Journal of Econometrics
Опубликовано на портале: 01-07-2004Andrew Chesher Journal of Econometrics. 1985. Vol. 28. No. 3. P. 291-305.
Efficient estimation of normal linear simultaneous equations systems is frequently easier when error covariances are zero. The score test is examined for the hypothesis that an error covariance is zero in a 2-equation recursive normal linear simultaneous equations system where endogenous variates may be completely observed, censored, or grouped. The model contains the seemingly unrelated regression equation model and its analogues for grouped and censored data as special cases. The score test for the hypothesis explores the sample covariance of suitably defined residuals and is closely related to the Information Matrix test calculated for the restricted model in which the error covariance is zero. These results are obtained by viewing a non-zero error covariance as emerging from correlated random variation in intercept parameters that can be detected through the use of Chesher's (1984) test for neglected heterogeneity
Опубликовано на портале: 06-04-2004John Kennan Journal of Econometrics. 1985. Vol. 28. No. 1. P. 5-28.
This paper develops new evidence on the hazard function for strike duration, and on cyclical changes in this function, using data on contract strikes in U.S. manufacturing industries. A flexible duration model is estimated, and it is found that the hazard rate is generally a U-shaped function of strike age. The level of industrial production is found to have a significant positive effect on the hazard rate: strike duration is countercyclical. A convenient parametric model of heterogeneity and duration dependence is introduced, in which the logit of the hazard rate is a polynomial function of strike age, up to a random individual effect drawn from a beta distribution. Estimates of this `beta-logit' model indicate that it is difficult to detect the influence of unobserved heterogeneity on the aggregate hazard function for strike duration.