|
on Discrete Choice Models |
| By: | Nathaniel T. Wilcox (Economic Science Institute (Chapman University) and Center for the Economic Analysis of Risk (Georgia State University)) |
| Abstract: | I compare the generalization ability, or out-of-sample predictive success, of four probabilistic models of binary discrete choice under risk. One model is the conventional homoscedastic latent index model—the simple logit—that is common in applied econometrics: This model is “context-free” in the sense that its error part is homoscedastic with respect to decision sets. The other three models are also latent index models but their error part is heteroscedastic with respect to decision sets: In that sense they are “context-dependent” models. Context-dependent models of choice under risk arise from several different theoretical perspectives. Here I consider my own “contextual utility” model (Wilcox 2011), the “decision field theory” model of Busemeyer and Townsend (1993) and the “Blavatskyy-Fishburn” model (Fishburn 1978; Blavatskyy 2014). In a new experiment, all three context-dependent models outperform the context-free model in prediction, and significantly outperform a linear probability model (suggested by contemporary applied practice a la Angrist and Pischke 2009) when the latent preference structure is rank-dependent utility (Quiggin 1982). All of this holds true for function-free estimations of outcome utilities and probability weights as well as parametric estimations. Preoccupation with theories of the deterministic structure of choice under risk, to the exclusion of theories of error, is a mistake. |
| Keywords: | risk, discrete choice, probabilistic choice, heteroscedasticity, prediction |
| JEL: | C25 C91 D81 |
| Date: | 2015 |
| URL: | http://d.repec.org/n?u=RePEc:chu:wpaper:15-11&r=dcm |
| By: | Yukihiro Kidokoro (GRIPS); |
| Abstract: | Although discrete choice models are well suited to describing the demand structure of differentiated goods, two important problems remain unsolved in their application. First, the total demand for a choice set is exogenously fixed. Second, multiple categories of goods cannot be handled in an unrestrictive way. In this paper, we address these flaws by formulating a complete utility maximization problem that is consistent with discrete choice models and derive the implications for applied research. We then apply the results to the ketchup and mayonnaise markets and investigate the differences arising from the consideration of multiple categories of goods. |
| Date: | 2015–06 |
| URL: | http://d.repec.org/n?u=RePEc:ngi:dpaper:15-08&r=dcm |
| By: | Chen, Yongmin; Riordan, Michael |
| Abstract: | We develop a new approach to discrete choice demand for differentiated products, using copulas to separate the marginal distribution of consumer values for product varieties from their dependence relationship, and apply it to the issue of how preference dependence affects market outcomes in symmetric multiproduct industries. We show that greater dependence lowers prices and profits under certain conditions, suggesting that preference dependence is a distinct indicator of product differentiation. We also find new sufficient conditions for the symmetric multiproduct monopoly and the symmetric single-product oligopoly prices to be above or below the single-product monopoly price. |
| Keywords: | Product differentiation, discrete choice, copula, multiproduct industries. |
| JEL: | D4 L1 |
| Date: | 2014–12 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:64827&r=dcm |
| By: | Morgan McClellon |
| Abstract: | This paper studies random choice rules over finite sets that obey regularity but potentially fail to satisfy all of the Block-Marschak inequalities. Such random choice rules can be represented by non-additive random utility functions: that is, by capacities on the space of preferences. The higher-order Block-Marschak inequalities are shown to be related to the degree of monotonicity that can be achieved by a capacity representation. These results help to decipher the Block-Marschak inequalities, and are applied to study the relationship between random choice over finite sets and random choice over lotteries. |
| Date: | 2015–06 |
| URL: | http://d.repec.org/n?u=RePEc:qsh:wpaper:262656&r=dcm |
| By: | Pilny, Adam; Mennicken, Roman |
| Abstract: | A number of recent empirical studies document significant effects of in-patient care quality indicators on the choice of hospital. These studies use either objective quality indicators based on quantitative figures, or if subjective reputation scores are used, scores based on the opinion of hospital market insiders. We contribute to the current debate by using a subjective reputation score resorting to patient perceptions and examine its impact on the choice of hospital of patients undergoing a coronary artery bypass graft (CABG) in Germany. Our results show that 76% of the patients value hospital reputation positively when choosing a hospital. Moreover, we find evidence for a trade-off between hospital reputation and travel time, i.e. a significant share of patients is willing to accept additional travel time to get a treatment in a hospital with better reputation. The average marginal effect for hospital reputation confirms this finding, since the magnitude of the effect strengthens for higher thresholds of travel time. The results are robust for different degrees of co-morbidities and admission status. |
