The CALIS Procedure
-
Overview
-
Getting Started
-
SyntaxClasses of Statements in PROC CALISSingle-Group Analysis SyntaxMultiple-Group Multiple-Model Analysis SyntaxPROC CALIS StatementBOUNDS StatementBY StatementCOSAN StatementCOV StatementDETERM StatementEFFPART StatementFACTOR StatementFITINDEX StatementFREQ StatementGROUP StatementLINCON StatementLINEQS StatementLISMOD StatementLMTESTS StatementMATRIX StatementMEAN StatementMODEL StatementMSTRUCT StatementNLINCON StatementNLOPTIONS StatementOUTFILES StatementPARAMETERS StatementPARTIAL StatementPATH StatementPATHDIAGRAM StatementPCOV StatementPVAR StatementRAM StatementREFMODEL StatementRENAMEPARM StatementSAS Programming StatementsSIMTESTS StatementSTD StatementSTRUCTEQ StatementTESTFUNC StatementVAR StatementVARIANCE StatementVARNAMES StatementWEIGHT Statement
-
DetailsInput Data SetsOutput Data SetsDefault Analysis Type and Default ParameterizationThe COSAN ModelThe FACTOR ModelThe LINEQS ModelThe LISMOD Model and SubmodelsThe MSTRUCT ModelThe PATH ModelThe RAM ModelNaming Variables and ParametersSetting Constraints on ParametersAutomatic Variable SelectionPath Diagrams: Layout Algorithms, Default Settings, and CustomizationEstimation CriteriaRelationships among Estimation CriteriaGradient, Hessian, Information Matrix, and Approximate Standard ErrorsCounting the Degrees of FreedomAssessment of FitCase-Level Residuals, Outliers, Leverage Observations, and Residual DiagnosticsLatent Variable ScoresTotal, Direct, and Indirect EffectsStandardized SolutionsModification IndicesMissing Values and the Analysis of Missing PatternsMeasures of Multivariate KurtosisInitial EstimatesUse of Optimization TechniquesComputational ProblemsDisplayed OutputODS Table NamesODS Graphics
-
ExamplesEstimating Covariances and CorrelationsEstimating Covariances and Means SimultaneouslyTesting Uncorrelatedness of VariablesTesting Covariance PatternsTesting Some Standard Covariance Pattern HypothesesLinear Regression ModelMultivariate Regression ModelsMeasurement Error ModelsTesting Specific Measurement Error ModelsMeasurement Error Models with Multiple PredictorsMeasurement Error Models Specified As Linear EquationsConfirmatory Factor ModelsConfirmatory Factor Models: Some VariationsResidual Diagnostics and Robust EstimationThe Full Information Maximum Likelihood MethodComparing the ML and FIML EstimationPath Analysis: Stability of AlienationSimultaneous Equations with Mean Structures and Reciprocal PathsFitting Direct Covariance StructuresConfirmatory Factor Analysis: Cognitive AbilitiesTesting Equality of Two Covariance Matrices Using a Multiple-Group AnalysisTesting Equality of Covariance and Mean Matrices between Independent GroupsIllustrating Various General Modeling LanguagesTesting Competing Path Models for the Career Aspiration DataFitting a Latent Growth Curve ModelHigher-Order and Hierarchical Factor ModelsLinear Relations among Factor LoadingsMultiple-Group Model for Purchasing BehaviorFitting the RAM and EQS Models by the COSAN Modeling LanguageSecond-Order Confirmatory Factor AnalysisLinear Relations among Factor Loadings: COSAN Model SpecificationOrdinal Relations among Factor LoadingsLongitudinal Factor Analysis
- References
EFFPART Statement
-
EFFPART effect <, effect …>;
where effect represents:var-list < direction var-list2> and direction is the direction of the effect, as indicated by one of the following: ===>, --->, ==>, -->, =>, ->, >, <===, <---, <==, <--, <=, <-, or <.
In the EFFPART statement, you select those effects you want to analyze by partitioning the total effects into direct and indirect effects, with estimated standard errors. The EFFPART or TOTEFF option of the PROC CALIS statement also enables you to analyze effects. The difference is that the EFFPART or TOTEFF option displays effects on all endogenous variables, while the EFFPART statement shows only the effects of interest. In addition, the EFFPART statement enables you to arrange the effects in any way you like. Hence, the EFFPART statement offers a more precise and organized way to present various results of effects.
The EFFPART statement supports the following three types of effect specifications:
-
>,=>,->,==>,-->,===>, or--->directionExample:
effpart X1 X3-X5 ===> Y1 Y2;
This will display four separate tables, respectively for the effects of
X1,X3,X4, andX5onY1andY2. Each table contains the total, direct, and indirect effects of anX-variable on the twoY-variables. -
<,<=,<-,<==,<--,<===, or<---directionExample:
effpart Y1 Y2 <=== X1 X3-X5;
This will display two separate tables, respectively for the effects on
Y1andY2, byX1,X3,X4, andX5. Each table contains the total, direct, and indirect effects of the fourX-variables on aY-variable. Certainly, the results produced from this statement are essentially the same as the previous statement. The difference is about the organization of the effects in the tables. -
no direction
Example:
effpart Y1 Y2 X1-X3;
In this case, variables on the list are analyzed one by one to determine the nature of the effects. If a variable has nonzero effects on any other variables in the model, a table of the total, direct, and indirect effects of the variable on those variables is displayed. If a variable is endogenous, a table of total, direct, and indirect effects of those variables that have nonzero effects on the variable is displayed. Note that an endogenous variable in a model might also have effects on other endogenous variables. Therefore, the two cases mentioned are not mutually exclusive—a variable listed in the EFFPART statement might yield two tables for effect analysis.