1 / 9

Wilcoxon’s Rank-Sum Test (two independent samples) n1 + n2 ≤ 25: Same Distributions

Wilcoxon’s Rank-Sum Test (two independent samples) n1 + n2 ≤ 25: Same Distributions. Wilcoxon’s Rank-Sum Test (two independent samples) n1 + n2 ≤ 25: Different Distributions. Wilcoxon’s Rank-Sum Test (two independent samples) n1 + n2 > 25: Different Distributions.

jeank
Download Presentation

Wilcoxon’s Rank-Sum Test (two independent samples) n1 + n2 ≤ 25: Same Distributions

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Wilcoxon’s Rank-Sum Test (two independent samples) n1 + n2 ≤ 25: Same Distributions

  2. Wilcoxon’s Rank-Sum Test (two independent samples) n1 + n2 ≤ 25: Different Distributions

  3. Wilcoxon’s Rank-Sum Test (two independent samples) n1 + n2 > 25: Different Distributions

  4. Wilcoxon’s Matched Pairs Signed Ranks Test (for paired scores) n ≤ 50

  5. Wilcoxon’s Matched Pairs Signed Ranks Test (for paired scores) n > 50 • Randomly split the Adult data set at 50% 100 times. • For each training/testing data set, run Naïve Bayes and J48 and record their accuracy values as a pair for which we compute the difference in accuracy • Determine the signed ranks of the difference for each pair (as previous example – data is omitted due to space constraints) • We get W+ = 0 and W- = 5050 (J48 produces higher accuracy always), N = 100 • We get, mean(W) = 2525, STD(W)=290.84 • Z=(0-2525)/290.84 = -8.6818 < 1.96 (at alpha = 0.05)

  6. What is the Effect Size? (The effect of using LaPlace smoothing on accuracy of J48)

  7. One-Way ANOVA (J48 on three domains)

  8. One-Way ANOVA (J48 on three domains)

  9. Two-Way ANOVA (J48 & N.B. on 3 domains)

More Related