Ibm Laptop Spss Amos 21 Users Manual User’s Guide

2015-02-02

• IBM® SPSS® Amos™ 21 User’s Guide
  • Contents
    • Part I: Getting Started
    • 1 Introduction 1
    • 2 Tutorial: Getting Started with Amos Graphics 7
    • Part II: Examples
    • 1 Estimating Variances and Covariances 23
    • 2 Testing Hypotheses 41
    • 3 More Hypothesis Testing 59
    • 4 Conventional Linear Regression 67
    • 5 Unobserved Variables 81
    • 6 Exploratory Analysis 101
    • 7 A Nonrecursive Model 129
    • 8 Factor Analysis 137
    • 9 An Alternative to Analysis of Covariance 145
    • 10 Simultaneous Analysis of Several Groups 159
    • 11 Felson and Bohrnstedt’s Girls and Boys 175
    • 12 Simultaneous Factor Analysis for Several Groups 195
    • 13 Estimating and Testing Hypotheses about Means 209
    • 14 Regression with an Explicit Intercept 221
    • 15 Factor Analysis with Structured Means 229
    • 16 Sörbom’s Alternative to Analysis of Covariance 241
    • 17 Missing Data 269
    • 18 More about Missing Data 283
    • 19 Bootstrapping 295
    • 20 Bootstrapping for Model Comparison 303
    • 21 Bootstrapping to Compare Estimation Methods 311
    • 22 Specification Search 319
    • 23 Exploratory Factor Analysis by Specification Search 349
    • 24 Multiple-Group Factor Analysis 363
    • 25 Multiple-Group Analysis 377
    • 26 Bayesian Estimation 385
    • 27 Bayesian Estimation Using a Non-Diffuse Prior Distribution 409
    • 28 Bayesian Estimation of Values Other Than Model Parameters 423
    • 29 Estimating a User-Defined Quantity in Bayesian SEM 437
    • 30 Data Imputation 461
    • 31 Analyzing Multiply Imputed Datasets 469
    • 32 Censored Data 475
    • 33 Ordered-Categorical Data 489
    • 34 Mixture Modeling with Training Data 521
    • 35 Mixture Modeling without Training Data 539
    • 36 Mixture Regression Modeling 557
    • 37 Using Amos Graphics without Drawing a Path Diagram 577
    • Part III: Appendices
    • A Notation 591
    • B Discrepancy Functions 593
    • C Measures of Fit 597
    • D Numeric Diagnosis of Non-Identifiability 619
    • E Using Fit Measures to Rank Models 621
    • F Baseline Models for Descriptive Fit Measures 625
    • G Rescaling of AIC, BCC, and BIC 627
    • Notices 631
    • Bibliography 635
    • Index 647
      • Chapter
  • 1 Introduction
    • Featured Methods
    • About the Tutorial
    • About the Examples
    • About the Documentation
    • Other Sources of Information
    • Acknowledgements
      • Chapter
  • 2 Tutorial: Getting Started with Amos Graphics
    • Introduction
    • About the Data
    • Launching Amos Graphics
    • Creating a New Model
    • Specifying the Data File
    • Specifying the Model and Drawing Variables
    • Naming the Variables
    • Drawing Arrows
    • Constraining a Parameter
    • Altering the Appearance of a Path Diagram
      • To Move an Object
      • To Reshape an Object or Double-Headed Arrow
      • To Delete an Object
      • To Undo an Action
      • To Redo an Action
    • Setting Up Optional Output
    • Performing the Analysis
    • Viewing Output
      • To View Text Output
      • To View Graphics Output
    • Printing the Path Diagram
    • Copying the Path Diagram
    • Copying Text Output
      • Example
  • 1 Estimating Variances and Covariances
    • Introduction
    • About the Data
    • Bringing In the Data
    • Analyzing the Data
      • Specifying the Model
      • Naming the Variables
      • Changing the Font
      • Establishing Covariances
      • Performing the Analysis
    • Viewing Graphics Output
    • Viewing Text Output
    • Optional Output
      • Calculating Standardized Estimates
      • Rerunning the Analysis
      • Viewing Correlation Estimates as Text Output
    • Distribution Assumptions for Amos Models
    • Modeling in VB.NET
      • Generating Additional Output
