Homogeneity of Variance Pooling the variances doesn’t make sense when we cannot assume all of the sample Variances are estimating the same value. For two groups: Levene (1960): replace all of the individual scores with either then run a t-test t F - test ( yij y j ) 2 E ( Sl2arg e ) E ( S small ) Alternate Hypothesis: ( yij y j ) 2 y1 y2 2 MSerror n Given: 1. Random and independent samples 2. Both samples approach normal distributions Then: F is distributed with (n-large-1) and (n-small-1) df. Null Hypothesis: or 2 larg e small F Sl2arg e S 2 small K independent groups: Hartley: If the two maximally different variances are NOT significantly different, Then it is reasonable to assume that all k variances are estimating the population variance. The average differences between pairs will be less than the difference between the smallest And the largest variance. Sl2arg e S A2 E 2 E 2 SB S small Thus: F Fmax Sl2arg e S 2 small A and B are randomly selected pairs. will NOT be distributed as a normal F. (k groups, n-1) df Then, use Fmax Table to test Null Hypothesis: 12 22 i2 ... Alternate Hypothesis: j2 2 Data Transformation: When Homogeneity of Variance is violated Looking at the correlation between the variances (or standard deviations) And the means or the squared means. ( x x )( y y ) r n 1 Sx Sy b) Use square root transformation c) Use logarithmic transformation d) Use reciprocal transformation