ppt课件-aovassumptioncheckingandtransformations.pptVIP

AOV Assumption Checking andTransformations (§8.4, 8.5) Model Assumptions Checking the Equal Variance Assumption Bartlett’s Test Levene’s Test Minitab SAS Program SAS SPSS R Checking for Normality Histogram of Residuals Probability Plots (QQ-Plots) Software Excel Probability Plot Probability Plot Formal Tests of Normality Shapiro-Wilk’s W test Shapiro-Wilk W Table D’Agostino’s Test Transformations to Achieve Homoscedasticity Square Root Transformation ARCSINE SQUARE ROOT Power Family of Transformations (1) Box/Cox Transformations (advanced) Handling Heterogeneity How do we check the Normality assumption in AOV? How do we check the Homogeneity of variances assumption in AOV? (§7.4) What to do if these assumptions are not met? Homoscedasticity (common group variances). Normality of responses (or of residuals). Independence of responses (or of residuals). (Hopefully achieved through randomization…) Effect additivity. (Only an issue in multi-way AOV; later). Hartley’s Test: A logical extension of the F test for t=2. Reject if Fmax Fa,t,n-1, tabulated in Table 12. HA: some of the variances are different from each other Little work but little power Requires equal replication, n, among groups. Requires normality. Bartlett’s Test: Allows unequal replication, but requires normality. If C c2(t-1),a then apply the correction term Reject if C/CF c2(t-1),a More work but better power T.S. R.R. More work but powerful result. T.S. Let = sample median of i-th group R.R. Reject H0 if df1 = t -1 df2 = nT - t Essentially an AOV on the zij Test for Equal Variances Response Resist Factors Sand ConfLvl 95.0000 Bonferroni confidence intervals for standard deviations Lower Sigma Upper N Factor Levels 1.70502 3.28634 14.4467 5 15 1.89209 3.64692 16.0318 5 20 1.07585 2.07364 9.1157 5 25 1.07585 2.07364 9.1157 5 30 1.48567 2.86356 12.5882 5 35 Bartletts Test (normal distribution) Test Stat