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)

Many purposes can be served by using multiple dependent variables (MDVs) in program evaluations, and the application of path analysis to multiple measures can increase both conceptual and statistical power. Alternative types of MDV designs are described and evaluated. (Author/TJH)

Twenty-three journal articles on program evaluations were surveyed for incidence of four unethical practices: withholding purpose or mere existence of an evaluation from participants; exposure to stress; invasion of privacy; and denial of program benefits to control groups. Few violations were apparent. (CP)

In no-difference research, no differences are found among groups or conditions. This article summarizes the existing commentary on such research. The characteristics of no-difference research, its acceptance by the research community, strategies for conducting such studies, and its centrality within the experimental and nonexperimental paradigms…

The use of philosophic methods, especially concept analysis, in evaluation is explored through a retrospective study of a school district reading evaluation. The application of philosophic techniques in the design, conduct, and review of local district evaluations is assessed. (Author/AL)

Evaluability assessment is a diagnostic and prescriptive technique that can be used to determine the extent to which different problems inhibit program evaluation. It involves policymakers, managers, and staff in developing program theory, clarifying intended uses of evaluation information, and planning further evaluations that would stimulate…

Case studies of educational program evaluations demonstrate that utilization of evaluative information occurs; however, its forms and the forces influencing utilization are complex. Naturalistic methods were used to study utilization. (See RIE: ED 174 666). (Available from: Jossey-Bass, Inc., 433 California St., San Francisco, CA 94104, single…

A short history of program theory in evaluation is reviewed. Two related problems in program evaluation are discussed and illustrated: (1) how to specify in measurable terms the consensus of theories and values that guides the program; and (2) how to construct a theoretical framework that specifies the use of these measurements. (Author/JAZ)

Six papers on the use and usefulness of program evaluation conducted inside government institutions by government staff, rather than by outside contractors or university personnel, are presented. Federal, state, and local evaluation efforts in executive and legislative environments are analyzed. (TJH)

Permeated with ethical and political concerns, with racial gender, and cultural differences, this case study deals with specifics of Native American education in Canada. It is an example of educational change and takes its meaning from that reality. (Author)

This article discusses four basic types of cost analysis methods in educational evaluation. The results of a national survey of all evaluation units in state departments of education are reported. Evidence on the amount and types of cost analysis activities done for evaluation purposes in state education agencies is provided. (DWH)

The six articles of this special issue focus on minority issues in program evaluation. The aim is to begin a discussion of minority concerns about the impact of cultural dominance on definitions of social goals, the measurement of outcomes, and the political consequences of the selection of evaluation methods. (SLD)