Cover
Title Page
Copyright Page
Brief Contents
Detailed Contents
Preface
New To This Edition
The Online Data Files
Other Features Of The Book
After This Lesson, You Will Know
Key Words
Typing Conventions
Examples
Tips
System Requirements For SPSS 21 For Windows
System Requirements For SPSS 21 For Mac OS X
Acknowledgments
About the Authors
Part I: Introducing SPSS
UNIT 1. Getting Started with SPSS
Lesson 1. Starting SPSS
After This Lesson, You Will Know
Key Words
Starting SPSS
The SPSS Opening Window
Lesson 2. The SPSS Main Menus and Toolbar
After This Lesson, You Will Know
Key Words
The SPSS Main Menus
The File Menu
The Edit Menu
The View Menu
The Data Menu
The Transform Menu
The Analyze Menu
The Direct Marketing Menu
The Graphs Menu
The Utilities Menu
The Add-ons Menu
The Window and Help Menus
The SPSS Toolbar and Status Bar
The Data Files
The Crab Scale File
The Teacher Scale File
Lesson 3. Using SPSS Help
After This Lesson, You Will Know
Key Words
How To Get Help
Using Contents
Using F1 - Using Context Sensitive Help
Using the Search Option
Lesson 4. A Brief SPSS Tour
After This Lesson, You Will Know
Key Words
Opening a File
Working With Appearance
Creating a New Variable
A Simple Table
A Simple Analysis
UNIT 2. Creating and Working with Data Files
Lesson 5. Defining Variables
After This Lesson, You Will Know
Key Words
Creating An SPSS New Window
Having SPSS Define Variables
Custom Defining Variables: Using The Variable View Window
Defining Variable Names
Defining Variable Types
Defining Variable Widths
Defining Variable Decimals
Defining Variable Labels
Defining Variable Values
Defining Missing Values for a Variable
Defining Variable Columns
Defining Variable Alignment
Defining Variable Measure
Defining Role
Lesson 6. Entering and Editing Data
After This Lesson, You Will Know
Key Words
Getting Ready For Data
Entering Data
Editing Data
Changing a Cell Value
Editing a Cell Value
Saving a Data File
Saving a File in a New Location
Opening a File
Closing a File
Lesson 7. Inserting and Deleting Cases and Variables
After This Lesson, You Will Know
Key Words
Inserting a Case
Inserting a Variable
Deleting a Case
Deleting a Variable
Lesson 8. Selecting, Copying, Cutting, and Pasting Data
After This Lesson, You Will Know
Key Words
Copying, Cutting, And Pasting
Selecting Data
Cutting and Pasting
Copying And Pasting
Whre Copied Or Cut Data Go
Lesson 9. Printing and Exiting an SPSS Data File
After This Lesson, You Will Know
Key Word
Printing With SPSS
Printing an SPSS Data File
Printing a Selection from an SPSS Data File
Printing from the Viewer Window
Creating PDF Documents
Exiting SPSS
Lesson 10. Exporting and Importing SPSS Data
After This Lesson, You Will Know
Key Words
Getting Started Exporting and Importing Data
Exporting Data
Exporting a Chart
Exporting Output
Importing Data
Lesson 11. Validating SPSS Data
After This Lesson, You Will Know
Key Word
Validating a Data Set
Loading The Predefined Rules
Validating the Data Set Using Predefined Rules
Other Validate Data Dialog Box Options
Using a Single-Variable Rule
UNIT 3. Working with Data
Lesson 12. Finding Values, Variables, and Cases
After This Lesson, You Will Know
Key Words
Finding Things
Finding Variables
Finding Cases
Finding Values
Lesson 13. Recording Data and Computing Values
After This Lesson, You Will Know
Key Words
Recoding Data
Computing Values
Creating a Formula
Using a Function
Lesson 14. Sorting, Transposing, and Ranking Data
After This Lesson, You Will Know
Key Words
Sorting Data
Sorting Data on One Variable
Sorting Data on More Than One Variable
Transposing Cases and Variables
Assigning Ranks To Data
Lesson 15. Splitting and Merging Files
After This Lesson, You Will Know
Key Words
Splitting Files
Merging Files
Merging Same Variables and Different Cases
Merging Different Variables and Same Cases
UNIT 4A. Working with SPSS Graphs and Output for Windows
Lesson 16A. Creating an SPSS Graph
After This Lesson, You Will Know
Key Words
Creating a Simple Graph
Creating a Line Graph
Saving a Graph
Printing a Graph
Different SPSS Graphs
The Bar Graph
Scatter/Dot
The Pie Graph
