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
RENAMEPARM Statement
-
RENAMEPARM assignment <, assignment …>;
where assignment represents: old_parameters = parameter-spec
You can use the RENAMEPARM statement to rename parameters or to change the types of parameters of a reference model so that new parameters are transferred to the new model in question. The RENAMEPARM statement is a subsidiary model specification statement that should be used together with the REFMODEL statement. The syntax of the RENAMEPARM statement is similar to that of the VARIANCE statement—except that in the RENAMEPARM statement, you put parameter names on the left-hand side of equal signs, whereas you put variable names on the left-hand side in the VARIANCE statement. You can use no more than one RENAMEPARM statement within the scope of each REFMODEL statement.
In the REFMODEL statement, you transfer all the model specification information from a base model to the new model being specified. The RENAMEPARM statement enables you to modify the parameter names or types in the base model before transferring them to the new model. For example, in the following example, you define Model 2, which is a new model, by referring it to Model 1, the base model, in the REFMODEL statement.
model 1;
lineqs
V1 = F1 + E1,
V2 = b2 F1 + E2,
V3 = b3 F1 + E3,
V4 = b4 F1 + E4;
variance F1 = vF1,
E1-E4 = ve1-ve4;
model 2;
refmodel 1;
renameparm ve1-ve4=new1-new4, b2=newb2(.2), b4=.3;
Basically, the LINEQS model specification in Model 1 is transferred to Model 2. In addition, you redefine some parameters in the base model by using the RENAMEPARM statement. This example illustrates two kinds of modifications that the RENAMEPARM statement can do:
-
creating new parameters in the new model
The error variances for
E1–E4in Model 2 are different from those defined in Model 1 because new parametersnew1–new4are now used. Parameterb2is renamed asnewb2with a starting value at 0.2 in Model 2. So the two models have distinct path coefficients for theF1-to-V2path. -
changing free parameters into fixed constants
By using the specification
b4=.3in the RENAMEPARM statement,b4is no longer a free parameter in Model 2. The path coefficient for theF1-to-V4path in Model 2 is now fixed at 0.3.
The RENAMEPARM statement is handy when you have just few parameters to change in the reference model defined by the REFMODEL statement. However, when there are a lot of parameters to modify, the RENAMEPARM statement might not be very efficient. For example, to make all parameters unique to the current model, you might consider using the ALLNEWPARMS , PARM_PREFIX= , or PARM_SUFFIX= option in the REFMODEL statement.