ERIC Number: ED110468
Record Type: RIE
Publication Date: 1975-Apr
Reference Count: 0
Minimizing Context Effect When Using Multiple Matrix Sampling.
Hill, Richard K.
This study is an a priori demonstration of the applicability of multiple matrix sampling techniques to the practical research problem of parameter estimation. Three tests were administered to two separate but parallel populations, with one receiving item samples and the other receiving full tests. Special efforts were made to minimize the context effect due to sampling procedures. Parameters estimated from matrix sampling statistics closely matched those estimated from full test results, indicating little context effect bias due to the sampling procedures. (Author)
Publication Type: Reports - Research
Education Level: N/A
Authoring Institution: N/A
Note: Paper presented at the Annual Meeting of the National Council on Measurement in Education (Washington, D.C., March 31-April 2, 1975)