SPSS TESTS

Regression Analysis

Q: Is there a relationship between two variables?

Chi-square test

Q: Are the counts different among treatments?

Shapiro-Wilk test

Q: Are the means different among treatments?

Normally distributed…

p>0.05

Not Normally distributed..

p<0.05

p<0.05

Reject the Null

p>0.05

Fail to Reject the Null

T-test

A set of normally distributed data that has two groups.

ANOVA

A set of normally distributed data that has more than two groups.

Mann-Witney

A set of not normally distributed data that has two groups.

Kruskal-Wallis

A set of not normally distributed data that has more than two groups.

Creating a t-test

Analyze → Compare Means → Independent-Samples T-test

Creating a Mann-Whitney-test

Analyze → Nonparametric Tests → Legacy Dialogues → 2 Independent samples test

Creating a Normality test

Analyze → Descriptive Stats → Explore → Plots (check normality w/tests)

Creating an ANOVA test

Analyze → Compare means → One way ANOVA (post hoc +Turkey)

Creating a Kruskal Wallis test

Analyze → Nonparametric Tests → Independent samples (Automatically compare distributions across groups)

Creating a Chi-squared Test

Data → weight cases Analyze → Nonparametric Tests → Legacy → Chi-square

Creating a Regression Analysis

Analyze → Regression → Linear