Estimation of stationary stochastic coefficient regression models

Document Type : Original Article

Authors

1 Institute of Statistical Studies and Research, Cairo University

2 National Institute of Management Development

Abstract

In this paper an attempt is made to estimate a regression equation using a time series of cross-sections. It is assumed that the stochastic coefficient regression vector is distributed across individuals with the same mean and the same variance-covariance matrix. The distribution of the stochastic coefficint regression vector is assumed to be invariant to translations along the time axis. This distribution is assumed to be stationary over time. It is assumed that the disturbance terms have zero expectation, constant variances from one period to another as well as the absence of any auto or serial correlation. In other words the disturbances are heteroscedastic.

Keywords

Main Subjects