Haplo.glm error: Failed to converge during EM-glm loop

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

Haplo.glm error: Failed to converge during EM-glm loop

黄桦
Hi all,


I used R package "haplo.stats" to see if the haplotype in my data has any effect on the trait, with the genotype, age, height and

weight as the predictor and trait as the response. I used the following code:

 

fit.gaus <- haplo.glm(y ~ age + height + weight + geno.glm, family=gaussian, data=glm.data, na.action="na.geno.keep", x=TRUE, control=haplo.glm.control(haplo.freq.min=.02))

 

But R showed me this error:

 Warning message:

In haplo.glm(y ~ age + height + weight + geno.glm, family = gaussian,  :

  Failed to converge during EM-glm loop

 

What does it mean that failed to converge during EM-glm loop? I wonder if there is anything wrong with my command?

Thank you for your attention, I am looking forward to your reply.

 

Best.

 

Hua
        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
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.
Reply | Threaded
Open this post in threaded view
|

Re: Haplo.glm error: Failed to converge during EM-glm loop

Ravi Varadhan-2
It is a "warning" message, but not an "error" message.  Therefore, you should still get parameter estimates.  However, lack of convergence is often an important issue. Although in the case of the EM algorithm, it may not be so serious since EM is notoriously slow to converge when you set a small tolerance for convergence. You may fiddle with the control options for EM algorithm and see if you can get convergence.  If not, you should contact the package authors.

Hope this is helpful,
Ravi

Ravi Varadhan, Ph.D. (Biostatistics), Ph.D. (Environmental Engg)
Associate Professor,  Department of Oncology
Division of Biostatistics & Bionformatics
Sidney Kimmel Comprehensive Cancer Center
Johns Hopkins University
550 N. Broadway, Suite 1111-E
Baltimore, MD 21205
410-502-2619


        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
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.