Scribd
Upload
15 views

Khater

Uploaded by

123456789ra.com
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
15 views

Khater

Uploaded by

123456789ra.com
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

By: Mohamed Khater

(Comparison between Correlation-Simple Regression-Multiple Regression-One way ANOVA-TWO Way ANOVA)

Feature Correlation Simple Regression Multiple Regression One-way ANOVA Two-way ANOVA

Measure the strength Predict the dependent Predict dependent variable Assess interaction effects
Compare means across
Purpose & direction of linear variable based on one based on multiple between two categorical
multiple groups
relationship independent variable independent variables variables

Categorical Categorical
Continuous and/or Continuous and/or
Types of Variables Continuous (independent) and (independent) and
categorical categorical
continuous (dependent) continuous (dependent)

Equation
Interaction effects, main
Output Correlation coefficient Equation 𝑦=𝑚𝑥+𝑏 𝑦=𝑏0+𝑏1𝑥1+𝑏2𝑥2+...+𝑏𝑛𝑥𝑛 F-statistic
effects, F-statistics

Directionality Symmetric Directional Directional Directional Directional


Does not imply Does not imply
Causality Can imply causation Can imply causation Can imply causation
causation causation

Assessing relationships, Prediction, hypothesis Prediction, understanding Experimental research, Experimental research,
Application
preliminary analysis testing relationships hypothesis testing hypothesis testing

Correlation coefficient
Ordinary Least Squares F-statistic, interaction
Analysis Technique (e.g., Pearson, OLS, logistic regression, etc. F-statistic
(OLS) effects
Spearman)
Simple interpretation, Simple and Can handle multiple Ability to compare Ability to assess
Advantage
easy to calculate interpretable, flexible predictors multiple groups interaction effects

Assumes homogeneity Assumes homogeneity of


Does not imply
Assumes linear Can overfit, assumes linear of variances, can't variances, complexity
Disadvantage causation, limited to
relationships, can overfit relationships handle non-parametric increases with more
linear relationships
data factors

You might also like