Littérature scientifique sur le sujet « Public procurement, auction, non-parametric estimation »

Abstract Motivated by the prevalence of simultaneous bidding across a wide range of auction markets, we develop and estimate a model of strategic interaction in simultaneous first-price auctions when objects are heterogeneous and bidders have nonadditive preferences over combinations. We establish non-parametric identification of primitives in this model under standard exclusion restrictions, providing a basis for both estimation and testing of preferences over combinations. We then apply our model to data on Michigan Department of Transportation (MDOT) highway procurement auctions, quantifying the magnitude of cost synergies and evaluating the performance of the simultaneous first-price mechanism in the MDOT marketplace.

Abstract Each summer milk processors around the country participate in sealed bid procurements for the right to provide public schools with milk throughout the subsequent academic year. School district contracts are an important part of vehicle routing problems that milk processors solve on an ongoing basis. There are allegedly substantial cost savings for a milk processor from servicing a district that is directly adjacent to one they already service. In this paper, following the work of Krishna and Rosenthal (1996), we construct a procurement model allowing for cost synergies. The equilibrium bid function maps directly into an empirical specification. Using data from a time period when bidders were allegedly acting non-cooperatively, our structural parametric estimation results give significant support for the presence of cost synergies in the bidding.

In Paper [I] we use data on Swedish public procurement auctions for internal regularcleaning service contracts to provide novel empirical evidence regarding green publicprocurement (GPP) and its effect on the potential suppliers’ decision to submit a bid andtheir probability of being qualified for supplier selection. We find only a weak effect onsupplier behavior which suggests that GPP does not live up to its political expectations.However, several environmental criteria appear to be associated with increased complexity,as indicated by the reduced probability of a bid being qualified in the postqualificationprocess. As such, GPP appears to have limited or no potential to function as an environmentalpolicy instrument. In Paper [II] the observation is made that empirical evaluations of the effect of policiestransmitted through public procurements on bid sizes are made using linear regressionsor by more involved non-linear structural models. The aspiration is typically to determinea marginal effect. Here, I compare marginal effects generated under both types ofspecifications. I study how a political initiative to make firms less environmentally damagingimplemented through public procurement influences Swedish firms’ behavior. Thecollected evidence brings about a statistically as well as economically significant effect onfirms’ bids and costs. Paper [III] embarks by noting that auction theory suggests that as the number of bidders(competition) increases, the sizes of the participants’ bids decrease. An issue in theempirical literature on auctions is which measurement(s) of competition to use. Utilizinga dataset on public procurements containing measurements on both the actual and potentialnumber of bidders I find that a workhorse model of public procurements is bestfitted to data using only actual bidders as measurement for competition. Acknowledgingthat all measurements of competition may be erroneous, I propose an instrumental variableestimator that (given my data) brings about a competition effect bounded by thosegenerated by specifications using the actual and potential number of bidders, respectively.Also, some asymptotic results are provided for non-linear least squares estimatorsobtained from a dependent variable transformation model. Paper [VI] introduces a novel method to measure bidders’ costs (valuations) in descending(ascending) auctions. Based on two bounded rationality constraints bidders’costs (valuations) are given an imperfect measurements interpretation robust to behavioraldeviations from traditional rationality assumptions. Theory provides no guidanceas to the shape of the cost (valuation) distributions while empirical evidence suggeststhem to be positively skew. Consequently, a flexible distribution is employed in an imperfectmeasurements framework. An illustration of the proposed method on Swedishpublic procurement data is provided along with a comparison to a traditional BayesianNash Equilibrium approach.

Primo paper: costruzione ottimale di un meccanismo di offerta economicamente più vantaggiosa dove due qualità sono importanti. Secondo paper: analisi empirica su offerta economicamente più vantaggiosa e favoritismo. Terzo paper: analisi non parametrica sull'efficacia dei prezzi di riferimento in ambito sanitario in Italia. Si veda l'abstract in inglese.
Abstract paper 1. Moving from Che (1993), I investigate the optimal design of a scoring rule awarding mechanism where qualities of 2 items are included, along with price. I use independently distributed bi-dimensional private information across suppliers. Using a quadratic cost function for bidders, I derive the optimal scoring rule and I prove that provision of the most important quality is below its optimal level, while provision of the other quality may be above or below, depending on its relative importance with respect to the other one. Some simulations validate the main results and two extensions are proposed. Abstract paper 2. We built an original dataset of 307 auctions aimed at awarding canteen services in Italy; it contains the scoring rules, first price, and average bid mechanisms. We exploit this dataset to test the degree of competitiveness and the presence of favoritism by the public contracting authority (CA) towards a possibly predetermined bidder. We start with a working hypothesis: a presumption of which auctions were competitive; we then run an econometric test and construct a variable that individuates possible non-competitive behaviors. Our results highlight that scoring rules can be distorted to favor a bidder, and the victory of the incumbent is associated with lower competition, which is a sign of favoritism. Abstract paper 3. Reference price (RP) in the health market is a threshold for unitary prices usually set on classes of functionally homogeneous products to be adopted by public contracting authorities (CAs) in buying such products. Aim of this paper is to test whether the introduction of RPs reduces procurement inefficiencies - how much the observed price paid by hospitals departs from an estimated optimal one. We use Italian data on simple and standardized medical devices. We adopt non-parametric techniques to calculate unobserved marginal costs. Then we exploit the exogenous discontinuity originated by the competent Adminis- trative Tribunalís decision which terminates the RPi's adoption. Considering the CA inefficiency as a random variable, we find that inefficiency without RP first order stochastically dominates inefficiency with RP.

AbstractThis chapter summarizes the overall tendering and contracting process in the pharmaceutical industry by providing an overview of the first-sealed price auction theory, auction rules, and drug pricing mechanism of different countries. Comparing procurement systems across Asia, Africa, Europe, and Latin America, the review casts light on various pharmaceutical bidding systems across the world and their impact on drug prices. Then, this review focuses on the empirical estimation of first-price auction models. In terms of model specification, we compare the two most commonly used empirical methods for bidding price estimation: structural models and reduced form approaches to test the auction theory. Maximum likelihood estimation is the most frequently used method for structural estimation in literature and selection bias correction is widely adopted using reduced form models. In addition to parametric model construction, we also provide an extensive introduction of non-parametric testing methodologies, including non-parametric estimation and quantile-based estimation to reduce the computation complexity and further illustrate how auction theory could be validated by real-world applications. Additional thoughts and adjustments on non-parametric testing are brought up based on a real-world tendering use case from a large multi-national pharmaceutical company.