    • Modeling in C#
    • Other Program Development Tools
      • Example
  • 2 Testing Hypotheses
    • Introduction
    • About the Data
    • Parameters Constraints
      • Constraining Variances
      • Specifying Equal Parameters
        • Benefits of Specifying Equal Parameters
      • Constraining Covariances
    • Moving and Formatting Objects
    • Data Input
      • Performing the Analysis
      • Viewing Text Output
    • Optional Output
      • Covariance Matrix Estimates
      • Displaying Covariance and Variance Estimates on the Path Diagram
    • Labeling Output
    • Hypothesis Testing
    • Displaying Chi-Square Statistics on the Path Diagram
    • Modeling in VB.NET
      • Timing Is Everything
      • Example
  • 3 More Hypothesis Testing
    • Introduction
    • About the Data
    • Bringing In the Data
    • Testing a Hypothesis That Two Variables Are Uncorrelated
    • Specifying the Model
    • Viewing Text Output
    • Viewing Graphics Output
    • Modeling in VB.NET
      • Example
  • 4 Conventional Linear Regression
    • Introduction
    • About the Data
    • Analysis of the Data
    • Specifying the Model
    • Identification
    • Fixing Regression Weights
    • Viewing the Text Output
    • Viewing Graphics Output
    • Viewing Additional Text Output
    • Modeling in VB.NET
      • Assumptions about Correlations among Exogenous Variables
      • Equation Format for the AStructure Method
      • Example
  • 5 Unobserved Variables
    • Introduction
    • About the Data
    • Model A
    • Measurement Model
    • Structural Model
    • Identification
    • Specifying the Model
      • Changing the Orientation of the Drawing Area
      • Creating the Path Diagram
      • Rotating Indicators
      • Duplicating Measurement Models
      • Entering Variable Names
      • Completing the Structural Model
    • Results for Model A
      • Viewing the Graphics Output
    • Model B
    • Results for Model B
    • Testing Model B against Model A
    • Modeling in VB.NET
      • Model A
      • Model B
      • Example
  • 6 Exploratory Analysis
    • Introduction
    • About the Data
    • Model A for the Wheaton Data
      • Specifying the Model
      • Identification
      • Results of the Analysis
      • Dealing with Rejection
      • Modification Indices
        • Using Modification Indices
        • Changing the Modification Index Threshold
    • Model B for the Wheaton Data
      • Text Output
      • Graphics Output for Model B
      • Misuse of Modification Indices
      • Improving a Model by Adding New Constraints
        • Calculating Critical Ratios
    • Model C for the Wheaton Data
      • Results for Model C
      • Testing Model C
      • Parameter Estimates for Model C
    • Multiple Models in a Single Analysis
    • Output from Multiple Models
      • Viewing Graphics Output for Individual Models
      • Viewing Fit Statistics for All Four Models
      • Obtaining Optional Output
      • Obtaining Tables of Indirect, Direct, and Total Effects
    • Modeling in VB.NET
      • Model A
      • Model B
      • Model C
      • Fitting Multiple Models
      • Example
  • 7 A Nonrecursive Model
    • Introduction
    • About the Data
    • Felson and Bohrnstedt’s Model
    • Model Identification
    • Results of the Analysis
      • Text Output
      • Obtaining Standardized Estimates
      • Obtaining Squared Multiple Correlations
      • Graphics Output
      • Stability Index
    • Modeling in VB.NET
      • Example
  • 8 Factor Analysis
    • Introduction
    • About the Data
    • A Common Factor Model
    • Identification
    • Specifying the Model
      • Drawing the Model
    • Results of the Analysis
      • Obtaining Standardized Estimates
      • Viewing Standardized Estimates
    • Modeling in VB.NET
      • Example
  • 9 An Alternative to Analysis of Covariance
