nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2016‒08‒07
four papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. Stochastic choice, systematic mistakes and preference estimation By Breitmoser, Yves
  2. The Demand for Season of Birth By Clarke, Damian; Oreffice, Sonia; Quintana-Domeque, Climent
  3. A regression model of product differentiation By Mogens, Fosgerau
  4. Adaptation to climate variability: Evidence from German households By Kussel, Gerhard

  1. By: Breitmoser, Yves
    Abstract: Individual choice exhibits "presentation effects" such as default, ordering and round-number effects. Using existing models, presentation effects bias utility estimates, which suggests instability of preferences and obscures behavioral patterns. This paper derives a generalized model of stochastic choice by weakening logit's axiomatic foundation. Weakening the axioms implies that focality of options is choice-relevant, alongside utility, which entails presentation effects. The model is tested on four well-known studies of dictator games exhibiting typical round-number patterns. The generalized logit model captures the choice patterns reliably, substantially better than existing models: it robustly predicts and controls for the round-number effects, thus provides "clean" utility estimates that are stable and predictive across experiments.
    Keywords: stochastic choice, systematic mistakes, axiomatic foundation, utility estimation, dictator game
    JEL: C10 C90 D03
    Date: 2016–07–28
    URL: http://d.repec.org/n?u=&r=dcm
  2. By: Clarke, Damian (Universidad de Santiago de Chile); Oreffice, Sonia (University of Surrey); Quintana-Domeque, Climent (University of Oxford)
    Abstract: We study the determinants of season of birth of the first child, for white married women aged 25-45 in the US, using birth certificate and Census data. We also analyze stated preferences for season of birth using our own Amazon Mechanical Turk survey. The prevalence of quarters 2 and 3 is significantly related to mother's age, education, and smoking status during pregnancy. Moreover, those who did not use assisted reproductive technology present a higher prevalence of these births. The frequency of April to September births is also higher and more strongly related to mother's age in states where cold weather is more severe, and varies with mother's occupation, exhibiting a particularly strong positive association with working in "education, training, and library" occupations. Remarkably, this relationship between season and weather disappears for mothers in "education, training, and library" occupations, revealing that season of birth is a matter of choice and preferences, not simply a biological mechanism. We find that the average willingness to pay for season of birth of mothers who report to have chosen season of birth is 19% of financial wealth while for those who report not to have chosen it is only 2% and not statistically different from zero, with the former always targeting an April to September birth. In addition, the average willingness to pay for season of birth is higher among individuals, and parents, in "education, training, and library" occupations. We also document that the top-3 reasons for choosing season of birth are mother's wellbeing, child's wellbeing, and job requirements, while those in "education, training, and library" occupations rank job requirements as the most important reason. Finally, we present evidence that babies born between April and September have on average better health at birth even conditional on the observable maternal characteristics which predict selection.
    Keywords: quarter of birth, fertility timing, pregnancy, first birth, teachers, birth outcomes, willingness to pay, NVSS, ACS, Amazon Mechanical Turk
    JEL: I10 J01 J13
    Date: 2016–07
    URL: http://d.repec.org/n?u=&r=dcm
  3. By: Mogens, Fosgerau
    Abstract: This note develops a model of product differentiation that can be estimated using standard regression techniques and applies it to a panel data set of new car sales. The model allows for complex substitution patterns according to an overlapping nest structure that makes cars closer substitutes if the share brand, body type, and/or quality level. A nest comprising all the car alternatives ensure that they are closer substitutes with each other than with the outside good. In addition, the model comprises fixed effects by car model, controlling for unobserved car quality.
    Keywords: Market shares; complex substitution; endogeneity; discrete choice; new cars
    JEL: C23 C25 C26 D12 L62
    Date: 2016–07–01
    URL: http://d.repec.org/n?u=&r=dcm
  4. By: Kussel, Gerhard
    Abstract: Using panel data originating from two extensive surveys conducted in 2012 and 2014, we investigate German households' adaptation behavior in response to indoor heat stress during summer months. Providing detailed information of household characteristics, behavior and technical equipment, our unique database allows us to estimate a random-eff ects probit model on households' vulnerability and adaptive capacity. The estimates indicate that even moderate increases in temperatures are suffi cient to trigger investments in adaptation measures: While the propensity to adapt is heterogeneous across socio-economic groups, an increase of one degree Celsius in average summer temperature is associated with a rise of 2.3 percentage points in adaptation probability.
    Keywords: climate change,heat stress,panel data,discrete choice models
    JEL: D12 Q54 R22
    Date: 2016
    URL: http://d.repec.org/n?u=&r=dcm

This nep-dcm issue is ©2016 by Edoardo Marcucci. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at http://nep.repec.org. For comments please write to the director of NEP, Marco Novarese at <director@nep.repec.org>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.