ERIC Number: ED287881
Record Type: RIE
Publication Date: 1987-Apr
Reference Count: N/A
Sample Size for Variance in a Power Calculation.
Neel, John H.
Determination of statistical power for analysis of variance procedures requires five elements: (1) significance level; (2) effect size; (3) number of means; (4) error variance; and (5) sample size. Significance levels are traditionally chosen to be 0.5, .01, or .001. Effect size is not discussed in this paper. The number of means is determined by the particular experimental setting. Sample size is guessed at until the desired power is obtained, leaving error variance to be established before the calculation can proceed. Establishing the goodness of the estimate of the error variance is the focus here, in an explanation of what constitutes a good estimate. Discussion is restricted to a consideration of error variances in one-way design. (RR)
Publication Type: Speeches/Meeting Papers; Reports - Research
Education Level: N/A
Authoring Institution: N/A
Note: Paper presented at the Annual Meeting of the American Educational Research Association (Washington, DC, April 20-24, 1987).