[R] convergence error with heidel.diag

Uwe Ligges ligges at statistik.uni-dortmund.de
Thu Sep 13 10:47:37 CEST 2007


I fear most of us get:

R> heidel.diag(posterior, eps=0.1, pvalue=0.05)
Error: could not find function "heidel.diag"

Uwe Ligges



Anthony Pezzola wrote:
> I received the following error after running:
> 
> ####
>  > heidel.diag(posterior, eps=0.1, pvalue=0.05)
> Error in glm.fit(x = X, y = Y, weights = weights, start = start, 
> etastart = etastart,  :
> 	inner loop 1; cannot correct step size
> In addition: There were 21 warnings (use warnings() to see them)
>  > test.diag <- heidel.diag(posterior, eps=0.1, pvalue=0.05)
> Error in glm.fit(x = X, y = Y, weights = weights, start = start, 
> etastart = etastart,  :
> 	inner loop 1; cannot correct step size
> In addition: There were 21 warnings (use warnings() to see them)
>  > warnings()
> Warning messages:
> 1: algorithm did not converge in: glm.fit(x = X, y = Y, weights = 
> weights, start = start, etastart = etastart,   ...
> #####
> 
> posterior was generated using:
> 
> #####
>  > posterior <-MCMCirt1d(mydata, theta.fixed =1, burnin=35000, 
> mcmc=75000, thin=300)
> #####
> 
> Is a chain of 250 simply too short for heidel.diag to work with?  If so 
> how long should it be?
> 
> Thanks in advance,
> Anthony
>



More information about the R-help mailing list