Bayesian Estimation in AMOS Editor

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view
|

Bayesian Estimation in AMOS Editor

Jennie Day
Hi everyone -



Thanks for looking at my problem.  I am trying to use the Bayesian procedure
to estimate a system of equations in AMOS Editor.  This seems to be fairly
straightforward in AMOS Graphics, but I can't find the equivalent of an
"Sem." command in AMOS Editor.  My equations are far too complex to diagram.




The only command I've found in any of the resources I've looked at is
<PathDiagrammer.AnalyzeBayesianEstimation ()>

BUT this command does not work in my code.



Does anyone know how to use the Bayesian procedure in AMOS Editor?



Also, a higher-level question: I'm trying to estimate a system of equations
where two of the dependent variables are bivariate categorical (coded 1,0),
and one d.v. is continuous with a normal-ish distribution.  I THINK Bayesian
estimation is what I want to use here, but does anyone have any better
ideas?



Here's an outline of my code if that helps:





Module MainModule

    '

                Sub Main()

                                Dim FileName As String

                                Dim ModelAdmissible As Boolean,
ModelConverged As Boolean

                                Dim SaturatedAdmissible As Boolean,
SaturatedConverged As Boolean

                                Dim ModelCmin As Double, SaturatedCmin As
Double, P As Double

                                Dim ChiSquare As Double

                                Dim ModelNparms As Integer, SaturatedNparms
As Integer, Df As Integer



                                Dim Sem As New AmosEngine




                                Try

                                                Sem.title("Example 17:
Working Model")

                                                Sem.TextOutput()

                                                Sem.Standardized()

                                                Sem.Smc()

                                                Sem.AllImpliedMoments()


Sem.ModelMeansAndIntercepts()

                                                Sem.BeginGroup(FileName)




'PathDiagrammer.AnalyzeBayesianEstimation ()




Sem.AStructure("Delta_PcntHHInc_Housing = NoChoiceOR +
HHInc1_LessThanHalfMean + HHInc1_LessThanMean + . +  (1) error1")



Sem.AStructure("Delta_Tenure_Own = NoChoiceOR + HHInc1_LessThanHalfMean +
HHInc1_LessThanMean + HHInc1_LessThan1_5Mean  +. +   (1) error6")



Sem.AStructure("Delta_Tenure_Mortgage = NoChoiceOR + HHInc1_LessThanHalfMean
+ HHInc1_LessThanMean + HHInc1_LessThan1_5Mean  + .  +  (1) error7")





                                Finally

                                                Sem.Dispose()

                                End Try



                End Sub

End Module





Thanks!

Jennie D



Jennifer Day

Doctoral Candidate

Department of City and Regional Planning

University of California, Berkeley

415 613 4969 (mobile)

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD