[R] anova(lme.model)

Sun Nov 7 16:08:04 CET 2010

I said nothing about legitimacy. I only suggested what I thought was a
more satisfactory way the OP could get the issues resolved, since they
seemed to go beyond R. The R-sig-mixed-models (check spelling) list
might be a good place to look.

I believe Th R-help archives not the packages contain Doug Bates's
comments on the issue.

-- Bert

On Sat, Nov 6, 2010 at 11:30 AM, Mike Marchywka <marchywka at hotmail.com> wrote:
>
>> Date: Sat, 6 Nov 2010 07:45:26 -0700
>> From: gunter.berton at gene.com
>> To: sibylle.stoeckli at gmx.ch
>> CC: r-help at r-project.org
>> Subject: Re: [R] anova(lme.model)
>>
>> Sounds to me like you should really be seeking help from your local
>> statistician, not this list. What you request probably cannot be done.
>
>
> I'm still bringing my install up to speed so I can't immediately
> read the cited R stuff below but it sounds like the OP
> mentions a controversy documented in the R packages. Is there
> a list for discussing these topics? Offhand that seems legitimate
> for a user help list unless you want people to believe that
> " it came out of a computer so it must be right, whatever a P value
> is."
>
>
>>
>> What is wrong with what you get from lme, whose results seem fairly
>> clear whether the P values are accurate or not?
>>
>> Cheers,
>> Bert
>>
>>
>>
>>
>>
>> On Sat, Nov 6, 2010 at 4:04 AM, "Sibylle Stöckli"
>>  wrote:
>> > Dear R users
>> >
>> > Topic: Linear effect model fitting using the nlme package (recomended by Pinheiro et al. 2008 for unbalanced data set).
>> >
>> > The R help provides much info about the controversy to use the anova(lme.model) function to present numerator df and F values. Additionally different p-values calculated by lme and anova are reported. However, I come across the same problem, and I would very much appreciate some R help to fit an anova function to get similar p-values compared to the lme function and additionally to provide corresponding F-values. I tried to use contrasts and to deal with the ‚unbalanced data set’.
>> >
>> > Thanks
>> > Sibylle
>> >
>> >> Kaltenborn<-read.table("Kaltenborn_YEARS.txt", na.strings="*", header=TRUE)
>> >>
>> >>
>> >> library(nlme)
>> >
>> >> model5c<-lme(asin(sqrt(PropMortality))~Diversity+ Management+Species+Height+Height*Diversity, data=Kaltenborn, random=~1|Plot/SubPlot, na.action=na.omit, weights=varPower(form=~Diversity), subset=Kaltenborn$ADDspecies!=1, method="ML")
>> >
>> >> summary(model5c)
>> > Linear mixed-effects model fit by maximum likelihood
>> >  Data: Kaltenborn
>> >  Subset: Kaltenborn$ADDspecies != 1
>> >        AIC       BIC   logLik
>> >  -249.3509 -205.4723 137.6755
>> >
>> > Random effects:
>> >  Formula: ~1 | Plot
>> >        (Intercept)
>> > StdDev:  0.06162279
>> >
>> >  Formula: ~1 | SubPlot %in% Plot
>> >        (Intercept)   Residual
>> > StdDev:  0.03942785 0.05946185
>> >
>> > Variance function:
>> >  Structure: Power of variance covariate
>> >  Formula: ~Diversity
>> >  Parameter estimates:
>> >    power
>> > 0.7302087
>> > Fixed effects: asin(sqrt(PropMortality)) ~ Diversity + Management + Species +      Height + Height * Diversity
>> >                      Value  Std.Error  DF   t-value p-value
>> > (Intercept)       0.5422893 0.05923691 163  9.154585  0.0000
>> > Diversity        -0.0734688 0.02333159  14 -3.148896  0.0071
>> > Managementm+      0.0217734 0.02283375  30  0.953562  0.3479
>> > Managementu      -0.0557160 0.02286694  30 -2.436532  0.0210
>> > SpeciesPab       -0.2058763 0.02763737 163 -7.449198  0.0000
>> > SpeciesPm         0.0308005 0.02827782 163  1.089210  0.2777
>> > SpeciesQp         0.0968051 0.02689327 163  3.599602  0.0004
>> > Height           -0.0017579 0.00031667 163 -5.551251  0.0000
>> > Diversity:Height  0.0005122 0.00014443 163  3.546270  0.0005
>> >  Correlation:
>> >                 (Intr) Dvrsty Mngmn+ Mngmnt SpcsPb SpcsPm SpcsQp Height
>> > Diversity        -0.867
>> > Managementm+     -0.173 -0.019
>> > Managementu      -0.206  0.005  0.499
>> > SpeciesPab       -0.253  0.085  0.000  0.035
>> > SpeciesPm        -0.239  0.058  0.001  0.064  0.521
>> > SpeciesQp        -0.250  0.041 -0.001  0.032  0.502  0.506
>> > Height           -0.518  0.532 -0.037 -0.004  0.038  0.004  0.033
>> > Diversity:Height  0.492 -0.581  0.031 -0.008 -0.149 -0.099 -0.069 -0.904
>> >
>> > Standardized Within-Group Residuals:
>> >        Min          Q1         Med          Q3         Max
>> > -2.99290873 -0.60522612 -0.05756772  0.62163049  2.80811502
>> >
>> > Number of Observations: 216
>> > Number of Groups:
>> >             Plot SubPlot %in% Plot
>> >               16                48
>> >
>> >> anova(model5c)
>> >                 numDF denDF   F-value p-value
>> > (Intercept)          1   163 244.67887  <.0001
>> > Diversity            1    14   1.53025  0.2364
>> > Management           2    30   6.01972  0.0063
>> > Species              3   163  51.86699  <.0001
>> > Height               1   163  30.08090  <.0001
>> > Diversity:Height     1   163  12.57603  0.0005
>> >>
>> >
>>
>> --
>> Bert Gunter
>> Genentech Nonclinical Biostatistics
>>
>
>
>
>
>
>
> Mike Marchywka | V.P. Technology
>
> 415-264-8477
> marchywka at phluant.com
>
> Online Advertising and Analytics for Mobile
> http://www.phluant.com
>
>
>

-- 
Bert Gunter
Genentech Nonclinical Biostatistics
467-7374
http://devo.gene.com/groups/devo/depts/ncb/home.shtml