[R] Sem error - subscript out of bounds

[John Fox]

Dear Leonard,

There are no error variances defined for the endogenous variables in the
model. Have you read the document that describes how sem() works (at
http://socserv.socsci.mcmaster.ca/jfox/Books/Companion/appendix-sems.pdf)?
If not, that might help you specify the model. It should also help to study
the examples in ?sem.

The soon-to-be-released next version of the sem package will print a more
informative error message for this kind of error.

I hope that this helps,
 John 

> -----Original Message-----
> From: r-help-bounces at stat.math.ethz.ch 
> [mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of Leonard assis
> Sent: Tuesday, May 11, 2004 7:12 PM
> To: r-help at stat.math.ethz.ch
> Subject: [R] Sem error - subscript out of bounds
> 
> 
> What´s happening with this following code:
> 
> require(sem)
> Celpe.Mod.RAM <- matrix(c(
>                        #  path                           
> parametro    Inicio
>                           "Produção    ->  T1",          
> "gamma.11",  NA,
>                           "Produção    ->  T2",          
> "gamma.12",  NA,
>                           "Produção    ->  T3",          
> "gamma.13",  NA,
>                           "Produção    ->  T4",          
> "gamma.14",  NA,
>                           "Compreensão ->  T1",          
> "gamma.21",  NA,
>                           "Compreensão ->  T2",          
> "gamma.22",  NA,
>                           "Compreensão ->  PI",          
> "gamma.23",  NA,
>                           "Certificado ->  Produção",    
> "alpha.11",  NA,
>                           "Certificado ->  Compreensão", 
> "alpha.12",  NA,
>                           "Compreensão <-> Produção",    
> "alpha.21",  NA
>                           ),
>                         ncol=3, byrow=TRUE)
> 
> Celpe.cov <- cov(Celpe.Dados.Fatorial[3:7]) Celpe.cfa.sem <- 
> sem(ram=Celpe.Mod.RAM, S=Celpe.cov,
> N=1443,refit=TRUE,debug=TRUE)
> 
> Here comes the Results:
> 
> > Celpe.cfa.sem <- sem(ram=Celpe.Mod.RAM, S=Celpe.cov,
> N=1443,refit=TRUE,debug=TRUE)
> 
>  observed variables:
> [1] "1:T1" "2:T2" "3:T3" "4:T4" "5:PI"
> 
> 
>  latent variables:
> [1] "6:Produção"    "7:Compreensão" "8:Certificado"
> 
> 
>  parameters:
>  [1] "1:gamma.11"  "2:gamma.12"  "3:gamma.13"  "4:gamma.14"  
> "5:gamma.21"
> "6:gamma.22"  "7:gamma.23"  "8:alpha.11"  "9:alpha.12" 
> [10] "10:alpha.21"
> 
> 
>  RAM:
>       heads to from parameter start
>  [1,]     1  1    6         1    NA
>  [2,]     1  2    6         2    NA
>  [3,]     1  3    6         3    NA
>  [4,]     1  4    6         4    NA
>  [5,]     1  1    7         5    NA
>  [6,]     1  2    7         6    NA
>  [7,]     1  5    7         7    NA
>  [8,]     1  6    8         8    NA
>  [9,]     1  7    8         9    NA
> [10,]     2  6    7        10    NA
> Error in startvalues(S, ram, debug = debug, tol = start.tol) : 
>         subscript out of bounds
> > Celpe.cov
>           T1        T2        T3        T4        PI
> T1 1.2459212 0.6072653 0.6410553 0.4030267 0.7001731
> T2 0.6072653 0.9369251 0.5762526 0.3293337 0.6282211
> T3 0.6410553 0.5762526 1.5346904 0.3888291 0.6064140
> T4 0.4030267 0.3293337 0.3888291 0.5377340 0.3840199 PI 
> 0.7001731 0.6282211 0.6064140 0.3840199 1.9750506
> > version
>          _              
> platform i386-pc-mingw32
> arch     i386           
> os       mingw32        
> system   i386, mingw32  
> status   Patched        
> major    1              
> minor    9.0            
> year     2004           
> month    04             
> day      28             
> language R              
> > 
> 
> []s
> Leonard Assis
> Estatístico /  CONFE 7439
> UIN : 41-764-523 /  Skype : lmassis /  msn : lmassis at msn.com
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://www.stat.math.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! 
> http://www.R-project.org/posting-guide.html