Based on the decision tree presented in Figure 18-1, what are the possible appropriate statistical tests for when there is at least one ordinal variable? (You only have to list the tests for this exercise.)

Figure 18-1

Transcribed Image Text:

Four Categories of Hypothesis Tests (IV = independent variable; DV = dependent variable) 1. Only scale variables 2. Nominal IV; scale DV 3. Only nominal variables 4. Any ordinal variables Question about Question about Two or One nominal variable Two nominal Two ordinal variables; question about association Опe IV Nominal IV more IVs variables and ordinal DV association prediction Factorial Chi-square test for goodness of fit Chi-square test for Regression Pearson correlation coefficient ANOVA independence (e.g., two-way between-groups ANOVA) Spearman rank-order correlation coefficient Two groups (levels) Three or more groups (levels) Within-groups design; two groups Between- One represented by a sample, one by the population Two groups samples Within- Between- design groups design groups design Wilcoxon u and o known Only u known signed-rank test One-way within- One-way between- groups ANOVA groups ANOVA Single- sample t test z test Two groups Three or more groups Within-groups Between-groups design design Mann- Whitney U test Kruskal- Wallis Paired- Independent- samples t test H test samples ttest Nolan/Heinzen, Statistics for the Behavioral Sciences, 5e, © 2020 Worth Publishers