Which Model do I use?
Introduction
This is a very constrained, simple table to help students decide what type of statistical modeling is appropriate for their research question and data set.
| Comparing | Dependent (outcome) Variable | Independent (explanatory) variable | Parametric Test (normally distributed data) | Non-parametric test (ordinal or skewed data) |
|---|---|---|---|---|
| Single Comparison Tests | ||||
| Averages of two independent groups | Scale | Nominal (Binary) | Independent t-test | Mann-Whitney test/ Wilcoxon rank sum |
| Averages of 3+ independent groups | Scale | Nominal | One-way ANOVA | Kruskal-Wallis test |
| The average difference between paired (matched) samples e.g. test scores before and after a class | Scale | Time or Condition variable | Paired t-test | Wilcoxon signed rank test |
| The 3+ measurements on the same subject | Scale | Time or Condition variable | Repeated measures ANOVA | Friedman test |
| Association Tests | ||||
| Relationship between 2 continuous variables | Scale | Scale | Pearson’s Correlation Coefficient | Spearman’s Correlation Coefficient |
| What is value of DV when value of IV changes? | Scale | Any | Simple Linear Regression | Transform the data |
| What is value of DV when value of IV changes? | Nominal (Binary) | Any | Logistic regression | NA |
| What is value of DV when value of IV changes? | Nominal (Count) | Any | Poisson Regression | NA |
| What is value of DV when value of IV changes? | Nominal (Count, overdispersed) | Any | Negative Binomial Regression | NA |
| Assessing the relationship between two categorical variables | Categorical | Categorical | NA | Chi-squared test |