UNIT 4B. Working with SPSS Charts and Output for the Macintosh
Lesson 16B. Creating an SPSS Chart
After This Lesson, You Will Know
Key Words
Creating a Simple Chart
Creating a Line Chart
Saving a Chart
Printing a Chart
Different SPSS Charts
The Bar Chart
The Scatter/Dot Graph
The Pie Chart
Lesson 17A. Enhancing SPSS Graphs
After This Lesson, You Will Know
Key Words
Modifying a Chart
Working with Titles and Subtitles
Working with Fonts
Working with Axes
How to Modify the Scale (Y) Axis
How to Modify the Category (X) Axis
Working with Patterns and Colors
Changing Patterns
Changing Colors
Setting Chart Preferences
Getting Fancy
Using a Chart Template and Creating An Apa-Style Graph
Lesson 17B. Enhancing SPSS Charts
After This Lesson, You Will Know
Key Words
Modifying a Chart
Working with Titles and Creating Subtitles
Working with Frames
Working with Axes
Working with Patterns and Colors
Changing Patterns
Changing Colors
Lesson 18A. Using the Viewer and Pivot Tables
After This Lesson, You Will Know
Key Words
Saving Viewer Output
To Selectively Show and Hide Results
Printing The Contents Of The Viewer Window
Printing a Selection From The Viewer Window
Deleting Output
Moving Output
An Introduction To Pivot Tables
Using the Pivot Tray
Changing Table Appearance
Using TableLooks
Using Table Properties
Lesson 18B. Using the Viewer
After This Lesson, You Will Know
Key Words
Saving Viewer Output
To Selectively Show and Hide Results
Printing The Contents Of The Viewer Window
Printing a Selection from the Viewer Window
Deleting Output
Moving Output
Part II: Working with SPSS Procedures
UNIT 5. Creating Variables and Computing Descriptive Statistics
Lesson 19. Creating Variables
Applications For Creating Variables
The Data Set
Creating Variables
Creating an Overall Scale from Variables with the Same Metric and No Reverse-Scaling
Creating an Overall Scale from Variables with the Same Metric and Reverse-Scaling
Reverse-Scaling
Computing Total Scale Scores
Creating an Overall Scale from Variables with Different Metrics and No Reverse-Scaling
Creating Standardized Scores
Computing Total Scale Scores
Creating an Overall Scale from Variables with Different Metrics and Reverse-Scaling
Creating Standardized Scores
Reverse-Scaling Standardized Scores
Computing Total Scale Scores
Creating an Overall Scale from Variables with Missing Data
Creating a Qualitative Variable from One Quantitative Variable
Creating a Qualitative Variable from Two Quantitative Variables
Exercises
Lesson 20. Univariate Descriptive Statistics for Qualitative Variables
Applications For Describing Qualitative Variables
Qualitative Variables with Two Categories
Qualitative Variables with a Moderate Number of Categories
Qualitative Variables with Many Categories
Understanding Descriptive Statistics For Qualitative Variables
The Data Set
The Research Question
Conducting Descriptive Statistics For Qualitative Variables
Selected SPSS Output for Frequencies
Using SPSS Graphs To Display The Results
Creating a Bar Chart
Creating a Pie Chart
An Apa Participants Section
Exercises
Lesson 21. Univariate Descriptive Statistics for Quantitative Variables
Applications For Describing Quantitative Variables
Quantitative Variables with Few Values
Quantitative Variables with Many Values
Quantitative Variables within Levels of a Qualitative Variable
z Scores and Percentile Ranks on Quantitative Variables
Understanding Descriptive Statistics For Quantitative Variables
The Data Set
Conducting Descriptive Statistics For Quantitative Variables
Computing Descriptive Statistics for Quantitative Variables
Selected SPSS Output for Quantitative Variables
Computing Descriptive Statistics for Quantitative Variables within Levels of a Qualitative Variable
Selected SPSS Output for Quantitative Variables within Levels of a Qualitative Variable
Converting Scores to z Scores and Percentile Ranks Not Assuming Normality
Selected SPSS Output for Converting Scores, Not Assuming Normality
Converting Scores to z Scores and Percentile Ranks Assuming Normality
Using SPSS Graphs To Display The Results
Creating a Histogram
Creating a Stem-and-Leaf Plot