    • Introduction
    • Analysis of Covariance and Its Alternative
    • About the Data
    • Analysis of Covariance
    • Model A for the Olsson Data
    • Identification
    • Specifying Model A
    • Results for Model A
    • Searching for a Better Model
      • Requesting Modification Indices
    • Model B for the Olsson Data
    • Results for Model B
    • Model C for the Olsson Data
      • Drawing a Path Diagram for Model C
    • Results for Model C
    • Fitting All Models At Once
    • Modeling in VB.NET
      • Model A
      • Model B
      • Model C
      • Fitting Multiple Models
      • Example
  • 10 Simultaneous Analysis of Several Groups
    • Introduction
    • Analysis of Several Groups
    • About the Data
    • Model A
      • Conventions for Specifying Group Differences
      • Specifying Model A
      • Text Output
      • Graphics Output
    • Model B
      • Text Output
      • Graphics Output
    • Modeling in VB.NET
      • Model A
      • Model B
      • Multiple Model Input
      • Example
  • 11 Felson and Bohrnstedt’s Girls and Boys
    • Introduction
    • Felson and Bohrnstedt’s Model
    • About the Data
    • Specifying Model A for Girls and Boys
      • Specifying a Figure Caption
    • Text Output for Model A
    • Graphics Output for Model A
      • Obtaining Critical Ratios for Parameter Differences
    • Model B for Girls and Boys
    • Results for Model B
      • Text Output
      • Graphics Output
    • Fitting Models A and B in a Single Analysis
    • Model C for Girls and Boys
    • Results for Model C
    • Modeling in VB.NET
      • Model A
      • Model B
      • Model C
      • Fitting Multiple Models
      • Example
  • 12 Simultaneous Factor Analysis for Several Groups
    • Introduction
    • About the Data
    • Model A for the Holzinger and Swineford Boys and Girls
      • Naming the Groups
      • Specifying the Data
    • Results for Model A
      • Text Output
      • Graphics Output
    • Model B for the Holzinger and Swineford Boys and Girls
    • Results for Model B
      • Text Output
      • Graphics Output
    • Modeling in VB.NET
      • Model A
      • Model B
      • Example
  • 13 Estimating and Testing Hypotheses about Means
    • Introduction
    • Means and Intercept Modeling
    • About the Data
    • Model A for Young and Old Subjects
    • Mean Structure Modeling in Amos Graphics
    • Results for Model A
      • Text Output
      • Graphics Output
    • Model B for Young and Old Subjects
    • Results for Model B
    • Comparison of Model B with Model A
    • Multiple Model Input
    • Mean Structure Modeling in VB.NET
      • Model A
      • Model B
      • Fitting Multiple Models
      • Example
  • 14 Regression with an Explicit Intercept
    • Introduction
    • Assumptions Made by Amos
    • About the Data
    • Specifying the Model
    • Results of the Analysis
      • Text Output
      • Graphics Output
    • Modeling in VB.NET
      • Example
  • 15 Factor Analysis with Structured Means
    • Introduction
    • Factor Means
    • About the Data
    • Model A for Boys and Girls
      • Specifying the Model
    • Understanding the Cross-Group Constraints
    • Results for Model A
      • Text Output
      • Graphics Output
    • Model B for Boys and Girls
    • Results for Model B
    • Comparing Models A and B
    • Modeling in VB.NET
      • Model A
      • Model B
      • Fitting Multiple Models
      • Example
  • 16 Sörbom’s Alternative to Analysis of Covariance
    • Introduction
    • Assumptions
    • About the Data
    • Changing the Default Behavior
    • Model A
      • Specifying the Model
    • Results for Model A
      • Text Output
    • Model B
    • Results for Model B
    • Model C
    • Results for Model C
    • Model D
    • Results for Model D
    • Model E
    • Results for Model E
