willow1980
2010-Mar-25 12:52 UTC
[R] Do the missing values in random effect structure matter?
Hi, everyone, I met a problem with mixed effect model with lmer. Basically, I want to treat region and mother ID as a nested random effect structure with mother ID nested within a specific region. However, in my dataset, many subjects had no mother ID (about 25% of them). I want to know, if I use (1|region)+(1|region:motherID) as the random effect structure, will the statistical result be biased? Thank you very much for your help! Best regards, Jianghua -- View this message in context: http://n4.nabble.com/Do-the-missing-values-in-random-effect-structure-matter-tp1690569p1690569.html Sent from the R help mailing list archive at Nabble.com.