[R] get rid of error in Factor Analysis

[Prof Brian Ripley]

?try

On Wed, 19 Jul 2006, Robert Mcfadden wrote:

> Dear All,
> 
> I wrote a program and there is a loop. At each iteration I use maximum
> likelihood factor analysis (?factanal). Output of factor analysis I use
> later (in this loop). Unfortunately from time to time I get an error message
> (I paste it below) and everything is stopped. Is it possible to write a
> condition that if error appears in factor analysis (FA), change input data
> for FA and do it again? Example
> 
>  
> 
> for (i in 1:1000){
> 
> FA<-factanal(data,factor=3)
> 
> If error appears change data to data2 and do factor analysis again
> 
> #rest of the program  
> 
> ............
> 
> ............
> 
> }
> 
>  
> 
> Best,
> 
> Robert 
> 
>     
> 
> Error in optim(start, FAfn, FAgr, method = "L-BFGS-B", lower = lower,  : 
> 
>         L-BFGS-B needs finite values of 'fn'
> 
> In addition: Warning message:
> 
> NaNs produced in: log(x)
> 
>  
> 
>  
> 
>  
> 
>  
> 
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
> 

-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595