A study was conducted to develop a theoretical framework for unbiased estimation of the dynamic net impact of Comprehensive Employment and Training Act (CETA) programs on participants' earnings. (The possibility of selectivity bias arises from the non-random nature of participation in the program. That is, if participation is a function of unobservable variables such as ability or motivation, and these variables are also determinants of earnings, it will be impossible to distinguish the effects of the unobservables from the effects of the program without controlling for the selection process.) In the study, selectivity biases were controlled for through the use of an error components model. The model relies on the longitudinal nature of the data to eliminate the effects of the unobservables by differencing them away. The estimation techniques developed allow for participation to be a non-random function of individual, unobserved variables that are both fixed and changing over time, and temporary fluctuation in earnings prior to the program. This framework represents an advance in the state of the art in impact estimation for employment and training programs, since it places fewer restrictions on the nature and type of comparison group necessary for unbiased estimation and, thereby, contributes to solving a problem that has long plagued evaluations of employment and training programs. (Author/KC)