Creating a Boxplot for Different Levels of a Qualitative Variable
Creating Error Bar Charts
An Apa Participants Section
Creating Figures In Apa Format
Creating Tables In Apa Format
Exercises
UNIT 6. t Test Procedures
Lesson 22. One-Sample t Test
Applications Of The One-Sample t Test
Test Value as the Midpoint on the Test Variable
Test Value as the Average Value of the Test Variable Based on Past Research
Test Value as the Chance Level of Performance on the Test Variable
Understanding The One-Sample t Test
Assumptions Underlying the One-Sample t Test
Assumption 1: The Test Variable Is Normally Distributed In The Population
Assumption 2: The Cases Represent a Random Sample From The Population, and The Scores On The Test Variable Are Independent Of Each Other
Effect Size Statistics for the One-Sample t Test
The Data Set
The Research Question
Conducting a One-Sample t Test
SPSS Output for the One-Sample t Test
Using SPSS Graphs To Display The Results
An Apa Results Section
Writing An Apa Results Section
Exercises
Lesson 23. Paired-Samples t Test
Applications Of The Paired-Samples t Test
Repeated-Measures Designs with an Intervention
Repeated-Measures Designs with No Intervention
Matched-Subjects Designs with an Intervention
Matched-Subjects Design with No Intervention
Understanding The Paired-Samples t Test
Assumptions Underlying the Paired-Samples t Test
Assumption 1: Difference Scores Are Normally Distributed In The Population
Assumption 2: The Cases Represent a Random Sample From The Population, and The Defference Scores Are Independent Of Each Other
Effect Size Statistics for the Paired-Samples t Test
The Data Set
The Research Question
Conducting a Paired-Samples t Test
SPSS Output for the Paired-Samples t Test
Using SPSS Graphs To Display The Results
An Apa Results Section
Alternative Analyses
Exercises
Lesson 24. Independent-Samples t Test
Applications Of The Independent-Samples t Test
Experimental Study
Quasi-Experimental Study
Field Study
Understanding The Independent-Samples t Test
Assumptions Underlying the Independent-Samples t Test
Assumption 1: The Test Variable Is Normally Distributed In Each Of The Twopopulations (As Defined By The Grouping Variable)
Assumption 2: The Variances Of The Normally Distributed Test Variable Forthe Populations Are Equal
Assumption 3: The Cases Represent A Random Sample From The Population, and The Scores On The Test Variable Are Independent Of Each Other
Effect Size Statistics For The Independent-Samples t Test
The Data Set
The Research Question
Conducting An Independent-Samples t Test
SPSS Output for the Independent-Samples t Test
Using SPSS Graphs To Display The Results
An Apa Results Section
Alternative Analyses
Exercises
UNIT 7. Univariate and Multivariate Analysis-of-Variance Techniques
Lesson 25. One-Way Analysis of Variance
Applications Of One-Way Anova
Experimental Study
Quasi-Experimental Study
Understanding One-Way Anova
Assumptions Underlying One-Way Anova
Assumption 1: The Dependent Variable Is Normally Distributed For Each Of The Populations As Defined By The Different Levels Of The Factor
Assumption 2: The Variances Of The Dependent Variable Are The Same For All Populations
Assumption 3: The Cases Represent Random Samples From The Populations And The Scores On The Test Variable Are Independent Of Each Other
Effect Size Statistics for One-Way Anova
The Data Set
The Research Question
Conducting a One-Way Anova
Selected SPSS Output for One-Way Anova
Selected SPSS Output for Post Hoc Comparisons
Using SPSS Graphs To Display The Results
An Apa Results Section
Writing An Apa Results Section
Alternative Analyses
Exercises
Lesson 26. Two-Way Analysis of Variance
Applications Of Two-Way Anova
An Experimental Study
A Field Study
Understanding Two-Way Anova
Assumptions Underlying Two-Way Anova
Assumption 1: The Dependent Variable Is Normally Distributed For Each Of The Populations
Assumption 2: The Population Variances Of The Dependent Variable Are The same For All Cells
Assumption 3: The Cases Represent Random Samples From The Populations, And The Scores On The Dependent Variable Are Independent Of Each Other
