBC) based on practical study involving 421 respondents randomly assigned in one of three test groups. Suggested method has been found as useful alternative that can help with reducing number of choice task needed and as a solution for some situations when diverse importance of the attributes tested does not allow for indirect estimation of preferences with respect to all attributes tested.

Perception of scale is important to our activity within a space and to our experience of a landscape. This presents a problem if people cannot predict or convey the scale effects of large structures proposed in a landscape, as has been the case for recent wind turbine proposals in Scotland. To address this problem, this research explored how people perceive scale and scale effects in a landscape. It took wind turbines as an example structure and analysed how different scales of windfarm create different scale effects in different landscapes, as well as how to best assess and communicate these effects. The research applied three methods to address the research questions: Landscape and Visual Impact Assessment (LVIA), which is a standard, structured process applied by professional landscape architects; experiential landscape assessment, which included semi-structured interviews with local people in addition to site assessment; and public attitude and preference study, which included Adaptive Choice-Based Conjoint analysis (ACBC). These different methods allowed the research questions to be explored in different ways, while overlapping in some aspects and providing triangulation. The research findings revealed that our perception of scale and scale effects in a landscape is influenced by numerous attributes and depends on how these are experienced together. Building upon the theoretical background, an important difference between visual scale and spatial scale was highlighted, as well as alternative ways in which scale references are made. Throughout the research, the need for clear communication was emphasised and the findings included identifying the specific words that people use to describe scale effects in the most discriminating way. This research supported other studies in finding that consultation with local people (professionals and the public) was vital to understand in sufficient depth how a landscape was perceived, experienced and valued. In addition, the innovative development of Conjoint Analysis demonstrated how this method can reveal how people judge the relative importance of different attributes that influence landscape and visual effects and, by doing so, offer new possibilities as a tool in landscape research. Building upon the general findings concerning scale, specific findings regarding the scale effects of windfarms included: greater influence of the proximity of a windfarm than size or numbers of wind turbines; greater importance for being in private and/or fixed locations that offer a sense of refuge compared to public locations and/or when moving; the importance of collective effects perceived and experienced by a community; the importance of perceived spatial separation between a viewer and a windfarm (affecting sensitivity to scale effects within open settings); and differences in how people judge the importance of horizontal scale effects compared to vertical scale effects. The research findings contribute to the knowledge and understanding of people’s perception of scale and scale effects in a landscape and they counter some common assumptions and current practice in landscape architecture. They can be applied in practice and policy to help assess scale effects, convey more clearly to people the type of scale effects and how these will affect them, and minimise the adverse scale effects of windfarms through siting and design. The thesis also identifies how to build upon these findings in the future, including recommendations for additional research, new approaches to assessment (including the use of prompt lists) and thresholds for acceptability of scale effects.

Statistics
Ph.D.
Choice-based conjoint experiments are used when choice alternatives can be described in terms of attributes. The objective is to infer the value that respondents attach to attribute levels. This method involves the design of profiles on the basis of attributes specified at certain levels. Respondents are presented sets of profiles called choice sets, and asked to select the one they consider best. Sets with no dominating or dominated profiles are called Pareto Optimal sets. Information Per Profile (IPP) is used as an optimality criteria to compare designs with different numbers of profiles. For a 2^n experiment, the optimality of connected main effects plans based on two consecutive choice sets, Sl and Sl+1, has been examined in the literature. In this thesis we examine the IPP of both consecutive and non-consecutive choice sets and show that IPP can be maximized under certain conditions. We show that non-consecutive choice sets have higher IPP than consecutive choice sets for n ≥ 4. We also examine the optimality of connected first-order-interaction designs based on three choice sets and show that non-consecutive choice sets have higher IPP than consecutive choice sets under certain conditions. Further, we examine the D-, A- and E-optimality of consecutive and non-consecutive PO choice sets with maximum IPP. Finally, we consider 3^n choice experiments. We look for the optimal PO choice sets and examine their IPP, D-, A- and E-optimality, as well as comparing consecutive and non-consecutive choice sets.
Temple University--Theses