    • Fitting Models A Through E in a Single Analysis
    • Comparison of Sörbom’s Method with the Method of Example 9
    • Model X
    • Modeling in Amos Graphics
    • Results for Model X
    • Model Y
    • Results for Model Y
    • Model Z
    • Results for Model Z
    • Modeling in VB.NET
      • Model A
      • Model B
      • Model C
      • Model D
      • Model E
      • Fitting Multiple Models
      • Models X, Y, and Z
      • Example
  • 17 Missing Data
    • Introduction
    • Incomplete Data
    • About the Data
    • Specifying the Model
    • Saturated and Independence Models
    • Results of the Analysis
      • Text Output
      • Graphics Output
    • Modeling in VB.NET
      • Fitting the Factor Model (Model A)
      • Fitting the Saturated Model (Model B)
      • Computing the Likelihood Ratio Chi-Square Statistic and P
      • Performing All Steps with One Program
      • Example
  • 18 More about Missing Data
    • Introduction
    • Missing Data
    • About the Data
    • Model A
    • Results for Model A
      • Graphics Output
      • Text Output
    • Model B
    • Output from Models A and B
    • Modeling in VB.NET
      • Model A
      • Model B
      • Example
  • 19 Bootstrapping
    • Introduction
    • The Bootstrap Method
    • About the Data
    • A Factor Analysis Model
    • Monitoring the Progress of the Bootstrap
    • Results of the Analysis
    • Modeling in VB.NET
      • Example
  • 20 Bootstrapping for Model Comparison
    • Introduction
    • Bootstrap Approach to Model Comparison
    • About the Data
    • Five Models
      • Text Output
    • Summary
    • Modeling in VB.NET
      • Example
  • 21 Bootstrapping to Compare Estimation Methods
    • Introduction
    • Estimation Methods
    • About the Data
    • About the Model
      • Text Output
    • Modeling in VB.NET
      • Example
  • 22 Specification Search
    • Introduction
    • About the Data
    • About the Model
      • Figure 22-1: Felson and Bohrnstedt’s model for girls
    • Specification Search with Few Optional Arrows
      • Specifying the Model
      • Selecting Program Options
      • Performing the Specification Search
      • Viewing Generated Models
        • Figure 22-2: Path diagram for Model 7
      • Viewing Parameter Estimates for a Model
        • Figure 22-3: Parameter estimates for Model 7
      • Using BCC to Compare Models
      • Viewing the Akaike Weights
      • Using BIC to Compare Models
      • Using Bayes Factors to Compare Models
      • Rescaling the Bayes Factors
      • Examining the Short List of Models
        • Figure 22-4: The best model for each number of parameters
      • Viewing a Scatterplot of Fit and Complexity
      • Adjusting the Line Representing Constant Fit
      • Viewing the Line Representing Constant C - df
      • Adjusting the Line Representing Constant C - df
      • Viewing Other Lines Representing Constant Fit
      • Viewing the Best-Fit Graph for C
        • Figure 22-5: Smallest value of C for each number of parameters
      • Viewing the Best-Fit Graph for Other Fit Measures
      • Viewing the Scree Plot for C
        • Figure 22-6: Scree plot for C
      • Viewing the Scree Plot for Other Fit Measures
    • Specification Search with Many Optional Arrows
      • Figure 22-7: Highly exploratory model for Felson and Bohrnstedt’s girls’ data
      • Specifying the Model
      • Making Some Arrows Optional
      • Setting Options to Their Defaults
      • Performing the Specification Search
      • Using BIC to Compare Models
        • Figure 22-8: The 10 best models according to BIC0
      • Viewing the Scree Plot
    • Limitations
      • Example
  • 23 Exploratory Factor Analysis by Specification Search
    • Introduction
    • About the Data
    • About the Model
      • Figure 23-1: Exploratory factor analysis model with two factors
