Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
91 views2 pages

What Test Flowchart and Table

This document provides a table comparing parametric and non-parametric statistical tests that can be used depending on the scale and number of variables being examined. The table lists common tests for comparing means of independent and paired groups, investigating relationships between variables, predicting values, and assessing relationships between nominal variables. It also provides guidance on using regression versus ANOVA when variables include both scale/binary and categorical factors.

Uploaded by

iyerpadma
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
91 views2 pages

What Test Flowchart and Table

This document provides a table comparing parametric and non-parametric statistical tests that can be used depending on the scale and number of variables being examined. The table lists common tests for comparing means of independent and paired groups, investigating relationships between variables, predicting values, and assessing relationships between nominal variables. It also provides guidance on using regression versus ANOVA when variables include both scale/binary and categorical factors.

Uploaded by

iyerpadma
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Table of tests Dependent Independent Parametric test Non-parametric

(outcome) (explanatory) alternative


variable variable

Comparing means

The averages of two Scale Nominal/ Independent t-test Mann-Whitney test


INDEPENDENT groups binary (Wilcoxon rank sum)

The averages of 3+ independent Scale Nominal One-way ANOVA Kruskal-Wallis test


groups

The averages of 2 paired Scale Nominal Paired t-test Wilcoxon signed rank
(matched) samples e.g. weight Time/conditi test
before and after a diet on variable

The 3+ measurements on the same Scale Nominal Repeated measures Friedman test
subject ANOVA

Investigating relationships

Relationship between 2 Scale Scale Pearson’s Spearman’s


continuous variables Correlation Correlation Coefficient
Coefficient

Predicting the value of one Scale Any number of Simple Linear Transform the data
variable from the value of a scale or binary Regression
predictor variable
Binary Any number of Logistic regression
scale or binary

Assessing the relationship Nominal Nominal Chi-squared test


between two Nominal variables

One scale dependent and several independent variables


1st independent 2nd independent Test
Scale Scale/ binary Multiple regression
Nominal (Independent groups) Nominal (Independent groups) 2 way ANOVA
Nominal (repeated measures) Nominal (repeated measures) 2 way repeated measures ANOVA
Nominal (Independent groups) Nominal (repeated measures) Mixed ANOVA
Nominal Scale ANCOVA

Regression or ANOVA? Use regression if you have only scale or binary independent variables. Categorical
variables can be recoded to dummy binary variables but if there are a lot of categories, ANOVA is
preferable.

You might also like