Background: Social experiments frequently exploit data from administrative records. However, most administrative data systems are designed to track earnings or benefit payments among residents within a single state. When an experimental participant moves across state lines, his entries in the data system of his state of origin consist entirely of…

Active parental consent policies have been blamed for low participation rates and selection bias (i.e., loss of "high-risk" youths) in school-based studies. In this article, the authors describe active consent procedures that produced an overall active consent rate of 79% in a sample of more than 4,500 middle school students attending 29…

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.…

An approach for tracking a mobile group of 1,045 junior high school transfers and minimizing attrition in a longitudinal study of adolescent behavior was studied. Students were tracked through the home or directly through the new school. The new school strategy was very effective and greatly improved tracking. (SLD)

Effective early childhood intervention and child care policies should be based on an understanding of the effects of child care quality and type on child well-being. This article describes methods for securing unbiased estimates of these effects from nonexperimental data. It focuses on longitudinal studies like the one developed by the National…

Using data from the evaluation of the Fast Track intervention, this article illustrates three methods for handling attrition. Multiple imputation and ignorable maximum likelihood estimation produce estimates that are similar to those based on listwise-deleted data. A panel selection model that allows for selective dropout reveals that highly…

The relationships among grade, substance assessed, and type of measurement and statistical analysis used in the detection of external validity threats resulting from subject attrition in a modal follow-up study were examined in 6 successive 2-year panels of adolescents, including 4,819 overall stayers and 1,897 dropouts. (SLD)

Uses pretest data collected with passive parental consent for 2,496 middle school students to examine demographic, attitudinal, and behavioral differences between students for whom active parental consent was provided in later phases of the research and those for whom active consent was not provided. Results show the detrimental effects of…

A study with follow-up interviews of services for homeless and mentally ill persons (original sample of 163) had a very high success rate of over 70% in tracking this difficult to locate population. Techniques for locating clients are presented, as identified by a focus group of five researchers. (SLD)

Self-generated codes to insure student anonymity were used in a study of substance use among 2500 adolescents. Matching rates for various cohorts as a proportion of total respondents at different survey periods were less than ideal. The effects of coding and other attrition factors on the tracking are discussed. (JAZ)

Approaches to the practical problems of finding former offenders and making them want to participate in a study are described for a study of desistance from crime. In the example, a success rate of 78% was achieved for a sample of 50 former offenders. Attention to individual circumstances is critical. (SLD)

The central thesis of this article is that the process of eliminating validity threats depends fundamentally on no-difference findings, a fact that has not been made explicit by researchers. The implications of this neglect are explored using examples from a number of different substantive areas such as psychology, health, and medicine.…

Tracking and two statistical methods (probability weighting and sample selection modeling) were studied as ways to minimize bias attributable to sample attrition in school-based studies. Data on student smoking from 30 middle schools illustrate that sample weighting yields the best results, with estimates superior to sample selection and much less…

Simple methods for detecting attrition (nonresponse) in longitudinal evaluations are reviewed, focusing on regression-based analyses of data from a longitudinal evaluation. The approaches are illustrated with data from the Fort Bragg Evaluation, an evaluation of a major demonstration in children's mental health services. (SLD)

A meta-analysis of school-based substance abuse prevention studies revealed that the mean proportion of subjects retained dropped from 81.4 percent at the three-month followup to 67.5 percent at the three-year followup. Researchers should interpret their results in light of these normative data and adopt second-effort strategies to reduce…