lmer model specification problem
-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Rajibul, Gamma GLMs are not currently working well with glmer. We hope to fix this soon, but in the meantime I would recommend trying a lognormal model (i.e., log-transform the data and then use lmer without a family= argument). You say that your responses are positive continuous, but the responses you show all happen to be integers. Is that something you want to take into account? Ben Bolker
On 11-04-11 06:20 PM, rajibul islam wrote:
Dear All: I am having a problem with the function...........lmer() The data looks like........... id time res-----------(responses are all positive continuous) 1 1 1 2 1 3 1 6 2 1 2 2 2 3 2 6 . . . . i used a gamma model like............with two types of link function......(inverse and log), I also tried identity............they also shows different types of problem............
m1.1.0g2<-lmer(response0g~time0g+(1|id0g),family=Gamma(link = "inverse"))
Error in mer_finalize(ans) : mu[i] must be positive: mu = -16, i = 37
m1.1.0g2<-lmer(response0g~time0g+(1|id0g),family=Gamma(link = "log")) m1.1.0g2
Error in asMethod(object) : matrix is not symmetric [1,2] Any kinds of helps (as well as idea) will be highly appreciable..........Thanks........... Regards..... Rajib..............http://rimian85.web.officelive.com/
R-sig-mixed-models at r-project.org mailing list
[[alternative HTML version deleted]]
_______________________________________________ R-sig-mixed-models at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
-----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.10 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iEYEARECAAYFAk2jmQcACgkQc5UpGjwzenPwLQCfSsoQ1mx4fbcazTEb8r+ygM2A vV0AoIZ4VHW8iE1Mk6ao4pO6sa+ASPlP =mdD8 -----END PGP SIGNATURE-----