Premium
An Information‐Based Sample‐Selection Estimation Model of Agricultural Workers' Choice between Piece‐Rate and Hourly Work
Author(s) -
Golan Amos,
Moretti Enrico,
Perloff Jeffrey M.
Publication year - 1999
Publication title -
american journal of agricultural economics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.949
H-Index - 111
eISSN - 1467-8276
pISSN - 0002-9092
DOI - 10.2307/1244043
Subject(s) - library science , citation , agricultural experiment station , work (physics) , sample (material) , operations research , agriculture , management , computer science , history , economics , engineering , archaeology , mechanical engineering , chemistry , chromatography
This paper presents a new generalized maximum entropy (GME) approach to estimation of sample-selection models with small data sets, such as are found in many empirical agricultural economic analysis. For small samples, the GME approach produces more stable estimates and has smaller mean square error measures than other well-known estimators such as ordinary least squares, Heckman's two-step method, full-information maximum likelihood, and Ahn and Powell's method. The technique is used to analyze whether hired agricultural workers will work in piece-rate or time-rate jobs and to compare female-male wage differentials for both types of jobs.