Effect Size Statistics for Two-Way Anova
The Data Set
The Research Question
Conducting a Two-Way Anova
Conducting Tests of Main and Interactions Effects
Selected SPSS Output for Two-Way Anova Tests for Lesson 26 Data File 1
Selected SPSS Output for Two-Way ANOVA Tests for Lesson 26 Data File 2
Conducting Follow-Up Analyses To A Significant Main Effect
Selected SPSS Output for Pairwise Comparisons of Main Effect Means
Conducting Follow-Up Analyses To A Significant Interaction
Simple Main Effect Tests Following a Significant Interaction
1. Which Simple Main Effects Should Be Analyzed?
2. What Error Term Should Be Used To Conduct The Simple Main Effects?
Conducting Simple Main Effects Analyses
Selected SPSS Output for Simple Main Effects
Conducting Interaction Comparisons Following A Significant Interaction
Selected SPSS Output for Interaction Comparisons
Explaining the /lmatrix Commands for Tetrad Contrasts
Using SPSS Graphs to Display Results
Two Apa Results Sections
Results for Significant Main Effect And A Nonsignificant Interaction (Lesson 26 Data File 1)
Results for a Significant Interaction (Lesson 26 Data File 2)
A Word Of Caution: Additional Complexities Occur With Unequal Sample Sizes Across Cells
Exercises
Lesson 27. One-Way Analysis of Covariance
Applications Of The One-Way Ancova
Studies with a Pretest and Random Assignment to Factor Levels
Studies with a Pretest and Assignment to Factor Levels Based on the Pretest
Studies with a Pretest, Matching Based on the Pretest, and Random Assignment to Factor Levels
Studies with Potential Confounding
Understanding One-Way Ancova
Adequacy of One-Way Ancova for Each Application
Studies With A Pretest And Random Assignment To Factor Levels
Studies With A Pretest And Assignment To Factor Levels Based On The Pre-test
Studies With A Pretest, Matching Based On The Pretest, And Random Assignment to Factor Levels
Studies With Potential Confounding
Assumptions Underlying a One-Way Ancova
Assumption 1: The Dependent Variable Is Normally Distributed In The Population For Any Specific Value Of The Covariate And For Any One Level Of A Factor
Assumption 2: The Variances Of The Dependent Variable For The Conditional Distributions Described In Assumption 1 Are Equal
Assumption 3: The Cases Represent A Random Sample From The Population, And The Scores On The Dependent Variable Are Independent Of Each Other
Assumption 4: The Covariate Is Linearly Related To The Dependent Variable Within All Levels Of The Factor, And The Weights Or Slopes Relating The Covariate To The Dependent Variable Are Equal Across All Levels Of The Factor
Effect Size Statistics for One-Way Ancova
The Data Set
The Research Question
Conducting A One-Way Ancova And Related Analyses
Conducting a Test of the Homogeneity-of-Slopes Assumption
Selected SPSS Output for Test of the Homogeneity-of-Slopes Assumption
Conducting One-Way Ancova
Selected SPSS Results for the Group Main Effect and the Covariate
Conducting Tests of Simple Group Main Effects for Particular Values of the Covariate
Selected SPSS Output for Simple Group Main Effects
Using SPSS Graphs To Display The Results
An Apa Results Section
Results Assuming Homogeneity of Slopes
Results Not Assuming Homogeneity of Slopes
Alternative Analyses
Exercises
Lesson 28. One-Way Multivariate Analysis of Variance
Applications Of One-Way Manova
An Experimental Study
A Quasi-Experimental Study
Understanding One-Way Manova
Assumptions Underlying One-Way Manova
Assumption 1: The Dependent Variables Are Multivariately Normally Distributed For Each Population, With The Different Populations Being Defined By The Levels Of The Factor
Assumption 2: The Population Variances And Covariances Among The Dependent Variables Are The Same Across All Levels Of The Factor
Assumption 3: The Participants Are Randomly Sampled, And The Score On A Variable For Any One Participant Is Independent From The Scores On This Variable For All Other Participants
Effect Size Statistics for a One-Way Manova
The Data Set
The Research Question
Conducting A One-Way Manova
Selected SPSS Output for Manova
Selected SPSS Output for the Univariate Anova's
Selected SPSS Output for Follow-up Pairwise Comparisons
Using SPSS Graphs To Display The Results
An Apa Results Section
Exercises
Lesson 29. One-Way Repeated-Measures Analysis of Variance
Applications Of One-Way Repeated Measures Anova
Longitudinal Study
Experimental Study
Understanding One-Way Repeated-Measures Anova
Standard Univariate Assumptions
Assumption 1: The Dependent Variable Is Normally Distributed In The Population For Each Level Of The Within-subjects Factor
Assumption 2: The Population Variance Of Difference Scores Computed Between Any Two Levels Of A Within-subjects Factor Is The Same Value Regardless Of Which Two Levels Are Chosen
Assumption 3: The Cases Represent A Random Sample From The Population, And There Is No Dependency In The Scores Between Participants
Multivariate Assumptions
Assumption 1: The Difference Scores Are Multivariately Normally Distributed In The Population
