Educational researchers frequently study the impact of treatments or interventions on educational outcomes. However, when observational or quasiexperimental data are used for such investigations, selection bias can adversely impact researchers' abilities to make causal inferences about treatment effects. One way to deal with selection bias is to…

Education research rarely lends itself to large scale experimental research and true randomization, leaving the researcher to quasi-experimental designs. The problem with quasi-experimental research is that underlying factors may impact group selection and lead to potentially biased results. One way to minimize the impact of non-randomization is…

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…

In a nonrandomized or observational study, propensity scores may be used to balance observed covariates and trajectory groups may be used to control baseline or pretreatment measures of outcome. The trajectory groups also aid in characterizing classes of subjects for whom no good matches are available and to define substantively interesting groups…

This paper reviews limitations in the interpretations of group differences in studies that use younger, language-matched controls in addition to age-matched controls to examine the role of "language level" on performance. Problems arise because of the multidimensional nature of language, extraneous age effects associated with language matching,…

A persistent problem in the evaluation of field-based projects is the lack of no-treatment comparison groups. Frequently, potential comparison groups are confounded by socioeconomic, racial, or other factors. Among the possible methods for dealing with this problem are various matching procedures, but they are cumbersome to use with multiple…

Employed a developmental context to discuss the problem of assessing both quantitative and qualitative deficits in the behavioral profiles of various diagnostic subcategories of developmentally disabled children. Methods of appropriate matching of control groups are suggested to help delineate specific and general deficits in subgroups of…

A meta-analysis was conducted on 44 educational studies that used either a (labelled) Hawthorne control group, a manipulation of Hawthorne effects, or a group designed to control for the Hawthorne effect. The sample included published journal articles, ERIC documents or unpublished papers, and dissertations. The studies were coded on 20 variables,…

This article discusses research design problems peculiar to work with intellectually disabled subjects, such as discrepancies in uses of control groups and mental age matching, definitions of subject groups and variability within and between subject groups. Suggestions for minimizing these problems are made and alternative methodologies offered.…

Ninety-two research reports involving specifically language-impaired subjects were reviewed. Analysis showed few consistent trends with respect to subject selection, subject description, and the number and types of control groups. The importance of more complete subject descriptions and matching criteria for control groups is discussed.…

Evidence is presented that strengthens the argument against comparison group research strategies. Results from a study of youth attitudes related to the California Conservation Corps involving 528 participants and 668 comparisons indicate that the comparison group may not adequately represent the nontreatment state. (SLD)

An evaluation of an experimental problem-based medical education curriculum used with 18 first-year students at the Bowman Gray Medical School of Wake Forest University is discussed. The study, which included a matched group of students experiencing a traditional curriculum, provides insights into design problems in such evaluations. (TJH)

Problems with conducting randomized field experiments in education are explored. Focus is on problems encountered while evaluating a group of dropout prevention projects. Project planners were asked to manipulate the subject eligibility criteria until they identified as eligible three to four times as many students as they could serve. They were…