Format | |
---|---|
BibTeX | |
MARCXML | |
TextMARC | |
MARC | |
DublinCore | |
EndNote | |
NLM | |
RefWorks | |
RIS |
Files
Abstract
Selectivity models usually consist of two equations: a linear and a qualitative variables equation. This paper investigates the consistency of the ML-estimates of two selectivity models in which the heteroscedasticity of the error term of the linear equation is ignored. Homoscedastic estimation of a heteroscedastic model is proved to yield inconsistent estimates. Some Monte Carlo evidence is also provided.