Assumption 2: The Individual Cases Represent A Random Sample From The Population, And The Difference Scores For Any One Subject Are Independent From The Scores For Any Other Subject
Effect Size Statistics for One-Way Repeated-Measures Anova
The Data Set
The Research Question
Conducting A One-Way Repeated-Measures Anova
Selected SPSS Output for One-Way Repeated-Measures Anova
Selected SPSS Output for Pairwise Comparisons
Selected SPSS Output for Polynomial Contrasts
Using SPSS Graphs To Display The Results
An Apa Results Section
Exercises
Lesson 30. Two-Way Repeated-Measures Analysis of Variance
Applications of Two-Way Repeated-Measures Anova
Experimental Study with a Single Scale
Field Study with Multiple Scales
Understanding Two-Way Repeated-Measures Anova
Difference Scores Associated with the Coping Main Effect
Difference Scores Associated with the Time Main Effect
Difference Scores for the Interaction Effect
Assumptions Underlying a Two-Way Repeated-Measures Anova
Univariate Assumption 1: The Dependent Variable Is Normally Distributed In The Population For Each Combination Of Levels Of The Within-subjects Factors
Univariate Assumption 2: The Population Variances Of The Difference Variables Are Equal
Univariate Assumption 3: The Individuals Represent A Random Sample From The Population, And Scores Associated With Different Individuals Are Not Related
Multivariate Assumption 1: The Difference Scores Are Multivariately Normally Distributed In The Population
Multivariate Assumption 2: The Individuals Represent A Random Sample From The Population, And The Difference Scores For Any One Individual Are Independent From The Scores For Any Other Individual
Effect Size Statistics for Two-Way Repeated Measures Anova
The Data Set
The Research Question
Conducting a Two-Way Repeated-Measures Anova
Conducting Tests of Main and Interaction Effects
Selected SPSS Output for Two-Way Repeated-Measures Anova
Conducting Pairwise Comparisons Following a Significant Main Effect
Selected SPSS Output for Pairwise Comparisons for Time Main Effect
Conducting Simple Main Effect Analyses Following a Significant Interaction
Selected SPSS Output for Simple Main Effects
Conducting Interaction Comparisons Following a Significant Interaction
Selected SPSS Output for Interaction Comparisons
Using SPSS Graphs to Display the Results
An Apa Results Section
Exercises
UNIT 8. Correlation, Regression, and Discriminant Analysis Procedures
Lesson 31. Pearson Product-Moment Correlation Coefficient
Applications of the Pearson Correlation Coefficient
Study with a Correlation between Two Variables
Study with Correlations among Three or More Variables
Study with Correlations within and between Sets of Variables
Understanding the Pearson Correlation Coefficient
Assumptions Underlying the Significance Test
Assumption 1: The Variables Are Bivariately Normally Distributed
Assumption 2: The Cases Represent A Random Sample From The Population, And The Scores On Variables For One Case Are Independent Of Scores On These Variables For Other Cases
An Effect Size Statistic: A Pearson Correlation Coefficient
The Data Set
The Research Question
Conducting Pearson Correlation Coefficients
Conducting Pearson Correlation Coefficients among Variables within a Set
Selected SPSS Output for Pearson Correlations
Conducting Pearson Correlation Coefficients between Variables from Different Sets
Using SPSS Graphs to Display the Results
An Apa Results Section
Alternative Analyses
Exercises
Lesson 32. Partial Correlations
Applications of Partial Correlations
Partial Correlation between Two Variables
Partial Correlations among Multiple Variables within a Set
Partial Correlations between Sets of Variables
Understanding Partial Correlations
Research Hypotheses and Partial Correlations
Common Cause Hypothesis
Mediator Variable Hypothesis
Assumptions Underlying the Significance Test for a Partial Correlation Coefficient
Assumption 1: The Variables Are Multivariately Normally Distributed
Assumption 2: The Cases Represent A Random Sample From The Population, And Scores For One Case Are Independent Of Scores On Variables For Other Cases
An Effect Size Statistic: A Partial Correlation
The Data Set
The Research Question
Conducting Partial Correlations
Selected SPSS Output for Partial Correlations
Using SPSS Graphs to Display the Results
Creating a 3-D Scatterplot
Creating a Simple Scatterplot with Markers
An Apa Results Section
Alternative Analyses
Exercises
Lesson 33. Bivariate Linear Regression
Applications of Bivariate Linear Regression
Nonexperimental Study
Experimental Study
Understanding Bivariate Linear Regression
Fixed-Effects Model Assumptions for Bivariate Linear Regression
Assumption 1: The Dependent Variable Is Normally Distributed In The Population For Each Level Of The Independent Variable
Assumption 2: The Population Variances Of The Dependent Variable Are The Same For All Levels Of The Independent Variable
Assumption 3: The Cases Represent A Random Sample From The Population, And The Scores Are Independent Of Each Other From One Individual To The Next
