Han Chen

> Hello Xihao, > > I've recently noticed via testing additional phenotypes that this seems very dependent on the case/control imbalance of the phenotype being studied. In a set of...

Hi Lucia, This error message often implies a convergence problem. Could you please turn on `verbose = TRUE` and let me know what you see? Thanks, Han

Hi William, The function `glmm.wald` is not recommended for large numbers of SNPs. It should only be used for look-ups. Please use `glmm.score` instead. Best, Han

Hi William, You can approximate the effect size estimate by SCORE/VAR and the standard error by 1/sqrt(VAR) from the score test. It usually works very well if the effect size...

Can you clarify your question? Were you referring to unordered and ordered factors? Did you want to use them as covariates, or the outcome?

If your outcome is not supported by the function `glm( )`, then it is not supported by GMMAT.

I would be happy to take a look if you could send me a reproducible example. Thanks, Han

Hi Yuan, Yes, generalized linear mixed models as implemented in GMMAT have been applied to family data. Best, Han

Hi Dylan, You mean the meta-analysis p-value increased (compared to the discovery cohort results), correct? I don't think this is surprising. If you do a Wald test on both cohorts...

Hi Yu, Thank you for your interest in GMMAT. Can you turn on verbose = TRUE and let me know what you see? Best, Han