Four pooled Demographic and Health Survey data sets are used to examine the determinants of contraceptive method choice in rural Tanzania for the period from 1991 to 1999. The individual data are linked to facility surveys conducted in the same communities so that the impact of Tanzania's family planning program can be examined. The focus of the study is an examination of the effect on method choice of the three major components of Tanzania's family planning program: logistical support, trained providers, and communications programs. The statistical methods employed correct for the potential endogeneity of family planning message recall. Simulations are used to quantify the impact of the important policy variables. All three components of the program are shown to have had an impact on modern method choice.