Applied Power Analysis for the Behavioral Sciences

✍ Scribed by Christopher L. Aberson

• Year: 2019
• Tongue: English
• Leaves: 215
• Edition: 2
• Category: Library

✦ Synopsis

Revised edition of the author's Applied power analysis for the behavioral sciences, [2010]

✦ Table of Contents

Cover
Half Title
Title Page
Copyright Page
Table of Contents
List of Figures
List of Tables
Preface
Overview of the Book
What is New in this Edition?
Formulae and Calculations
Approaches to Power
The pwr2ppl Companion Package
Acknowledgments
1 What is Power? Why is Power Important?
Review of Null Hypothesis Significance Testing
Effect Sizes and Their Interpretation
What Influences Power?
Central and Noncentral Distributions
Misconceptions about Power
Empirical Reviews of Power
Consequences of Underpowered Studies
Overview of Approaches to Determining Effect Size for Power Analysis
Post Hoc Power (a.k.a. Observed or Achieved Power)
How Much Power?
Summary
Notes
2 Chi Square and Tests for Proportions
Necessary Information
Factors Affecting Power
Key Statistics
Example 2.1: 2 × 2 Test of Independence
Example 2.2: 2 × 2 Chi Square Test for Independence Using R
Example 2.3: Other χ2 Tests
Example 2.4: General Effect Size-Based Approaches Using R
Tests for Single Samples and Independent Proportions
Example 2.5: Single Sample Comparison
Example 2.6: Independent Proportions Comparison
Additional Issues
Summary
Note
3 Independent Samples and Paired t-tests
Necessary Information
Factors Affecting Power
Key Statistics
A Note about Effect Size for Two-Group Comparisons
Example 3.1: Comparing Two Independent Groups
Example 3.2: Power for Independent Samples t using R
Example 3.3: Paired t-test
Example 3.4: Power for Paired t using R
Example 3.5: Power from Effect Size Estimate
Dealing with Unequal Variances, Unequal Sample Sizes, and Violation of Assumptions
Example 3.6: Unequal Variances and Unequal Sample Sizes
Additional Issues
Summary
Notes
4 Correlations and Differences between Correlations
Necessary Information
Factors Affecting Power
Zero-Order Correlation
Example 4.1: Zero-order Correlations
Comparing Two Independent Correlations
Example 4.2: Comparing Independent Correlations
Comparing Two Dependent Correlations (One Variable in Common)
Example 4.3: Comparing Dependent Correlations, One Variable in Common
Comparing Two Dependent Correlations (No Variables in Common)
Example 4.4: Comparing Dependent Correlations, No Variables in Common
Note on Effect Sizes for Comparing Correlations
Additional Issues
Summary
Note
5 Between Subjects ANOVA (One and Two Factors)
Necessary Information
Factors Affecting Power
Omnibus Versus Contrast Power
Key Statistics
Example 5.1: One Factor ANOVA
Example 5.2: One Factor ANOVA with Orthogonal Contrasts
ANOVA with Two Factors
Example 5.3: Two Factor ANOVA with Interactions
Power for Multiple Effects
Additional Issues
Summary
Note
6 Within Subjects Designs with ANOVA and Linear
Necessary Information
Factors Affecting Power
Key Statistics
Example 6.1: One Factor Within Subjects Design
Example 6.2: Sphericity Adjustments
Example 6.3: Linear Mixed Model Approach to Repeated Measures
Example 6.4: A Serious Sphericity Problem
Trend Analysis
Example 6.5: Trend Analysis
Example 6.6: Two Within Subject Factors Using ANOVA
Example 6.7: Simple Effects Using ANOVA
Example 6.8: Two Factor Within and Simple Effects Using LMM
Additional Issues
Summary
7 Mixed Model ANOVA and Multivariate ANOVA
Necessary Information
Factors Affecting Power
Key Statistics
ANOVA with Between and Within Subject Factors
Example 7.1: ANOVA with One Within Subjects Factor and One Between Subjects Factor
Example 7.2: Linear Mixed Model with One Within Subjects Factor and One Between Subjects Factor
Multivariate ANOVA
Example 7.3: Multivariate ANOVA
Additional Issues
Summary
8 Multiple Regression
Necessary Information
Factors Affecting Power
Key Statistics
Example 8.1: Power for a Two Predictor Model (R2 Model and Coefficients)
Example 8.2: Power for Three Predictor Models
Example 8.3: Power for Detecting Differences between Two Dependent Coefficients
Example 8.4: Power for Detecting Differences between Two Independent Coefficients
Example 8.5: Comparing Two Independent R2 Values
Multiplicity and Direction of Predictor Correlations
Example 8.6: Power(All) with Three Predictors
Additional Issues
Summary
Notes
9 Analysis of Covariance, Moderated Regression, Logistic Regression, and Mediation
Analysis of Covariance
Example 9.1: ANCOVA
Moderated Regression Analysis (Regression with Interactions)
Example 9.2: Regression Analogy (Coefficients)
Example 9.3: Regression Analogy (R2 Change)
Example 9.4: Comparison on Correlations/Simple Slopes
Logistic Regression
Example 9.5: Logistic Regression with a Single Categorical Predictor
Example 9.6: Logistic Regression with a Single Continuous Predictor
Example 9.7: Power for One Predictor in a Design with Multiple Predictors
Mediation (Indirect Effects)
Example 9.8: One Mediating Variable
Example 9.9: Multiple Mediating Variables
Additional Issues
Summary
10 Precision Analysis for Confidence Intervals
Necessary Information
Confidence Intervals
Types of Confidence Intervals
Example 10.1: Confidence Limits around Differences between Means
Determining Levels of Precision
Confidence Intervals around Effect Sizes
Example 10.2: Confidence Limits around d
Precision for a Correlation
Example 10.3: Confidence Limits around r
Example 10.4: Precision for R2
Supporting Null Hypotheses
Example 10.5: “Supporting” Null Hypotheses
Additional Issues
Summary
Notes
11 Additional Issues and Resources
Accessing the Analysis Code
Using Loops to Get Power for a Range of Values
How to Report Power Analyses
Example 11.1: Reporting a Power Analysis for a Chi-Square Analysis
Example 11.2: Reporting a Power Analysis for Repeated Measures ANOVA
Reporting Power if Not Addressed A Priori
Statistical Test Assumptions
Effect Size Conversion Formulae
General (Free) Resources for Power and Related Topics
Resources for Additional Analyses
Improving Power without Increasing Sample Size or Cost
References
Index