RT Generic
T1 Estimating Learning Models with Experimental Data
A1 Cabrales, Antonio
A1 García-Fontes, Walter
AB We study the statistical properties of three estimation methods for a model of learning that is often  tted to experimental data: quadratic deviation measures without unobserved heterogeneity, and maximum likelihood with and without unobserved heterogeneity. After discussing identi cation issues, we show that the estimators are consistent and provide their asymptotic distribution.Using Monte Carlo simulations, we show that ignoring unobserved heterogeneity can lead to seriously biased estimations in samples which have the typical length of actual experiments. Better small sample properties are obtained if unobserved heterogeneity is introduced. That is, rather than estimatingthe parameters for each individual, the individual parameters areconsidered random variables, and the distribution of those random variablesis estimated.
PB Universidad Pompeu Fabra. Departamento de Economia y Empresa
YR 2000
FD 2000
LK https://hdl.handle.net/10016/3482
UL https://hdl.handle.net/10016/3482
LA eng
DS e-Archivo
RD 1 jun. 2024