TYPE OF TEST USE

I. PARAMETRIC Used when data is normally distributed.

A. CORRELATIONAL These tests look for an association between variables

1. Pearson Correlation Tests for the strength of the association between two continuous variables

Tests for the strength of the association between two continuous variables
2. Spearman Correlation between two ordinal variables (does not rely on the assumption of
normally distributed data)

Tests for the strength of the assocation between two categorical

3. Chi-Square variables.

B. COMPARISON OF MEANS These tests look for the difference between the means of variables

Tests for the difference between the same variables from the same
1. Paired T-Test
population (e.g., a pre and post-test score)
Tests for the difference between the same variable from different
2. Independent T-Test
populations (e.g., comparing boys to girls)

Tests for the difference between group means after any other variance in
3. ANOVA the outcome variable is accounted for (e.g., controlling for sex, income, or
age)

These tests assess if change in one variable predicts change in another

C. REGRESSION
variable
Tests how change in the predictor variable predicts the level of change in
1. Simple Regression
the outcome varaible
Tests how change in the combination of two or more predictor variables
2. Multiple Regression predict the level of change in the outcome variable

I. NON-PARAMETRIC Used when data is not normally distributed.

Tests for the difference between two independent variables; takes into
A. Wilcoxon Rank-Sum Test
account magnitude and direction of difference

Tests for the difference between related variables; takes into account the
B. Wilcoxon Sign-Rank Test
magnitude and direction of difference

Tests if two related variables are different; ignores the magnitude of

C. Sign Test
change - only takes into account the direction
The chart below provides a summary of the questions that need to be answered
before the right test can be chosen.
 TYPES OF STATISTICAL TEST
TYPE OF TEST USE

I. PARAMETRIC Used when data is normally distributed.

A. CORRELATIONAL These tests look for an association between variables

1. Pearson Correlation
2. Spearman Correlation
3. Chi-Square
B. COMPARISON OF MEANS
Tests for the strength of the association between two continuous variables
Tests for the strength of the association between between two ordinal variables (does not rely on the assumption of normally
distributed data)
Tests for the strength of the assocation between two categorical variables.
These tests look for the difference between the means of variables

1. Paired T-Test Tests for the difference between the same variables from the same population (e.g., a pre and post-test score)

2. Independent T-Test Tests for the difference between the same variable from different populations (e.g., comparing boys to girls)

Tests for the difference between group means after any other variance in the outcome variable is accounted for (e.g.,
3. ANOVA
controlling for sex, income, or age)
C. REGRESSION These tests assess if change in one variable predicts change in another variable
1. Simple Regression Tests how change in the predictor variable predicts the level of change in the outcome varaible

2. Multiple Regression Tests how change in the combination of two or more predictor variables predict the level of change in the outcome variable

I. NON-PARAMETRIC Used when data is not normally distributed.

A. Wilcoxon Rank-Sum Test Tests for the difference between two independent variables; takes into account magnitude and direction of difference

B. Wilcoxon Sign-Rank Test Tests for the difference between related variables; takes into account the magnitude and direction of difference

C. Sign Test Tests if two related variables are different; ignores the magnitude of change - only takes into account the direction

The chart below provides a summary of the questions that need to be answered before the right test can be chosen.