Scribd
Upload
414 views2 pages

Hypothesis Testing Roadmap

This document provides guidance on selecting appropriate statistical tests based on whether the input (X) and output (Y) variables are continuous or categorical. It outlines tests to compare means, medians, variances, and proportions between two or more samples. Key tests mentioned include t-tests, ANOVA, Wilcoxon, Mann-Whitney, Kruskal-Wallis, chi-square, and logistic regression. It also provides a hypothesis testing protocol and outlines graphical methods like scatter plots, histograms, and box plots to accompany statistical analyses.

Uploaded by

Ram Kumar
Copyright
© Attribution Non-Commercial (BY-NC)
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
414 views2 pages

Hypothesis Testing Roadmap

This document provides guidance on selecting appropriate statistical tests based on whether the input (X) and output (Y) variables are continuous or categorical. It outlines tests to compare means, medians, variances, and proportions between two or more samples. Key tests mentioned include t-tests, ANOVA, Wilcoxon, Mann-Whitney, Kruskal-Wallis, chi-square, and logistic regression. It also provides a hypothesis testing protocol and outlines graphical methods like scatter plots, histograms, and box plots to accompany statistical analyses.

Uploaded by

Ram Kumar
Copyright
© Attribution Non-Commercial (BY-NC)
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

Output (Y)

Continuous Categorical

Hypothesis Testing of Categorical Inputs (Xs)*


Continuous Y Data
Normality Normality Test Test
1 Sample H H :: Data Data is are Normal Normal O O H H :: Data Data is are not not Normal Normal a a Stat>Basic Stat>Basic Stat>Normality Stat>NormalityTest Test or or Stat>Basic Stat>Basic Stat>Graphical Stat>Graphical Summary Summary

1-Proportion Test
1 Sample

Input (X)

HO: p1 = Ptarget Ha: p1 , <, or > Ptarget


Stat>Basic Stat> 1-Proportion

Continuous

Categorical Y Data
2 Samples

Categorical

2-Proportion Test

Data are Not Normal


2 or More Samples 2 or More Samples 1 Sample

Data are Normal


2 or more Samples 2 Samples
For 2 or more Samples, Test for Independence

Ho: p1 = p2 Ha: p1 , <, or > p2 Stat>Basic Stat> 2-Proportion

Compare Variances
HO: 1= 2 = 3 Ha: i j for i to j (or at least one is different) Stat>ANOVA> Test for Equal Variances

Levenes Test

Compare Variance to Target


HO: 1 = target Ha: 1 target Stat>Basic Stat>Graphical Summary (if target std dev. falls within 95% CI, then fail to reject HO; otherwise, reject)

Compare Mean differences


Paired t-Test
HO: d = O Ha: d , <, or > O Stat>Basic Stat>Paired t

Compare 2 Means
2-Sample t-Test
HO:1 = 2 Ha: 1 , <, or > 2
Stat>Basic Stat>2-Sample t uncheck: Assume = Variances

Chi Square Test


HO: FA Independent FB Ha: FA Dependent FB Stat>Tables>Chi2 Test

Chi2 Test

Compare Variance to Target


HO: 1 = target Ha: 1 target Stat>Basic Stat>Graphical Summary

Chi2 Test

Compare 2 Medians
Mann-Whitney Test
(if several outliers, use Moods Median test) HO: 1 = 2 Ha: 1 , <, or > 2 Stat>Nonparametrics> Mann-Whitney (Moods Median Test)

Compare Variances
Bartletts Test (> 2) or F-Test (2)
HO: 21 = 2 2 = 23 Ha: 2i 2j for i to j

1 Sample

Compare Median to Target


1-Sample Wilcoxon
(if several outliers, use 1Sample Sign test) HO: 1 = target Ha: 1 , <, or > target Stat>Nonparametrics> 1-Sample Wilcoxon (1Sample Sign)

(or at least one is different) Stat>ANOVA>Test for Equal Variance

(if target std dev. falls within 95% CI for std dev, then fail to reject HO: reject otherwise)

Equal Variances

Compare Mean to Target


1-Sample t-Test
HO: 1 = target Ha: 1 , <, or > target
Stat>Basic Stat>1-Sample t

Compare More Than 2 Medians


Kruskal-Wallis Test
(if several outliers, use Moods Median test) HO: 1 = 2 = 3 Ha: i j for i to j (or at least one is different)
Stat>Nonparametrics> Kruskal-Wallis (Moods Median Test)

Compare More Than 2 Means


1-Way ANOVA
(assumes equality of variances) HO: 1 = 2 = 3 Ha: i j for i to j (or at least one is different) Stat>ANOVA>1-Way (select stacked or unstacked data)

Compare 2 Means
2-Sample t-Test
HO: 1 = 2 Ha: 1 , <, or > 2 Stat>Basic Stat>2-Sample t Check: Assume = Variances (uses pooled std dev)

*NOTE: If X is Continuous and Y is Continuous, proceed with Regression and Correlation Analysis.

If P-value P-Value alpha, alpha, then then reject reject H Ho o If P-value P-Value > > alpha, alpha, then then fail fail to to reject reject H Ho o Alpha is usually pre-set at 0.05. Use other values as appropriate. If P-value P-Value > > alpha, alpha, ensure ensure sufficient sufficient power and correct sample size if necessary.

Hypothesis Testing Protocol


Practical Problem or Theory: State problem or state theory to be proven. Statistical Problem: State Ho and Ha (with the correct test in mind) Statistical Analysis: Test to be used, alpha and power. Run test, show printout, results and p-value Statistical Conclusion: Based on p-value, Reject Ho or Fail to Reject Ho. (If the p is low, the null must go) Practical Conclusion: Answer to your practical problem. Theory is proven true or not.

Hypothesis Tests by Data Type

Y
Continuous Continuous
How does change in X affect change in Y? Statistical: Regression

Categorical
Logistic Regression (out of scope)

Graphical: Scatter Diagrams

X
Categorical

Means or Medians Different? Statistical: If Normal: t-tests; ANOVA If Non-Normal: Wilcoxon, MannWhitney, Kruskal-Wallis Graphical: Histograms; Box Plots Variance Different? Statistical: Test for Equal Variances (Bartletts, Levenes) Graphical: Histograms; Box Plots

Are the outputs different? Statistical: Chi Square, Proportions tests Graphical: Pareto Diagrams; Stratification

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy