Some identification and estimation results for regression models with stochastically varying parametres

Elsevier Science Publishers B.V.
Publication Type:
Journal Article
Journal of Econometrics, 1980, 13 (3), pp. 341 - 363
Issue Date:
Full metadata record
Files in This Item:
Filename Description SizeFormat
2009004421OK.pdf1.33 MBAdobe PDF
Although various theoretical and applied papers have appeared in recent years concerned with the estimation and use of regression models with stochastically varying coefficients, little is available in the literature on the properties of the proposed estimators or the identifiability of the parameters of such models. The present paper derives sufficient conditions under which the maximum likelihood estimator is consistent and asymptotically normal and also provides sufficient conditions for the estimation of regression models with stationary stochastically varying coefficients. In many instances these requirements are found to have simple, intuitively appealing interpretations. Consistency and asymptotic normality is also proven for a two-step estimator and a method suggested by Rosenberg for generating initial estimates.
Please use this identifier to cite or link to this item: