The paper argues that variance components models are very useful in pooling cross section and time series data because they enable us to extract some information about the regression parameters from the between group and between time-period variation--a source that is often completely eliminated in the commonly used dummy variable techniques. The paper studies the applicability and usefulness of the maximum likelihood method and analysis of covariance techniques in the analysis of this type of model, particularly when one of the covariates used is a lagged dependent variable.