Study Limitations

The EDS used a random assignment design, the strongest approach for estimating program impacts. However, projects volunteered for this study instead of being randomly selected, so we cannot generalize to the Even Start population on a strict statistical basis. EDS families are more likely than the population of Even Start families to be Hispanic, and EDS projects are more likely than the population of Even Start projects to be in urban areas. Thus, findings from the EDS are most relevant to urban projects that serve large numbers of Hispanic/ESL families.

In addition, to be included in the analysis for this study, children and parents were required to have a complete set of data for a given outcome variable (i.e., data at pretest, posttest, and follow-up) with all direct assessments administered in English. This limits generalizability to families that are relatively stable over a two-year period as well as children and parents who were comfortable enough with English to be assessed in that language.