A Beginner-Friendly Guide to Statistical Tests

Vocabulary flashcards covering common statistical tests and their primary uses across group comparisons, relationships, proportions, predictions, distributional assumptions, and time-based data.

One-sample t-test

Compares one group average with a specific reference value.

Independent-samples t-test

Compares the averages of two separate groups.

Paired t-test

Compares two measurements from the same people or matched items.

ANOVA

Compares averages across three or more separate groups.

Repeated-measures ANOVA

Compares the same people/items across three or more times or conditions.

Mann-Whitney U test

Compares two separate groups using ranks; often used when a t-test is unsuitable.

Wilcoxon signed-rank test

Compares two paired sets of measurements using ranks.

Kruskal-Wallis test

Compares three or more separate groups using ranks.

Friedman test

Compares three or more paired sets of measurements using ranks.

Pearson correlation

Measures the strength and direction of a linear relationship between two numerical variables.

Spearman correlation

Measures whether two variables tend to move together in an increasing or decreasing order.

Kendall tau

Measures association between ranked or ordered data.

Chi-square test of independence

Checks whether two categorical variables are associated.

Fisher's exact test

Tests association between categorical variables, especially with a small sample.

McNemar's test

Checks whether paired yes/no responses change between two conditions or times.

One-proportion test

Compares a sample proportion with a specified value.

Two-proportion test

Compares proportions from two groups.

Chi-square goodness-of-fit test

Checks whether observed category counts fit an expected pattern.

Binomial test

Checks whether yes/no outcomes are consistent with a specified probability.

Linear regression

Models or predicts a numerical outcome using explanatory variables.

Logistic regression

Models the probability of a categorical outcome, commonly yes/no.

Poisson regression

Models counts, such as the number of visits or events.

Cox regression

Studies time until an event, accounting for participants whose event has not happened yet.

Shapiro-Wilk test

Checks whether data are consistent with a normal distribution.

Kolmogorov-Smirnov test

Compares a sample distribution with a reference distribution, or compares two distributions.

Levene's test

Checks whether spread (variance) is similar across groups.

Bartlett's test

Checks whether group variances are similar; it is sensitive to departures from normality.

Log-rank test

Compares time-to-event patterns between groups.

Time-series tests

A broad family of methods for trends, seasonality, and dependence over time.