Know your Data - ARMS (neuropsychologie)

In this summary you will learn how distinguish parametric tests from non-parametric tests and how to conduct non-parametric tests using SPSS. Click here for more information on parametric tests.

In this table you can see what test to use:

Afbeelding met tafel

Automatisch gegenereerde beschrijving

When performing a test, you first have to test your data for normality. You do this by following these steps in SPSS:

Analyze --> descriptive statistics --> explore

--> plots --> check histogram and check normality plots

Then you get two tests of normality. You use the Smirnov when using >2000 participants, otherwise you use the Shapiro. If this test is significant, the assumption of normality is NOT met.

If the assumption of normality of not met, you can still conduct an analysis, but you have to test with non-parametric tests. In the table above you can see what test to use.

Non-parametric vs parametric:

Pro: non-parametric is robust against the violation of the normality assumption
Con: less powerful

You can also log-transform. Non-parametric vs. los-transform:

Pro: non-parametric outcome is easier to interpret than log-transform
Con: less powerful

Mann-Whitney U-test

Analyze --> nonparametric tests --> legacy dialogs --> 2 independent samples

Test variable: enter the dependent variable. Group: enter the grouping variable.

Exact --> exact

Look at the exact sig. (2-tailed) for the significance. If it is significant, calculate the effect size.

Kruskall-Wallis test

Analyze --> nonparametic tests --> independent samples

Enter the variables in 'fields'. Then click settings --> customize test --> Kruskall-Wallis --> Stepwise step-down.

As output you get a decision. You also get a subset table. If the variables are in different subsets, they differ signifantly from eachother. You do not get a seperate p-value for this. When reporting, also report the H and the freedom of degrees.

Wilcoxon Signed-Rak test

Analyze --> nonparametric test --> legacy dialogs --> 2 related samples

Enter the variables in the 'test pairs'. Check descriptives under options (if you want these)

Report at least the Z-value, the p-value and the effect size.

Friedman test

Analyze --> Nonparametric test --> related samples --> enter variables in 'fields' --> settings --> customize --> friedman 2 way --> stepwise step-down.

How to calculate effect sizes

For an ANOVA, you can just give the partial eta-squared. For others you might have to calculate it yourself using:

Cohen’s d:

Afbeelding met tafel

Automatisch gegenereerde beschrijving

Pearson’s r:

Afbeelding met tekst, klok

Automatisch gegenereerde beschrijving

The effect sizes can be interpreted using this table (also report the interpretation!):

Afbeelding met tafel

Automatisch gegenereerde beschrijving

Questions? Let me know in the contribution section!

Follow me for more summaries on statistics!

Access:

Public

Verzekeren bij een faire en solidaire zorgverzekeraar?

Join: WorldSupporter!

Join with a free account for more service, or become a member for full access to exclusives and extra support of WorldSupporter >>

Check: concept of JoHo WorldSupporter

Concept of JoHo WorldSupporter

JoHo WorldSupporter mission and vision:

JoHo wants to enable people and organizations to develop and work better together, and thereby contribute to a tolerant and sustainable world. Through physical and online platforms, it supports personal development and promote international cooperation is encouraged.

JoHo concept:

As a JoHo donor, member or insured, you provide support to the JoHo objectives. JoHo then supports you with tools, coaching and benefits in the areas of personal development and international activities.
JoHo's core services include: study support, competence development, coaching and insurance mediation when departure abroad.