This research is the outcome of a preeminent interest in the topic of price perception. Pointedly, the perception of prices is part of the purchasing process, the same willingness to pay and the actual purchase behaviour, and is indubitably a perceptual construct. As such, perception is problematic to measure as it does not relate to an observable behaviour. On the other hand, pricing is regarded as an important variable in the marketing mix. This research contributes to theory by augmenting the current knowledge on the perception of prices including the methods used in the measurement of such perception. Moreover, this research addresses a gap in the understanding of how diverse ethnic groups perceive prices. The relationship set in this study between ethnicity and price perception is thought-provoking as it contributes to the current discussion around diversity in the marketplace. For example, the literature shows advances in areas such as multicultural and ethnic marketing and this research makes a significant contribution to these areas from price perception. Accordingly, this study involved a systematic review of the literature and presented a framework that suggested that the formation of price perception is affected by external factors such as culture and ethnicity. Furthermore, a qualitative study examined the formation of price perception around ethnic groups. Next, this research used a quantitative study that sought differences in price perception among ethnic groups. Thus, the quantitative study used a price perception scale (Lichtenstein et al., 1993) and a choice-based conjoint analysis. Also, the study adopted structural equation modelling (SEM) to measure differences among scales and the multinomial logit model to analyse the choice-based conjoint analysis. The findings of both the quantitative and the qualitative studies link to the systematic review and support the framework for the formation and measurement of price perception originally proposed.

O mercado de Educação Superior privado no Brasil apresenta altos índices de concentração, caracterizando-se como um oligopólio, podendo, portanto, ser estudado sob a ótica da Teoria dos Jogos. Uma das técnicas existentes para abordar este tipo de mercado é conhecida por Análise Conjunta Baseada em Escolhas (Choice Based Conjoint Analysis), que permite estimar as utilidades atribuídas para cada característica dos produtos, prevendo o desejo de cada produto gerado pela combinação dos seus atributos, possibilitando, assim, simular como as decisões de uma amostra de respondentes seriam distribuídas em um mercado simulado entre dois ou mais produtos competidores. Esses modelos, porém, limitam-se a maximizar a receita individual de cada produto, de forma isolada, não levando em conta a possibilidade das firmas terem interesses em maximizar a soma de dois ou mais produtos de forma conjunta. Isso se torna necessário, por exemplo, quando uma empresa comercializa dois produtos que competem no mesmo mercado. Com o objetivo de maximizar a receita conjunta de dois ou mais produtos, foi desenvolvido um método alternativo, baseado em Programação Não-Linar, que foi aplicado em uma cidade brasileira e em um país centro-americano. A comparação dos resultados do modelo desenvolvido com os do modelo tradicional evidencia que o modelo desenvolvido apresenta melhores resultados – soma das receitas das firmas de interesse – gerando uma taxa de crescimento na receita 3% maior, no caso brasileiro e 75% maior no estudo centro-americano. O modelo desenvolvido pode ser adaptado e utilizado em outros mercados oligopolistas ou para otimizar diferentes funções-objetivo.
The Brazilian Higher Education private market shows high levels of concentration and can be considered an oligopoly. Therefore, one can study it as a Game Theory problem. Choice Based Conjoint Analysis – a technic that can be used to approach this kind of market – can estimates the utilities of each products’ features and predict the desire of each product generated by the combination of its attributes. Such technic can simulate how the decisions of a sample of respondents would be distributed among the products of a market made of two or more competitor. These models, however, only maximize the revenues of individual products, not considering the possibility of firms wanting to maximize the sum of the revenue of two or more products. This is useful, for instance, when a company trends two or more products that compete in the same market. An alternative method, based on nonlinear programming, was developed, in order to maximize the conjoint revenue of two or more products and it was applied in a Brazilian city and in a Central American country. Comparing both models – the traditional versus the developed one –, we can see that the developed model shows better outcomes – ie, sum of both companies’ revenues – resulting in a revenue increase rate 3% higher in the Brazilian case and 75% higher in the Central American study. This model can be fitted to other oligopolistic markets or to optimize others objective functions.

