Permanent URL to this publication: http://dx.doi.org/10.5167/uzh-52374
Boes, Stefan (2007). Count Data Models with Unobserved Heterogeneity: An Empirical Likelihood Approach. Working paper series / Socioeconomic Institute No. 704, University of Zurich.
As previously argued, the correlation between included and omitted regressors generally causes inconsistency of standard estimators for count data models. Using a specific residual function and suitable instruments, a consistent generalized method of moments estimator can be obtained under conditional moment restrictions. This approach is extended here by fully exploiting the model assumptions and thereby improving efficiency of the resulting estimator. Empirical likelihood estimation in particular has favorable properties in this setting compared to the two-step GMM procedure, which is demonstrated in a Monte Carlo experiment. The proposed method is applied to the estimation of a cigarette demand function.
541 downloads since deposited on 29 Nov 2011
123 downloads since 12 months
|Item Type:||Working Paper|
|Communities & Collections:||03 Faculty of Economics > Department of Economics
Working Paper Series > Socioeconomic Institute (former)
|Dewey Decimal Classification:||330 Economics|
|JEL Classification:||C14, C25, D12|
|Deposited On:||29 Nov 2011 22:47|
|Last Modified:||09 Jul 2012 05:04|
|Series Name:||Working paper series / Socioeconomic Institute|
Users (please log in): suggest update or correction for this item
Repository Staff Only: item control page