Talk:Fixed effects estimation

The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.

Untitled

I plan to use the refs to expand the article soon, as well as th random effect model.--_{Piotr Konieczny aka Prokonsul Piotrus | talk} 18:30, 12 October 2006 (UTC)[reply]

Technical Tag

This article would be much clearer, in my opinion, if it told readers up front why they would want to use this type of model and provided example studies where it would be appropriate. Also, the focus on meta-analysis is confusing since multi-level modeling can be used for a variety of other problems as well. If meta-analysis is used to mean 'having a hierarchical groupings of samples' then this should be specified. (User:antonrojo, not signed in) 198.190.230.57 21:06, 23 January 2007 (UTC)[reply]

Consistancy Comment

The following ***statements*** are not consistent:

A random effects model makes the additional assumption that the individual effects are randomly distributed. It is thus ***not the opposite of a fixed effects model***, but a special case. If the random effects assumption holds, the random effects model is slightly more efficient than the fixed effects model. However, if this additional assumption does not hold, the random effects model is not consistent

[edit] Fixed effects hierarchical linear modeling This section is at odds with various texts on the subject and requires rigorous fact checking Fixed effect(s) model is a term often used in hierarchical linear modeling. ***It is an opposite of a random effects model.*** Fixed effect model assumes that the data come from normal populations which differ in their means.