Random-Effects Model Assumptions for Bivariate Linear Regression
Assumption 1: The X And Y Variables Are Bivariately Normally Distributed In The Population
Assumption 2: The Cases Represent A Random Sample From The Population, And The Scores On Each Variable Are Independent Of Other Scores On The Same Variable
Effect Size Statistics for Bivariate Linear Regression
The Data Set
The Research Question
Conducting a Bivariate Linear Regression Analysis
Selected SPSS Output for Bivariate Linear Regression
Using SPSS Graphs to Display the Results
Creating a Bivariate Scatterplot
Creating a Plot of Predicted and Residual Values
An Apa Results Section
Exercises
Lesson 34. Multiple Linear Regression
Applications of Multiple Regression
One Set of Predictors
Unordered Sets of Predictors
Ordered Sets of Predictors
Understanding Multiple Regression
Assumptions Underlying the Significance Test for the Multiple Correlation Coefficient
Fixed-effects Model Assumption 1: The Dependent Variable Is Normally Distributed In The Population For Each Combination Of Levels Of The Independent Variables
Fixed-effects Model Assumption 2: The Population Variances Of The Dependent Variable Are The Same For All Combinations Of Levels Of The Independent Variables
Fixed-effects Model Assumption 3: The Cases Represent A Random Sample From The Population, And The Scores Are Independent Of Each Other From One Individual To The Next
Random-effects Model Assumption 1: The Variables Are Multivariately Normally Distributed In The Population
Random-effects Model Assumption 2: The Cases Represent A Random Sample From The Population, And The Scores On Variables Are Independent Of Other Scores On The Same Variables
Effect Size Statistics for Multiple Regression
Multiple Correlation Indices
The Relative Importance Of Predictors: Using Part And Partial Correlations
The Data Set
The Research Question
Conducting a Multiple Regression
Conducting Multiple Regression with One Set of Predictors
Selected SPSS Output for One Set of Predictors
Conducting Multiple Regression with Two Unordered Sets of Predictors
Selected SPSS Output for Two Unordered Sets of Predictors
Conducting Multiple Regression with Two Ordered Sets of Predictors
Selected SPSS Output for Two Ordered Sets of Predictors
Using SPSS Graphs to Display the Results
Three Apa Results Sections
Results for One Set of Predictors
Results for Two Unordered Sets of Predictors
Results for Two Ordered Sets of Predictors
Tips for Writing an APA Results Section for Multiple Regression
Exercises
Lesson 35. Discriminant Analysis
Applications of Discriminant Analysis
Predicting Group Membership
Discriminant Analysis as a Follow-Up Procedure to Manova
Understanding Discriminant Analysis
Assumptions Underlying Discriminant Analysis
Assumption 1: The Quantitative Variables Are Multivariately Normally Distributed For Each Of The Populations, With The Different Populations Being Defined By The Levels Of The Grouping Variable
Assumption 2: The Population Variances And Covariances Among The Dependent Variables Are The Same Across All Levels Of The Factor
Assumption 3: The Participants Are Randomly Sampled, And The Score On A Variable For Any One Participant Is Independent From The Scores On This Variable For All Other Participants
Effect Size Statistics for Discriminant Analysis
The Data Set
The Research Question
Conducting a Discriminant Analysis
Selected SPSS Output for Preliminary Statistics of Discriminant Analysis
Selected SPSS Output for Significance Tests and Strength-of-Relationship Statistics
Selected SPSS Output of Coefficients for the Discriminant Functions
Selected SPSS Output for Group Centroids
Selected SPSS Output for Group Classification
Computing Kappa to Assess Classification Accuracy
Selected SPSS Output for Kappa
Using SPSS Graphs to Display the Results
An Apa Results Section
Alternative Analyses
Exercises
UNIT 9. Scaling Procedures
Lesson 36. Factor Analysis
Applications of Factor Analysis
Defining Indicators of Constructs
Defining Dimensions for an Existing Measure
Selecting Items or Scales to Be Included in a Measure
Understanding Factor Analysis
Assumptions Underlying Factor Analysis
Assumption 1: The Measured Variables Are Linearly Related To The Factors Plus Errors
Assumption 2: The X^2 Test For The Maximum Likelihood Solution Assumes That The Measured Variables Are Multivariately Normally Distributed
The Data Set
The Research Question
Conducting Factor Analysis
Conducting Factor Extraction
Selected SPSS Output for the Initial Factor Extraction
Conducting Factor Rotation
Selected SPSS Output for Rotated Factors
Factor Analysis of a Correlation Matrix
Creating Correlation Matrices As Data
Conducting Factor Analysis Of A Correlation Matrix
An Apa Results Section
Alternative Analyses
Exercises
Lesson 37. Internal Consistency Estimates of Reliability
Applications of Internal Consistency Estimates of Reliability
No Transformation of Items
Reverse-Scoring of Some Items