Les systèmes de santé accordent une attention croissante au point de vue des usagers dans l’organisation de l’offre de soins. L’instauration d’une offre de soins sensible aux besoins et préférences des patients constitue un enjeu majeur de qualité et d’efficacité des soins. Ce travail analyse le point de vue des patients pour l’offre de soins de médecine générale en utilisant différentes méthodes permettant d’obtenir des informations complémentaires en termes d’expérience de soins, de satisfaction, d’importance ou encore de préférences. Il s’agit des méthodes Delphi, de classement du meilleur au pire et de révélation des préférences par les choix discrets. Ces méthodes sont appliquées sur deux échantillons : en population générale pour la première et chez des patients poly-pathologiques pour les 2 autres afin d’identifier les principaux enjeux actuels et à venir de la réorganisation de l’offre de soins de médecine générale du point de vue des patients. Les résultats montrent le rôle central de la relation médecin-patient et plus particulièrement de l’échange d‘informations entre le médecin et le patient. Cependant une relation médecin-patient de qualité ne doit pas pour autant être réalisée au détriment de la qualité technique du soin et de la coordination de la prise en charge du patient. Ce travail montre également l’importance de prendre en compte l’expérience de soins des patients lors de l’analyse de leur point de vue, et plus particulièrement de leur disposition au changement. L’évaluation systématique et régulière des préférences des patients en pratique quotidienne peut permettre d’améliorer la communication médecin-patient ainsi que le contenu de l’offre de soins du point de vue des patients
The healthcare systems are paying a great interest to the patients’ perspective for the organization of health care provision. Healthcare system which is accountable and responsive of patients’ needs and preferences is a major issue for the quality and efficiency of care. In this thesis, we analyze the views of patients for the supply of GP care in using different complementary methods about patients’ experience, satisfaction, importance or preferences. These methods are applied to a sample of patients in GP and to a sample of chronically ill patients in order to identify current and future major issues for the reorganization of GP care from the patients’ perspective. The results show the main role of the doctor-patient relationship and especially of the information exchange between doctor and patient and between patient and doctor. However the quality of the doctor-patient relationship is not enough. The technical quality of care (i.e. thoroughness) and the coordination are of high importance for patients. This work highlights that it is necessary to take into account the patients’ experiences in the analysis of their perspective (e.g. preferences) to fully and appropriately understand the results, especially in terms of willingness to change. The systematic and regular screening of patient preferences in daily GP practice can improve the doctor-patient communication and the content of the provision of care from the perspective of patients

Conjoint analysis is a widely used marketing research tool for analyzing consumer preferences for a set of product/service attributes and estimating part-worths for the levels of each attribute. Although numerous studies have confirmed the reliability and validity of part-worth estimates, several studies have reported what was called the Number of Levels (NOL) effect, especially in full-profile conjoint designs. The NOL effect occurs in conjoint analysis when the estimated relative importance weight of an attribute increases as a function of the number of levels by which it is defined. This study investigates the NOL effect for Adaptive and Choice-Based Conjoint Analysis (ACA and CBC), two increasingly popular data collection methods. Three experiments were conducted with 684 physicians in Canada to test the hypothesis that NOL effect will be observed for both ACA and CBC but the effect will be stronger for CBC than ACA. The findings suggest that while CBC suffers from the NOL effect, ACA does not. The results also suggest that a less important attribute may be more susceptible to the NOL effect. Given the findings, it is recommended that when CBC is used it is better to have equal number of levels across all attributes in the conjoint design whenever possible. Also, relative importance weights from two different studies where the number of levels differ should not be compared. ACA does not seem to have these limitations.

碩士
國立臺灣大學
國際企業學研究所
95
In recent years, consumers are more request for necessity because quality of life ascent. Besides brand, flavor and package, there are many new function with treatment and healthy in the market of toothpaste in recent ten years. Every manufacturing also produce new function and treatment in toothpaste to satisfy changeable necessary of customers. This article will research the structure of preference about the toothpaste product by using conjoint analysis. This study uses choice-based conjoint (CBC) analysis, utilizes multinomial logit model in CBC software to analyze the data. According to this data, the respondents are segmented by cluster analysis and each cluster is characterized by variable, such as lifestyles and involvement. The purpose of this study is to set the model of market segmentation in effect and offer marketing strategies to toothpaste manufacturing. Concluding and suggestion results the meaning of marketing and management, and explains the limiting factor of tins study and recommends future research directions.

碩士
臺灣大學
國際企業學研究所
95
Cell phone has become more and more popular, and given the big opportunities of business in Taiwan. There have been lots of firms, including international and local brands, getting into this fierce competition, and leading the cell phone market to become saturated, even declined a little bit. How to outshine others in this saturated market is most important for cell phone manufacturers. At the present time, there are thousand kinds of cell phone products on the market, but what kind of term can attract consumers to purchase, which is the main research purpose of this thesis. This research uses the choice-based conjoint analysis, with the undergraduate and graduate students of Taipei for research object. Utilizing multinomial logit model in CBC software by Sawtooth to analyze the data and to study the relative importance of cell phone attributes. Then using Part-Worth Utility as the basis to classify total users into four market segments, which are “price orientation segment”, “Korean series reception segment”, “low level involvement segment”, and “low price sensitivity segment”, and discussing the correlations between market segments and life groups, personality, and the influences of different market segments on purchase behaviors. To sum up analyzed data and results, I make conclusion and suggestion with the meaning of marketing, explain the research limitation this research faces and recommend future research directions.

