Choosing the Correct Statistic
by Edward J. Stepanksi Ph.d., Larry Hatcher, Norm O'Rourke
A Step-by-Step Approach to Using SAS® for Univariate & Multivariate Statistics, Second Edition
- Copyright
- Praise for the Second Edition
- Acknowledgments
- Using This Book
- Basic Concepts in Research and DATA Analysis
- Introduction to SAS® Programs, SAS® Logs, and SAS® Output
- Data Input
- Introduction: Inputting Questionnaire Data versus Other Types of Data
- Entering Data: An Illustrative Example
- Inputting Data Using the DATALINES Statement
- Additional Guidelines
- Inputting a Correlation or Covariance Matrix
- Inputting Data Using the INFILE Statement Rather than the DATALINES Statement
- Controlling the Output Size and Log Pages with the OPTIONS Statement
- Conclusion
- Reference
- Working with Variables and Observations in SAS® Datasets
- Exploring Data with PROC MEANS, PROC FREQ, PROC PRINT, and PROC UNIVARIATE
- Measures of Bivariate Association
- Assessing Scale Reliability with Coefficient Alpha
- t Tests: Independent Samples and Paired Samples
- One-Way ANOVA with One Between-Subjects Factor
- Introduction: The Basics of One-Way ANOVA, Between-Subjects Design
- Example with Significant Differences between Experimental Conditions
- Example with Nonsignificant Differences between Experimental Conditions
- Understanding the Meaning of the F Statistic
- Using the LSMEANS Statement to Analyze Data from Unbalanced Designs
- Conclusion
- Assumptions Underlying One-Way ANOVA with One Between-Subjects Factor
- References
- Factorial ANOVA with Two Between-Subjects Factors
- Introduction to Factorial Designs
- Some Possible Results from a Factorial ANOVA
- Example with a Nonsignificant Interaction
- Example with a Significant Interaction
- Using the LSMEANS Statement to Analyze Data from Unbalanced Designs
- Conclusion
- Assumptions Underlying Factorial ANOVA with Two Between-Subjects Factors
- Multivariate Analysis of Variance (MANOVA) with One Between-Subjects Factor
- One-Way ANOVA with One Repeated-Measures Factor
- Factorial ANOVA with Repeated-Measures Factors and Between-Subjects Factors
- Introduction: The Basics of Mixed-Design ANOVA
- Some Possible Results from a Two-Way Mixed-Design ANOVA
- Problems with the Mixed-Design ANOVA
- Example with a Nonsignificant Interaction
- Example with a Significant Interaction
- Use of Other Post-Hoc Tests with the Repeated-Measures Variable
- Conclusion
- Assumptions Underlying Factorial ANOVA with Repeated-Measures Factors and Between-Subjects Factors
- References
- Multiple Regression
- Introduction: Answering Questions with Multiple Regression
- Background: Predicting a Criterion Variable from Multiple Predictors
- The Results of a Multiple Regression Analysis
- Example: A Test of the Investment Model
- Overview of the Analysis
- Gathering and Entering Data
- Computing Bivariate Correlations with PROC CORR
- Estimating the Full Multiple Regression Equation with PROC REG
- Computing Uniqueness Indices with PROC REG
- Summarizing the Results in Tables
- Getting the Big Picture
- Conclusion: Learning More about Multiple Regression
- Assumptions Underlying Multiple Regression
- References
- Principal Component Analysis
- Introduction: The Basics of Principal Component Analysis
- Example: Analysis of the Prosocial Orientation Inventory
- SAS Program and Output
- Steps in Conducting Principal Component Analysis
- An Example with Three Retained Components
- Conclusion
- Assumptions Underlying Principal Component Analysis
- References
- Choosing the Correct Statistic
- Datasets
- Critical Values of the F Distribution
- Books Available from SAS Press
- Wiley Series in Probability and Statistics
- Wiley Series in Probability and Statistics
- Index
Appendix A. Choosing the Correct Statistic
| Introduction: Thinking about the Number and Scale of Your Variables | 484 |
| Guidelines for Choosing the Correct Statistic | 486 |
| Conclusion | 490 |
| Reference | 490 |
OverviewThis appendix provides a structured approach for choosing the correct statistical procedure to use when analyzing data. With this approach, the choice of a specific statistic is based on the number and scale of the criterion (dependent) variables in the study considered in conjunction with the number and scale of the predictor (independent) variables. Commonly used statistics are grouped into three tables based on the number of criterion and predictor variables in the analysis. |
-
No Comment
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.