| Abstract: | Eine Reihe jüngst veröffentlichter empirischer Studien hat nachgewiesen, dass Qualitätsindikatoren einen signifikanten Einfluss auf die Krankenhauswahl haben. Diese Studien haben entweder objektive Qualitätsindikatoren herangezogen, die auf quantitativen Größen beruhen, oder sofern subjektive Indikatoren herangezogen wurden, basierten diese auf der Meinung von Krankenhausmarktinsidern. Mit dieser Studie leisten wir einen Beitrag zur aktuellen Debatte, indem wir als Indikator die Reputation von Krankenhäusern verwenden, die auf der Meinung von ehemals behandelten Patienten basiert, und untersuchen dessen Einfluss auf die Krankenhauswahl von Patienten, die sich einer Koronararterien-Bypass-Operation in Deutschland unterzogen haben. Unsere Ergebnisse zeigen, dass die Reputation der Klinik bei 76 Prozent aller Patienten einen signifikanten Einfluss auf die Krankenhauswahl hat. Darüber hinaus finden wir empirische Evidenz für einen Trade-off zwischen Reputation und der Fahrzeit zum Klinikum. Ein signifikanter Anteil der Patienten ist folglich bereit, längere Fahrzeiten in Kauf zu nehmen, um in einer Klinik mit besserer Reputation behandelt zu werden. Die durchschnittlichen marginalen Effekte bestätigen diesen Befund insofern, als dass die Größenordnung des marginalen Effekts für Krankenhausreputation für längere Fahrzeiten stetig zunimmt. Die Ergebnisse sind robust für verschiedene Schweregrade und den Aufnahmestatus des Patienten. |
| Keywords: | hospital choice,hospital reputation,mixed logit model |
| JEL: | C25 D12 I11 |
| Date: | 2014 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:rwirep:516&r=dcm |
| By: | Nathaniel T. Wilcox (Economic Science Institute (Chapman University) and Center for the Economic Analysis of Risk (Georgia State University)) |
| Abstract: | I present new estimates of the probability weighting functions found in rank-dependent theories of choice under risk. These estimates are unusual in two senses. First, they are free of functional form assumptions about both utility and weighting functions, and they are entirely based on binary discrete choices and not on matching or valuation tasks, though they depend on assumptions concerning the nature of probabilistic choice under risk. Second, estimated weighting functions contradict widely held priors of an inverse-s shape: Instead I usually find populations dominated by “optimists” who uniformly overweight best outcomes in risky options. A salience-based theory of choice may help to explain this. Additionally, the choice pairs I use here mostly do not provoke similarity-based simplifications. In a third experiment, I show that the presence of choice pairs that provoke similarity-based computational shortcuts does indeed flatten estimated probability weighting functions. |
| Keywords: | prospect theory, probability weighting, probabilistic choice, rank-dependent utility, risk, similarity, salience |
| JEL: | C25 C91 D81 |
| Date: | 2015 |
| URL: | http://d.repec.org/n?u=RePEc:chu:wpaper:15-10&r=dcm |
| By: | Bünnings, Christian; Schmitz, Hendrik; Tauchmann, Harald; Ziebarth, Nicolas R. |
| Abstract: | This paper empirically assesses the relative role of health plan prices, service quality and optional benefits in the decision to choose a health plan. We link representative German SOEP panel data from 2007 to 2010 to (i) health plan service quality indicators, (ii) measures of voluntary benefit provision on top of federally mandated benefits, and (iii) health plan prices for almost all German health plans. Mixed logit models incorporate a total of 1,700 health plan choices with more than 50 choice sets for each individual. The findings suggest that, compared to prices, health plan service quality and supplemental benefits play a minor role in making a health plan choice. |
| Abstract: | Dieses Papier untersucht empirisch die Rollen von Beitrag, Servicequalität und freiwilligen Zusatzleistungen im Rahmen der Krankenkassenwahl. Dazu verknüpfen wir repräsentative Paneldaten des SOEP der Jahre 2007 bis 2010 mit kassenspezifischen Indikatoren für (i) die Servicequalität, (ii) das Angebot von freiwilligen Zusatzleistungen und (iii) den Beitrag von fast allen deutschen Krankenkassen. Die verwendeten mixed logit Modelle basieren auf 1 700 individuellen Entscheidungssituationen, welche jeweils mehr als 50 Krankenkassen zur Wahl beinhalten. Die Ergebnisse deuten an, dass Servicequalität und freiwillige Zusatzleistungen eine - im Vergleich zu Beiträgen - untergeordnete Rolle in der Wahl der Krankenkasse spielen. |
| Keywords: | service quality,non-essential benefits,prices,health plan switching,German sickness funds,SOEP |
| JEL: | D12 H51 I11 I13 I18 |
| Date: | 2015 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:rwirep:545&r=dcm |