z -Score Transformations of Item Scores
Understanding Internal Consistency Estimates of Reliability
Assumptions Underlying Internal Consistency Reliability Procedures
Assumption 1: The Parts Of The Measure Must Be Equivalent
Assumption 2: Errors In Measurement Between Parts Are Unrelated
Assumption 3: An Item Or Half Test Score Is A Sum Of Its True And Its Error Scores
The Data Set
The Research Question
Conducting a Reliability Analysis
Computing Coefficient Alpha
Selected SPSS Output for Coefficient Alpha
Computing Split-Half Coefficient Estimates
Selected SPSS Output for Split-Half Reliability
Using SPSS Graphs to Display the Results
An Apa Results Section
Exercises
Lesson 38. Item Analysis Using the Reliability Procedure
Applications of Item Analysis
Measure of a Single Construct Requiring No Transformations
Measure of a Single Construct Requiring Reverse-Scoring of Some Item Scores
Measure of a Single Construct Requiring z Transformations of All Item Scores and Reverse-Scoring of Some Items
Measures of Multiple Constructs
Understanding Item Analysis
Assumption Underlying Item Analyses
Assumption 1: Items Are Linearly Related To A Single Factor Plus Random Measurement Error
The Data Set
The Research Question
Conducting Item Analyses
Conducting Item Analysis of a Measure of a Single Construct
Selected SPSS Output for Item Analysis of a Measure of a Single Construct
Conducting Item Analysis of a Measure of Multiple Constructs
Stage 1: Corrected ItemβTotal Correlations For The Emotion-focused Coping Items
Stage 2: Corrected ItemβTotal Correlations For The Problem-focused Coping Items
Stage 3: Computing Correlations Between The Emotion-focused Coping Items And The Problem-focused Coping Scale
Stage 4: Computing Correlations Between The Problem-focused Coping Items And The Emotion-focused Coping Scale
Selected SPSS Output for Item Analysis of a Measure of Multiple Constructs
Using SPSS Graphs to Display the Results
Two Apa Results Sections
Results for a Single Construct
Results for Multiple Constructs
Alternative Analyses
Exercises
UNIT 10. Nonparametric Procedures
Lesson 39. Binomial Test
Applications of the Binomial Test
Binomial Test with Equal Proportions
Binomial Test with Unequal Proportions
Understanding the Binomial Test
Assumption Underlying the Binomial Test
Assumption 1: The Observations Must Be From A Random Sample, And The Data For These Observations Are Independent Of Each Other
Effect Size Statistics For The Binomial Test
The Data Set
The Research Question
Conducting a Binomial Test
Selected SPSS Output for the Binomial Test
Using SPSS Graphs to Display the Results
An Apa Results Section
Alternative Analyses
Exercises
Lesson 40. One-Sample Chi-Square Test
Applications of the One-Sample Chi-Square Test
Testing a Hypothesis with Equal Proportions
Testing a Hypothesis with Unequal Proportions
Understanding the One-Sample Chi-Square Test
Assumptions Underlying the One-Sample Chi-Square Test
Assumption 1: The Observations Must Be From A Random Sample, And The Scores Associated With The Observation Are Independent Of Each Other
Assumption 2: The One-sample Chi-Square Test Yields A Test Statistic That Is Approximately Distributed As A Chi-Square When The Sample Size Is Relatively Large
Effect Size Statistics for a One-Sample Chi-Square Test
The Data Set
The Research Question
Conducting a One-Sample Chi-Square Test
Conducting the Overall Chi-Square Test
Selected SPSS Output for One-Sample Chi-Square Test
Conducting Follow-up Tests with Equal Expected Frequencies
Selected SPSS Output for Follow-up Test with Equal Expected Frequencies
Conducting Follow-up Tests with Unequal Expected Frequencies
Selected SPSS Output for Follow-up Test with Unequal Expected Frequencies
Using SPSS Graphs to Display the Results
An Apa Results Section
Alternative Analyses
Conducting a Kolmogrov-Smirnov Test
Exercises
Lesson 41. Two-Way Contingency Table Analysis Using Crosstabs
Applications of a Two-Way Contingency Table Analysis
Independence between Variables
Homogeneity of Proportions
Understanding a Two-Way Contingency Table Analysis
Assumptions Underlying a Two-Way Contingency Table Analysis
Assumption 1: The Observations For A Two-way Contingency Table Analysis Are Independent Of Each Other
Assumption 2: Two-way Contingency Table Analyses Yield A Test Statistic That Is Approximately Distributed As A Chi-Square When The Sample Size Is Relatively Large
Effect Size Statistics for a Two-Way Contingency Table Analysis
The Data Set
The Research Question
Conducting a Two-Way Contingency Table Analysis
Conducting the Overall Two-Way Contingency Table Analysis
Selected SPSS Output for Crosstabs
Conducting Follow-up Tests
Selected SPSS Output of Follow-up Tests
Using SPSS Graphs to Display the Results
An Apa Results Section
Exercises
Lesson 42. Two Independent-Samples Test: The Mann-Whitney U Test
Applications of the Mann-Whitney U Test
Quasi-Experimental Study
Understanding the Mann-Whitney U Test
Assumptions Underlying a Mann-Whitney U Test
