Choosing the correct statistical test - University of Richmond



Choosing the correct statistical test

Questions to ask yourself:

1. What scale of measurement has been used?

2. Are you testing differences between groups or associations between variables?

3. Are the samples independent or related (same person tested twice or paired ppl)?

4. How many groups are involved?

Nominal data:

Ordinal data:

Interval/ratio data:

-----------------------

Coefficient of Contingency

Any number of cells

McNemar Test

Chi Square

Related selection

Independent Selection

Hypothesis of Association

Hypothesis of Difference

Nominal Data

Friedman ANOVA by ranks

Wilcoxon T test

More than 2 groups

Kruskal-Wallis H Test

Mann-Whitney U

More than 2 group

Spearman r

Two groups

Two Groups

Related selection

Independent Selection

Hypothesis of Association

Hypothesis of Difference

Ordinal Data

Multiple regression

With prediction

Multiple R

Regression of Y on X

With prediction

Pearson r

More than 2 groups

Factorial ANOVA

More than 1 IV

Within-subjects ANOVA

Paired t-test

2 or more groups

One-way ANOVA

Independent t Test

2 or more groups

Two groups

Two groups

Two Groups

Related selection

Independent Selection

Hypothesis of Association

Hypothesis of Difference

Interval Data

................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download