Consumer preference measurement is a quantitative field of study for modeling, collecting and analyzing product decisions by consumers. Discovering how consumers choose products is an important area of marketing research and recognized as a successful partnership between academic theory and practice over the past forty years. Despite preference measurement’s success in consumer products, little guidance is available for its application to software product management. This paper assesses the feasibility of applying advanced preference measurement techniques to software products and suggests a framework for conducting such studies. A summary of the methods is provided to give guidance to software product managers seeking to apply preference measurement to common product decisions. The paper concludes by recommending a technique called ‘maximum difference scaling’ to elicit customer feedback to help measure the importance of new features for software product improvement.
text

碩士
國立中興大學
科技管理研究所
106
In recent years, mobile payment services have been widely used in our daily life. It not only changes payment methods to consumers, but also influences merchants’ business model. With the arrival of Apple Pay, Samsung Pay, and Google Pay in Taiwan have increased the competition in mobile payment industry. How to catch up with this trend under sheer competition from global mobile payment players becomes an important issue for Taiwanese mobile payment service providers. This study uses Hierarchical Bayes Choice-Based conjoint (HB-CBC) analysis to determine the preferences of consumers and merchants on mobile payments. This method allows respondents to experience simulated consumption situation and capture their trade-offs between products attributes. Based on individual preference, market segments of Taiwanese mobile payments could be identified and mobile payment service providers could determine appropriate services to their target segments. With a clearly defined target audience, Taiwanese mobile payment providers could develop their product strategies to keep up with competitors and sustain continuous market growth.

碩士
國立中興大學
應用經濟學系所
107
In recent years, because of the improvement of income and living standards, the demand on tea quality by consumer have become higher and higher through the years，tea have become a culture, an art, instead of just a drink. Consumer no longer limit their concern on quality of tea, but to extrinsic attribute, for example origin, award record, product package, certification. It has become a crucial task for producer to gain popularity among consumer and out preformed other competitor in a competitive market, therefore the main purpose of this thesis is to find consumer’s structure of preference toward tea. Choice Based Conjoint Analysis will be used in this research to find consumer’s structure of preference toward tea. XLSTAT will be used to design conjoint analysis experiment, multinomial logit model will be used to analyzing data to find out the part worth value of each respondent toward each attribute level. Then by using part worth value as a reference, we will be able to segment respondents with similar preference into groups, and their most preferred product combination. Then we’ll be using SPSS to run a chi-square analysis between each segment and consumer habit, drinking habit and population variables to test whether there’s a connection between them. At last we will be using a market simulation tool to find the market share of 14 products designed in this research with every respondent and each segment. The empirical results shows the importance of the attributes to subject in order is price, origin label, type of tea, image of the outer packaging, brand, award record and package. Then according to consumer’s preference to each attribute and level , we divided them into 4 clusters. The first group preferred black tea, affordable prices, award-winning records, indications of origin, practical overall image, novelty of packaging and famous brands. Most of the subjects are under 30 years old, which care mostly about the price and aroma of tea, therefore the design of the product should emphasize the difference in the price and the aroma of tea ,with novelty packaging; the second group preferred oolong tea, affordable price, award-winning record, indication of origin, practical The overall image, regular package and famous brands, the frequency of drinking tea and the preference for taste tea is higher than other clusters. The group believes that drinking tea could control weight. Therefore, when designing products, we should try to lower the price of packaging design, produce high-quality oolong tea, emphasize the taste of tea and function of controlling weight; the third group preferred black tea, affordable price, award-winning record, and indication of origin, practical overall image, regular packaging style and famous brands, the group has the highest preference for black tea, second highest frequency of drinking tea, pays special attention to the origin of tea, and has strong loyalty to the origin. So the product should be consistent with their preference in order to increases their loyalty; the fourth group preferred oolong tea, high price, award-winning record, indication of origin, classic outer image, novel creative packaging and farmer association brand. This group cares most about packaging and tea leaves comparing to others. This group also believed that drinking tea can control weight and help them make friends, but the response to other attributes is not high. Therefore, it is recommended that tea producers should cooperate with the farmer association to design a novelty packaging, and emphasize that you can control your weight and make friends by drinking tea, to attract consumers'' interest in tea, in order to change their preference and consumption behavior.