Assumption 1: The Continuous Distributions For The Test Variable Are Exactly The Same (Except Their Medians) For The Two Populations
Assumption 2: The Cases Represent Random Samples From The Two Populations, And The Scores On The Test Variable Are Independent Of Each Other
Assumption 3: The Z-approximation Test For The Mann-whitney U Test Requires A Large Sample Size
Effect Size Statistics for the Mann-Whitney U Test
The Data Set
The Research Question
Conducting a Mann-Whitney U Test
Selected SPSS Output for the Mann-Whitney U Test
Using SPSS Graphs to Display the Results
An APA Results Section
Alternative Analyses
Exercises
Lesson 43. K Independent-Samples Tests: The Kruskal-Wallis and the Median Tests
Applications of the Kruskal-Wallis and the Median Tests
Experimental Study
Understanding the Kruskal-Wallis and Median Test
Assumptions Underlying the Median Test
Assumptions Underlying the Kruskal-Wallis Test
Assumption 1: The Continuous Distributions For The Test Variable Are Exactly The Same For The Different Populations
Assumption 2: The Cases Represent Random Samples From The Populations, And The Scores On The Test Variable Are Independent Of Each Other
Assumption 3: The Chi-square Statistic For This Test Is Only Approximate And Becomes More Accurate With Larger Sample Sizes
Effect Size Statistics for the Median Test and the Kruskal-Wallis Test
The Data Set
The Research Question
Conducting a K Independent-Samples Test
Conducting a Median Test
Conducting The Overall Median Test
Selected SPSS Output for the Median Test
Computing Pairwise Comparisons After A Significant Median Test
Selected SPSS Output for Pairwise Comparisons
Conducting a Kruskal-Wallis Test
Conducting The Overall Kruskal-Wallis Test
Selected SPSS Output for the Kruskal-Wallis Test
Conducting Pairwise Comparisons after Obtaining a Significant Kruskal-Wallis Test
Selected SPSS Output for Pairwise Comparisons
Using SPSS Graphs to Display the Results
Two Apa Results Sections
Results for the Median Test
Results for the Kruskal-Wallis Test
Alternative Analyses
Exercises
Lesson 44. Two Related-Samples Tests: The McNemar, the Sign, and the Wilcoxon Tests
Applications of the Mcnemar, Sign, and Wilcoxon Tests
Repeated-Measures Designs with an Intervention
Repeated-Measures Designs with No Intervention
Matched-Subjects Designs with an Intervention
Matched-Subjects Designs with No Intervention
Understanding the Mcnemar, Sign, and Wilcoxon Tests
Assumptions Underlying the McNemar, Sign, and Wilcoxon Tests
Assumption 1: Each Pair Of Observations Must Represent A Random Sample From A Population And Must Be Independent Of Every Other Pair Of Observations
Assumption 2: The Z Tests For The Three Tests Yield Relatively Accurate Results To The Extent That The Sample Size Is Large
Assumption 3 (Wilcoxon Test Only): The Distribution Of The Difference Scores Is Continuous And Symmetrical In The Population
Effect Size Statistics for the McNemar, Sign, and Wilcoxon Tests
The Data Set
The Research Question
Conducting Tests for Two Related Samples
Conducting a McNemar Test
Selected SPSS Output for the McNemar Test
Conducting a Sign Test
Selected SPSS Output for the Sign Test
Conducting a Wilcoxon Test
Selected SPSS Output for the Wilcoxon Test
Using SPSS Graphs to Display Results
Three Apa Results Sections
Results for McNemar Test
Results for Sign Test
Results for Wilcoxon Test
Alternative Analyses
Exercises
Lesson 45. K Related-Samples Tests: The Friedman and the Cochran Tests
Applications of the Cochran and Friedman Tests
Repeated-Measures Designs
Matched-Subjects Designs
Understanding the Cochran and Friedman Tests
Assumptions Underlying the Cochran and Friedman Tests
Assumption 1: Each Set Of K Observations Represent A Random Sample From A Population And Must Be Independent Of Every Other Set Of K Observations
Assumption 2: The Chi-Square Values For The Cochran And Friedman Tests Yield Relatively Accurate Results To The Extent That The Sample Size Is Large
Assumption 3 (Friedman Test Only): The Distribution Of The Differences Scores Between Any Pair Of Levels Is Continuous And Symmetrical In The Population
Effect Size Statistics for the Friedman and the Cochran Tests
The Data Set
The Research Question
Conducting K Related-Samples Tests
Conducting a Cochran Test
Conducting An Overall Cochran Test
Selected SPSS Output for the Cochran Test
Conducting Follow-up Tests to a Cochran Test by Using the McNemar Test
Selected SPSS Output for the McNemar Follow-up Tests
Conducting the Friedman Test
Conducting The Overall Friedman Test
Selected SPSS Output for the Friedman Test
Conducting Follow-up Tests by Using the Wilcoxon Test
Selected SPSS Output for the Wilcoxon Follow-up Tests
Using SPSS Graphs to Display Results
Two Apa Results Sections
Results for Cochran Test
Results for Friedman Test
Exercises
Appendices
Appendix A: Data for Crab Scale and Teacher Scale
Appendix B: Methods for Controlling Type I Error across Multiple Hypothesis Tests
Appendix C: Selected Answers to Lesson Exercises
References
Index