# lme X lmer results

5 messages
Open this post in threaded view
|

## lme X lmer results

Open this post in threaded view
|

## Re: lme X lmer results

Open this post in threaded view
|

## Re: lme X lmer results

 In reply to this post by John Maindonald Message: 18 Date: Fri, 30 Dec 2005 12:51:59 -0600 From: Douglas Bates <[hidden email]> Subject: Re: [R] lme X lmer results To: John Maindonald <[hidden email]> Cc: [hidden email] Message-ID:         <[hidden email]> Content-Type: text/plain; charset=ISO-8859-1 On 12/29/05, John Maindonald <[hidden email]> wrote:  >> Surely there is a correct denominator degrees of freedom if the design  >> is balanced, as Ronaldo's design seems to be. Assuming that he has  >> specified the design correctly to lme() and that lme() is getting the df  >> right, the difference is between 2 df and 878 df.  If the t-statistic  >> for the  >> second level of Xvar had been 3.0 rather than 1.1, the difference  >> would be between a t-statistic equal to 0.095 and 1e-6.  In a design  >> where there are 10 observations on each experimental unit, and all  >> comparisons are at the level of experimental units or above, df for  >> all comparisons will be inflated by a factor of at least 9. Doug Bates commented: I don't want to be obtuse and argumentative but I still am not convinced that there is a correct denominator degrees of freedom for _this_ F statistic.  I may be wrong about this but I think you are referring to an F statistic based on a denominator from a different error stratum, which is not what is being quoted.  (Those are not given because they don't generalize to unbalanced designs.) This is why I would like to see someone undertake a simulation study to compare various approaches to inference for the fixed effects terms in a mixed model, using realistic (i.e. unbalanced) examples. Doug-- Here is a paper that focused on the various alternatives to denominator degrees of freedom in SAS and does report some simulation results: http://www2.sas.com/proceedings/sugi26/p262-26.pdfNot sure whether it argues convincingly one way or the other in the present discussion. cheers, Dave -- Dave Atkins, PhD [hidden email] ______________________________________________ [hidden email] mailing list https://stat.ethz.ch/mailman/listinfo/r-helpPLEASE do read the posting guide! http://www.R-project.org/posting-guide.html