The use of qualitative measures in a quantitative framework can result in triangulation. Independently conducting qualitative and quantitative evaluations is less likely to cause triangulation and allows for greater discovery. Three usages of triangulation, research as story telling, and problems with qualitative methods and phenomenological…

Four principles of taking statistical uncertainty into account when estimating and reporting effects are discussed. Means of implementing the principles, ways in which the principles are violated in practice, implications for the use of multiple methods, effect size, estimation techniques, and random and nonrandom certainty are described. (TJH)

Confusion about the meaning of validity in quasi-experimental research can be addressed by carefully relabeling types of validity. Internal validity can more aptly be termed "local molar causal validity." More tentatively, the "principle of proximal similarity" can be substituted for the concept of external validity. (Author)

Modeling the process by which participants are selected into groups, rather than adjusting for preexisting group differences, provides the basis for several new approaches to the analysis of data from nonrandomized studies. Econometric approaches, the propensity scores approach, and the relative assignment variable approach to the modeling of…

Causal models often omit variables that should be included, use variables that are measured fallibly, and ignore time lags. Such practices can lead to severely biased estimates of effects. The discussion explains these biases and shows how to take them into account. (Author)

The adequacy of traditional effect size measures for research synthesis is challenged. Analogues to analysis of variance and multiple regression analysis for effect sizes are presented. The importance of tests for the consistency of effect sizes in interpreting results, and problems in obtaining well-specified models for meta-analysis are…

Two chapters of this issue consider critical multiplism as a research strategy with links to meta analysis and generalizability theory. The unifying perspective it can provide for quantitative and qualitative evaluation is discussed. The third chapter explores meta analysis as a way to improve causal inferences in nonexperimental data. (SLD)

Twenty-nine steps necessary for data file preparation for secondary analysis are discussed. Data base characteristics and planned use vary the complexity of the preparation. Required techniques (file verification, sample verification, file merger, data aggregation, file modification, and variable controls) and seven associated pitfalls are defined…

Large-scale databases are an underutilized source of data for secondary analysis by researchers. Major government and private databases available to the public, the types of agencies developing them, and how to obtain and utilize them are described. A catalogue of 20 databases, their characteristics and sources is included. (BS)

Time series analysis is applied to an assessment of the temporary and permanent impact of the 1975 Australian Family Law Act and its effect on number of divorces. The application and construct validity of the model is examined. (Author/PN)

The eight articles of this issue examine the nature of differences that arise between qualitative and quantitative researchers in program evaluation in terms of goals and epistemologies. The origins of these differences and their consequences are explored. Authors represent both perspectives but do not defend their ideological turfs. (SLD)

The 9 articles of this theme issue stem from a project on alcohol and drug abuse that involved 14 projects, 10 of which began with randomized clinical trials. These papers describe implementation problems associated with experimentation in field research and the focus on ensuring internal validity. (SLD)

This case study describes how path analysis and causal modeling were used to assess the impact of federal research and development spending on Ph.D production in science and engineering at leading research universities. The nature of existing data, integrated into a single data base from seven surveys, influenced the research methodology. (BS)