PDF pending restoration
ERIC Number: ED178492
Record Type: RIE
Publication Date: 1979-Jun
Reference Count: 0
The Effects of Block Size and Heterogeneity of Covariance on Type 1 Error Rates with Constant Error and Variable Error Data.
Schutz, Robert W.; Gessaroli, Marc E.
The question of whether or not block size has an effect on the statistical analysis of data is examined through a study involving a total of 10,000 simulated experiments. Results indicate that the inflation in Type 1 error rate is much higher than is reported in the literature when using CE as the independent variable. There is little or no difference under varying blocking parameters. With VE, however, there was no effect of heterogeneity of covariance. It is concluded that block size can be chosen on logical rather than on statistical grounds, and that it has no effect on the validity of the statistical analysis involved. (Author/LH)
Publication Type: Reports - Research; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A
Identifiers: Block Size; Type 1 Error
Note: Paper presented at the International Congress in Physical Education (Three Rivers, Quebec, Canada, June 1979)