help requested: RI-CLPM doesn't run!
Hi,
For my master's thesis im trying to perform a RI-CLPM analysis (3waves, 2 variables(observed). For some reason I keep getting error messages when I try to run my syntax in JASP (0.19.1). I checked at the statistics department of my university and there it was said the syntax is correct. (When I perform a classic CLPM with these variables everything works fine; but would rather go with the RI). My question: what is going wrong? Is my syntax indeed correct and could it be a bug in JASP? Can someone help me out? :
This is my syntax:
RIx =~ 1*PSMU_T1 + 1*PSMU_T2 + 1*PSMU_T3
RIy =~ 1*PCJT_T1 + 1*PCJT_T2 + 1*PCJT_T3
wx1 =~ 1*PSMU_T1
wx2 =~ 1*PSMU_T2
wx3 =~ 1*PSMU_T3
wy1 =~ 1*PCJT_T1
wy2 =~ 1*PCJT_T2
wy3 =~ 1*PCJT_T3
wx2 + wy2 ~ wx1 + wy1
wx3 + wy3 ~ wx2 + wy2
wx1 ~~ wy1
wx2 ~~ wy2
wx3 ~~ wy3
RIx ~~ RIx
RIy ~~ RIy
RIx ~~ RIy
wx1 ~~ wx1
wy1 ~~ wy1
wx2 ~~ wx2
wy2 ~~ wy2
wx3 ~~ wx3
wy3 ~~ wy3
This is the error message I get:
This analysis terminated unexpectedly.
Error in if (nrow(originalSyntaxTable[originalSyntaxTable$op = ':=', : argument is of length zero
Stack trace
tryCatchOne(expr, names, parentenv, handlers[[1]])
doTryCatch(return(expr), name, parentenv, handler)
withCallingHandlers(expr = analysis(jaspResults = jaspResults, dataset = dataset, options = options), error = .addStackTrace)
analysis(jaspResults = jaspResults, dataset = dataset, options = options)
.semParameters(modelContainer, dataset, options, ready)
.semParameterTables(modelContainer[['results']][['object']][[1]], NULL, params, options, ready, modelContainer, dataset)
Hope someone can help me get back on track!
Thanks, Christianne
Comments
Hi Cristianne,
I've attended our expert to this. Because of the holidays it may take a while before you receive a response.
Cheers,
E.J.
Hi Cristianne,
at a first glance I cannot see anything wrong with your syntax. Could you share your data perhaps? Then I could be of more help. One thing you might try is the latest released version of JASP. In there, I have made some changes so errors are better reported.
Best,
Julius