    • Specifying the Model
    • Opening the Specification Search Window
    • Making All Regression Weights Optional
      • Figure 23-2: Two-factor model with all regression weights optional
    • Setting Options to Their Defaults
    • Performing the Specification Search
    • Using BCC to Compare Models
      • Figure 23-3: The 10 best models according to BCC0
      • Figure 23-4: Reversing F1 and F2 yields another candidate model
      • Figure 23-5: Reversing F1 and F2 yields the same candidate model
      • Figure 23-6: Model 63
    • Viewing the Scree Plot
    • Viewing the Short List of Models
    • Heuristic Specification Search
    • Performing a Stepwise Search
      • Figure 23-7: Results of stepwise specification search
    • Viewing the Scree Plot
      • Figure 23-8: Scree plot after stepwise specification search
    • Limitations of Heuristic Specification Searches
      • Example
  • 24 Multiple-Group Factor Analysis
    • Introduction
    • About the Data
    • Model 24a: Modeling Without Means and Intercepts
      • Figure 24-1: Two-factor model for girls and boys
      • Specifying the Model
      • Opening the Multiple-Group Analysis Dialog Box
        • Figure 24-2: The Multiple-Group Analysis dialog box
      • Viewing the Parameter Subsets
      • Viewing the Generated Models
        • Figure 24-3: Amos Graphics window after automatic constraints
      • Fitting All the Models and Viewing the Output
    • Customizing the Analysis
    • Model 24b: Comparing Factor Means
      • Specifying the Model
        • Figure 24-4: Two-factor model with explicit means and intercepts
      • Removing Constraints
      • Generating the Cross-Group Constraints
      • Fitting the Models
      • Viewing the Output
      • Example
  • 25 Multiple-Group Analysis
    • Introduction
    • About the Data
    • About the Model
      • Figure 25-1: Sörbom model for Olsson data
    • Specifying the Model
    • Constraining the Latent Variable Means and Intercepts
    • Generating Cross-Group Constraints
    • Fitting the Models
    • Viewing the Text Output
    • Examining the Modification Indices
      • Modifying the Model and Repeating the Analysis
      • Example
  • 26 Bayesian Estimation
    • Introduction
    • Bayesian Estimation
      • Selecting Priors
      • Performing Bayesian Estimation Using Amos Graphics
      • Estimating the Covariance
    • Results of Maximum Likelihood Analysis
    • Bayesian Analysis
    • Replicating Bayesian Analysis and Data Imputation Results
      • Examining the Current Seed
      • Changing the Current Seed
      • Changing the Refresh Options
    • Assessing Convergence
    • Diagnostic Plots
    • Bivariate Marginal Posterior Plots
    • Credible Intervals
      • Changing the Confidence Level
    • Learning More about Bayesian Estimation
      • Example
  • 27 Bayesian Estimation Using a Non-Diffuse Prior Distribution
    • Introduction
    • About the Example
    • More about Bayesian Estimation
    • Bayesian Analysis and Improper Solutions
    • About the Data
    • Fitting a Model by Maximum Likelihood
    • Bayesian Estimation with a Non-Informative (Diffuse) Prior
      • Changing the Number of Burn-In Observations
      • Example
  • 28 Bayesian Estimation of Values Other Than Model Parameters
    • Introduction
    • About the Example
    • The Wheaton Data Revisited
    • Indirect Effects
      • Estimating Indirect Effects
    • Bayesian Analysis of Model C
    • Additional Estimands
    • Inferences about Indirect Effects
      • Example
  • 29 Estimating a User-Defined Quantity in Bayesian SEM
    • Introduction
    • About the Example
    • The Stability of Alienation Model
    • Numeric Custom Estimands
      • Dragging and Dropping
    • Dichotomous Custom Estimands
      • Defining a Dichotomous Estimand
      • Example
  • 30 Data Imputation
