ERIC Number: ED193295
Record Type: RIE
Publication Date: 1980-Apr
Reference Count: 0
Use of Composite Scores in Title I Evaluation.
Gabriel, Roy M.
Three principal uses of composite variables in the Title I Evaluation and Reporting System (TIERS) are examined in light of four basic methodological issues: (1) the criterion used in constructing the composite; (2) the likely reliability of both component and criterion variables; (3) the form of the relationship between components and criterion; and (4) the weighting schemes used to combine the component variables to form the composite. The first usage of composite requires "expert" judgment to assemble, weight, and combine information from several variables. Methods used to select students typically do not have well-defined, measurable criteria, and require a linear approach with a simple weighting scheme. A second usage of composite requires that a set of predictors be weighted and combined to predict a single outcome variable. A prediction framework typically includes a measured criterion variable and permits consideration of a variety of alternative models and weighting schemes. A composite predictor of student achievement gains may even uncover these aspects of the program relating to student gains. A third usage of composites which weights and combines multiple outcomes measures may incorporate such relevant constructs as students' self-concept or attitudes toward school. (RL)
Publication Type: Speeches/Meeting Papers; Reports - Evaluative
Education Level: N/A
Authoring Institution: N/A
Identifiers: Composite Scores; Elementary Secondary Education Act Title I; EValuation Problems; RMC Models; Title I Evaluation and Reporting System
Note: Paper presented at the Annual Meeting of the American Educational Research Association (64th, Boston, MA, April 7-11, 1980).