Scribd
Upload
13 views3 pages

Statistical Tests Overview Guide

The document outlines various statistical tests used for comparing means, measuring relationships, and analyzing data characteristics. It categorizes tests into parametric and non-parametric types, specifying the assumptions and suitable situations for each test. Examples include the independent t-test, ANOVA, and correlation tests, along with their appropriate applications based on data type and distribution.

Uploaded by

nikdaniaazmira
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
13 views3 pages

Statistical Tests Overview Guide

The document outlines various statistical tests used for comparing means, measuring relationships, and analyzing data characteristics. It categorizes tests into parametric and non-parametric types, specifying the assumptions and suitable situations for each test. Examples include the independent t-test, ANOVA, and correlation tests, along with their appropriate applications based on data type and distribution.

Uploaded by

nikdaniaazmira
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

Test Characteristics Assumptions Parametric / Suitable Situations

Non-parame (When to Use)


tric

Independent Compares means of • Normality• Equal Parametric Compare scores


t-test 2 independent variances between 2
groups (Levene’s test)• unrelated groups
Interval/ratio DV (e.g., male vs
female, Class A vs
Class B).

One-way Compares means of • Normality• Parametric Compare means of


Independent 3 or more Homogeneity of 3+ groups (e.g.,
ANOVA independent groups variance• three teaching
Interval/ratio DV methods).

One-way Same participants • Normality• Parametric Compare


Repeated measured 3+ times Sphericity measurements over
Measures (Mauchly’s test)• 3+ time points
ANOVA Interval/ratio DV (Week 1 vs Week 4
vs Week 8).

Paired t-test Compares means of • Normality of Parametric Pre-test vs Post-test


2 related difference scores• for same group.
measurements Interval/ratio DV

Correlation Measures strength & • Both variables Parametric To see if two


(Pearson) direction of linear continuous• continuous
relationship between Linear variables relate
2 continuous relationship• (e.g., hours studied
variables Normality & exam score).
Mann–Whitney Compares 2 • Non-normal data Non-parame Alternative to
U test independent groups OR ordinal data• tric independent t-test
(median/ranks) Independent when data is not
groups normal or DV is
ordinal.

Kruskal–Wallis Compares 3+ • Non-normal DV Non-parame Alternative to


test independent groups OR ordinal data• tric one-way ANOVA for
(medians/ranks) Independent 3+ groups with
groups non-normal or
ordinal data.

Wilcoxon Compares 2 related • Non-normal Non-parame Alternative to


Signed-Rank samples (median paired data• tric paired t-test for
test differences) Ordinal or non-normal data.
continuous DV

Friedman’s test Compares 3+ related • Non-normal Non-parame Alternative to


samples (ranks) repeated tric repeated-measures
measures• ANOVA for 3+ time
Ordinal or points.
continuous DV

Chi-square Test Tests relationship • Expected cell Non-parame Used for gender ×
of between two count ≥ 5• tric preference, race ×
Independence categorical Independent employment, etc.
variables observations•
Nominal
categories
Correlation Measures strength & • Ordinal or Non-parame Alternative to
(Spearman) direction of non-normal tric Pearson correlation
monotonic continuous data• when data is
relationship between Monotonic ordinal or not
2 ranked variables relationship normal.

You might also like