In experimental research, internal validity refers to what extent researchers can conclude that changes in dependent variable (i.e. outcome) are caused by manipulations in independent variable. The causal inference permits researchers to meaningfully interpret research results. This article discusses (a) internal validity threats in social and…

The third-year evaluation of the federally funded Washington, D.C. voucher program shows that low-income students offered vouchers in the first two years of the program had modestly higher reading scores after three years but showed no significant difference in mathematics. Students were randomly assigned to treatment and control groups, and the…

This article discusses the difficulties in conducting intervention research or evaluating intervention programs in a school setting. In particular, the problems associated with randomization and obtaining control groups are examined. The use of quasi-experimental designs, specifically a paired comparison design using the individual as his or her…

Recognition of radio and television antismoking messages was measured in 6 treatment and 4 control cities. A survey of 574 adolescents found high recognition of messages even in areas where they were not broadcast, reinforcing the need for true control groups and distinctive messages to ensure validity in mass media evaluation. (SK)

The need to attend to both methodological and social concerns is demonstrated in two examples: one where the unchecked effects of the social consequences of a methodologically rigorous research design invalidated the evaluation and a second where explicit trade-offs between methodological rigor and social costs enabled the evaluation to proceed.…

A number of potential threats to internal validity in true experiments are discussed. Programmatic research efforts proceeding from established correlational findings to experiments employing random assignment are described and used as referents in discussions of validity considerations. The collection of observational data is recommended for use…

Discusses an ethical dilemma that emerged in a study with bereaved college students. The instruments used to gather data clearly elicited grief-related distress, and more bereaved students in control groups left the study than did participants in social support groups. Three alternatives to a traditional control-group design are discussed for…

The three RMC models endorsed by the U.S. Office of Education for the evaluation of Elementary and Secondary Education Act Title I programs are based on narrowly conceived approaches to evaluation--the measurement of cognitive achievement gains. Each model requires the comparison of observed student performance with an estimate of what level of…

The original version of this report dealt with the feasibility of a longitudinal design for studying the effects of preceptorships on medical students' career choices. The present document supplements the original report, focuses on various non-longitudinal designs, and assesses their suitability for providing the type of information required for…

In order to make policy decisions, educators must evaluate educational research proposals and projects. Findings immediately related to practice are often inadequate, omitting the theoretical establishment of principles by which we can explain and predict the phenomena of our world. These theoretical linkages to the practical world of…

The orientation of this report is that of identifying educational projects which can be considered clearly exemplary. The largest section consists of a 22-step procedure for validating the effectiveness of educational projects using existing evaluation data. It is not intended as a guide for conducting evaluations but rather for interpreting data…