Tests

Alla Inga Spara

• When you want to compare a sample mean with a known population mean One-sample t-test
• When you want to compare two different means of two independent groups to see differences Two-sample t-test
• When you want to compare paired measurements from the same subjects (before-after) Paired t-test
• When you want to see if the means of 3 or more groups differ One-way ANOVA
• When you want to see how two independent variables affect one continuous dependent variable and how they interact Two-way ANOVA
• When you want to see if the observed distribution of one cateogircal variable match an expected distribution? Chi-square goodness-of-fit-test
• WHen you want to test for association between two or more categorical variables Chi-square contingency analysis
• When you want to measure stregnth and direction of the linear relationship between two variables, if the data is norm.dist with linear relationship Pearson's correlation test
• If the data of a linear correlation is skewed, monotonic or ordinal Spearman's correlation rank test
• Nonparametric alternative to two-sample t-test when you want to compare two groups Mann-Whitney U-test
• Nonparametric aternative to paired t-test if the data isn't normally distributed Wilcoxon signed-rank test
• Nonparametric alternative to ANOVA, when the data isn't normally distributed for each group Kruski-Wallis test
• When you eant to see if a data set is consistent with normal distribution Shapiro-Wilk test
• Nonparametric test that looks if an association occured by chance. It randomly rearranges the data many times to create a null distribution Permutation test
• A nonparametric test to x2 contingency analysis which tests association between two categorical variables when n = small Fisher's exact test
• A test that examines if the observed proportion of two possible outcomes differs from an expected otucome Binomial test

Alla Inga Spara