|
on Discrete Choice Models |
| By: | Jawwad Noor (Department of Economics, Boston University) |
| Abstract: | Temptation is the conflict between one’s desires (temptation preference) and one’s view of what choices he should make (normative preference). In seminal work, Gul and Pesendorfer [7, 8] provide foundations for a model of temptation on the basis of the idea that temptation creates a preference for commitment. This paper studies agents for whom temptation may in fact create the absence of a preference for commitment. An alternative approach to providing foundations is introduced. Motivated by the evidence on preference reversals, it is hypothesized that delayed temptations are easier to resist than immediate temptations. Normative preference is derived via choices between sufficiently delayed alternatives, and temptation preference is inferred from discrepancies between normative preference and choice. With a choice correspondence as the primitive, agents who are .tempted not to commit’ are modeled. The foundations of the model are used to identify evidence supporting such temptation. It is argued that normative preference serves as an appropriate guide for welfare policy. |
| Keywords: | Self-Control, Temptation, Commitment, Preference Reversals, Revealed Preference. |
| JEL: | D11 D60 |
| Date: | 2007–02 |
| URL: | http://d.repec.org/n?u=RePEc:bos:wpaper:wp2007-009&r=dcm |
| By: | Ivan Fernandez-Val (Department of Economics, Boston University) |
| Abstract: | Fixed effects estimators of nonlinear panel models can be severely biased due to the incidental parameters problem. In this paper I find that the most important component of this incidental parameters bias for probit fixed effects estimators of index coefficients is proportional to the true value of these coe±cients, using a large-T expansion of the bias. This result allows me to derive a lower bound for this bias, and to show that fixed effects estimates of ratios of coefficients and average marginal effects have zero bias in the absence of heterogeneity, and have negligible bias relative to their true values for a wide variety of distributions of regressors and individual effects. New bias corrected estimators for index coefficients and marginal effects with improved finite sample properties are also proposed for static and dynamic probit, logit, and linear probability models with predetermined regressors. |
| Keywords: | Panel data; Bias; Discrete Choice Models; Probit; Fixed effects; Labor Force Participation. |
| JEL: | C23 C25 J22 |
| Date: | 2007–02 |
| URL: | http://d.repec.org/n?u=RePEc:bos:wpaper:wp2007-010&r=dcm |
| By: | Jawwad Noor (Department of Economics, Boston University) |
| Abstract: | Experiments on time preference document numerous .ndings that seem to con- tradict the standard model of intertemporal choice. These .ndings are based on how subjects choose between delayed rewards. This paper shows that if subjects integrate such rewards with their consumption plans, and expect changes in future consump- tion, then except for violations of basic properties like transitivity, the standard model (with CRRA utility) can rationalize all the popular experimental .ndings: preference reversals, dynamic inconsistency, hyperbolic discounting, magnitude e¤ect, sign e¤ect, delay-speedup asymmetry etc. It is demonstrated formally that the standard model has no peculiar testable implications for subjects.preferences between delayed money rewards, which is the data of typical experiments. A testable implication of the model is derived in the richer setting with risky prospects as rewards. |
| Keywords: | Discounted Utility, Exponential discounting, Preference Reversals, Dy- namic Inconsistency, Hyperbolic discounting, Sign E¤ect, Magnitude E¤ect. |
| JEL: | D11 |
| Date: | 2007–07 |
| URL: | http://d.repec.org/n?u=RePEc:bos:wpaper:wp2007-029&r=dcm |
| By: | Victoria Prowse |
| Abstract: | This paper considers the problem of determining the extent of any state dependencies in women`s labor supply behavior. Employment outcomes are modeled using a dynamic multinomial choice framework including persistent unobserved heterogeneity with a relatively general distribution. In order to ensure reliable parameter estimates, appropriate restrictions are imposed on the distribution of unobservables. Significant state dependence is present in both full-time and part-time employment. State dependencies are overestimated if persistent unobservables are ignored, and underestimated if an overly restrictive form of persistence is imposed. |
| Keywords: | Discrete Labor Supply, Unobserved Heterogeneity, Repeated Multinomial Choice |
| JEL: | C15 C25 J6 J22 |
| Date: | 2007 |
| URL: | http://d.repec.org/n?u=RePEc:oxf:wpaper:337&r=dcm |