SEMIPARAMETRIC ESTIMATION OF REGRESSION-MODELS FOR PANEL-DATA

Citation
Jl. Horowitz et M. Markatou, SEMIPARAMETRIC ESTIMATION OF REGRESSION-MODELS FOR PANEL-DATA, Review of Economic Studies, 63(1), 1996, pp. 145-168
Citations number
12
Categorie Soggetti
Economics
Journal title
ISSN journal
00346527
Volume
63
Issue
1
Year of publication
1996
Pages
145 - 168
Database
ISI
SICI code
0034-6527(1996)63:1<145:SEORFP>2.0.ZU;2-O
Abstract
Linear models with error components are widely used to analyse panel d ata. Some applications of these models require knowledge of the probab ility densities of the error components. Existing methods handle this requirement by assuming that the densities belong to known parametric families of distributions (typically the normal distribution). This pa per shows how to carry out nonparametric estimation of the densities o f the error components, thereby avoiding the assumption that the densi ties belong to known parametric families. The nonparametric estimators are applied to an earnings model using data from the Current Populati on Survey. The model's transitory error component is not normally dist ributed. Use of the nonparametric density estimators yields estimates of the probability that individuals with row earnings will become high earners in the future that are much lower than the estimates obtained under the assumption of normally distributed error components.