To explore the feasibility of sample selection to predict agricultural employment, a stratified sample of 360 employers was drawn from the employers reporting employment in the Disability Insurance Program for agricultural workers in Fresno County. Month-to-month changes were examined for seven industry strata, and estimates were made by the link-relative method. Employment estimates were compared with the reported universe employment for the corresponding month to determine the accuracy of the sample as a means of estimating. Data indicated that the method may be feasible, but that the sample must be designed to include employers whose seasonal labor needs occur at different periods of the year. (JM)