Randomness in the experimental samples of PROGRESA --Education, Health, and Nutrition Program

Jere R. Behrman, Petra E. Todd

PROGRESA is a new large-scale social program being implemented in Mexico to provide various kinds of assistance to families living in conditions of extreme poverty. The program is targeted mainly at rural communities. It aims to improve living standards of poor families by improving family health and nutrition and by increasing educational opportunities for children. PROGRESA is a multifaceted program made up of three closely linked components related to education, health and nutrition. The program provides educational grants to families, designed to promote school enrollment and attendance, provides resources for improving the quality of schools, provides resources for increasing the quality and availability of health care, and gives direct monetary transfers and nutritional supplements to families. Because the PROGRESA program is still in its early stages, little is yet known about how it impacts the families receiving program services. A major goal of PROGRESA is to evaluate its effectiveness in achieving its stated goals. For purposes of evaluation, the program is initially being implemented as a randomized social experiment, whereby some households are assigned to a treatment group that receives program services and others to a randomized-out control group. Treatment impacts can then be assessed by comparing the performance of the treated households under a variety of criteria to that of the control group at various times after the administration of the program. In this report, we compare the characteristics of treatment and control group households, measured at a point in time prior to having received any program services, to determine whether the control and treatment groups truly appear to have been randomly assigned. This evaluation of randomization is being carried out so that any deviations from randomization can be detected early on and taken into account later in the course of the evaluation.