Access

You are not currently logged in.

Access your personal account or get JSTOR access through your library or other institution:

login

Log in to your personal account or through your institution.

If You Use a Screen Reader

This content is available through Read Online (Free) program, which relies on page scans. Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.

Specification Error in Probit Models

Adonis Yatchew and Zvi Griliches
The Review of Economics and Statistics
Vol. 67, No. 1 (Feb., 1985), pp. 134-139
Published by: The MIT Press
DOI: 10.2307/1928444
Stable URL: http://www.jstor.org/stable/1928444
Page Count: 6
  • Read Online (Free)
  • Download ($19.00)
  • Subscribe ($19.50)
  • Cite this Item
Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Specification Error in Probit Models
Preview not available

Abstract

This paper examines the effects of various types of misspecification (left out variable, errors in variables, heteroskedastic errors incorrectly assumed to be homoskedastic) on the maximum likelihood (ML) and minimum chi-square (MC) estimators of the probit model. Various asymptotic bias formulae are derived. The chi-square goodness of fit test and the (Hausman) specification test are applied to the problems and found to be asymptotically equivalent. The asymptotic biases may be used to obtain the local power of the tests.

Page Thumbnails

  • Thumbnail: Page 
134
    134
  • Thumbnail: Page 
135
    135
  • Thumbnail: Page 
136
    136
  • Thumbnail: Page 
137
    137
  • Thumbnail: Page 
138
    138
  • Thumbnail: Page 
139
    139