    • Introduction
    • About the Example
    • Multiple Imputation
    • Model-Based Imputation
    • Performing Multiple Data Imputation Using Amos Graphics
      • Example
  • 31 Analyzing Multiply Imputed Datasets
    • Introduction
    • Analyzing the Imputed Data Files Using SPSS Statistics
    • Step 2: Ten Separate Analyses
    • Step 3: Combining Results of Multiply Imputed Data Files
    • Further Reading
      • Example
  • 32 Censored Data
    • Introduction
    • About the Data
      • Recoding the Data
      • Analyzing the Data
      • Performing a Regression Analysis
    • Posterior Predictive Distributions
    • Imputation
    • General Inequality Constraints on Data Values
      • Example
  • 33 Ordered-Categorical Data
    • Introduction
    • About the Data
      • Specifying the Data File
      • Recoding the Data within Amos
      • Specifying the Model
      • Fitting the Model
    • MCMC Diagnostics
    • Posterior Predictive Distributions
    • Posterior Predictive Distributions for Latent Variables
    • Imputation
      • Example
  • 34 Mixture Modeling with Training Data
    • Introduction
    • About the Data
    • Performing the Analysis
    • Specifying the Data File
    • Specifying the Model
    • Fitting the Model
    • Classifying Individual Cases
    • Latent Structure Analysis
      • Example
  • 35 Mixture Modeling without Training Data
    • Introduction
    • About the Data
    • Performing the Analysis
    • Specifying the Data File
    • Specifying the Model
      • Constraining the Parameters
    • Fitting the Model
    • Classifying Individual Cases
    • Latent Structure Analysis
    • Label Switching
      • Example
  • 36 Mixture Regression Modeling
    • Introduction
    • About the Data
      • First Dataset
      • Second Dataset
      • The Group Variable in the Dataset
    • Performing the Analysis
    • Specifying the Data File
    • Specifying the Model
    • Fitting the Model
    • Classifying Individual Cases
    • Improving Parameter Estimates
    • Prior Distribution of Group Proportions
    • Label Switching
      • Example
  • 37 Using Amos Graphics without Drawing a Path Diagram
    • Introduction
    • About the Data
    • A Common Factor Model
      • Creating a Plugin to Specify the Model
      • Controlling Undo Capability
      • Compiling and Saving the Plugin
      • Using the Plugin
    • Other Aspects of the Analysis in Addition to Model Specification
      • Defining Program Variables that Correspond to Model Variables
      • Appendix
  • A Notation
    • Appendix
  • B Discrepancy Functions
    • Appendix
  • C Measures of Fit
    • Measures of Parsimony
      • NPAR
      • DF
      • PRATIO
    • Minimum Sample Discrepancy Function
      • CMIN
      • P
      • CMIN/DF
        • Rules of Thumb
      • FMIN
    • Measures Based On the Population Discrepancy
      • NCP
      • F0
      • RMSEA
        • Rule of Thumb
      • PCLOSE
    • Information-Theoretic Measures
      • AIC
      • BCC
      • BIC
      • CAIC
      • ECVI
      • MECVI
    • Comparisons to a Baseline Model
      • NFI
        • Rule of Thumb
      • RFI
      • IFI
      • TLI
      • CFI
    • Parsimony Adjusted Measures
      • PNFI
      • PCFI
    • GFI and Related Measures
      • GFI
      • AGFI
      • PGFI
    • Miscellaneous Measures
      • HI 90
      • HOELTER
      • LO 90
      • RMR
    • Selected List of Fit Measures
      • Appendix
  • D Numeric Diagnosis of Non-Identifiability
    • Appendix
  • E Using Fit Measures to Rank Models
    • Appendix
  • F Baseline Models for Descriptive Fit Measures
    • Appendix
  • G Rescaling of AIC, BCC, and BIC
    • Zero-Based Rescaling
    • Akaike Weights and Bayes Factors (Sum = 1)
    • Akaike Weights and Bayes Factors (Max = 1)
  • Notices
    • Trademarks
  • Bibliography
  • Index