比较试验基本理论及MiniTAB操作.pptVIP

Basic Statistical Methods Section T-Test: 1 to Standard T-Test: 2 sample Paired Comparisons Comparing Variances Test for Independence Normality Test Box-Cox Transformation Stat – Basic Statistics – 1 Sample t Select Variable. Enter value for Null Hypothesis. Select Select any or all of the 3 graphs. Choose confidence level (1-alpha). Choose sign of Alternative Hypothesis. One-Sample T: CycleTime Test of mu = 50 vs mu not = 50 Variable N Mean StDev SE Mean CycleTime 100 49.020 5.978 0.598 Variable 95.0% CI T P CycleTime ( 47.834, 50.206) -1.64 0.104 Stat – Basic Statistics – 2 Sample t Need to test first for equal variances. Select Select Y X Factor – 2 levels Use this option if Y is in 2 separate columns. Select one or both graphs. Choose 1-alpha risk. Select Null Hypothesis Value which is usually 0 for this test. Select Alternative Hypothesis Value which is usually “not equal” for this test. Two-Sample T-Test and CI: CycleTime, Size Cust Two-sample T for CycleTime Size Cus N Mean StDev SE Mean Large 45 49.00 5.53 0.82 Small 55 49.04 6.37 0.86 Difference = mu (Large) - mu (Small) Estimate for difference: -0.04 95% CI for difference: (-2.43, 2.36) T-Test of difference = 0 (vs not =): T-Value = -0.03 P-Value = 0.976 DF = 98 Both use Pooled StDev = 6.01 Stat – Basic Statistics – Paired t Select the 2 columns of data that are paired. Select Choose any or all graphs. Default settings are usually good. Paired T-Test and CI: Material A, Material B Paired T for Material A - Material B N Mean StDev SE Mean Material A 10 10.630 2.451 0.775 Material B 10 11.040 2.518 0.796 Difference 10 -0.410 0.387 0.122 95% CI for mean difference: (-0.687, -0.133) T-Test of mean difference = 0 (vs not = 0): T-Value = -3.35 P-Value = 0.009 Stat – ANOVA – Test for Equal Vari