[R] Extracting SD of random effects from lme object
Douglas Bates
bates at stat.wisc.edu
Mon Mar 23 20:41:40 CET 2009
On Mon, Mar 23, 2009 at 2:18 PM, Kingsford Jones
<kingsfordjones at gmail.com> wrote:
> On Mon, Mar 23, 2009 at 11:26 AM, Ben Domingue <ben.domingue at gmail.com> wrote:
>> Hello,
>> How do I get the standard deviations for the random effects out of the
>> lme object? I feel like there's probably a simple way of doing this,
>> but I can't see it. Using the first example from the documentation:
>>
>>> fm1 <- lme(distance ~ age, data = Orthodont) # random is ~ age
>>> fm1
>> Linear mixed-effects model fit by REML
>> Data: Orthodont
>> Log-restricted-likelihood: -221.3183
>> Fixed: distance ~ age
>> (Intercept) age
>> 16.7611111 0.6601852
>>
>> Random effects:
>> Formula: ~age | Subject
>> Structure: General positive-definite
>> StdDev Corr
>> (Intercept) 2.3270339 (Intr)
>> age 0.2264276 -0.609
>> Residual 1.3100399
>>
>> Number of Observations: 108
>> Number of Groups: 27
>>
>> I want to extract the column vector (2.3270339, 0.2264276,
>> 1.3100399)'. Any thoughts?
>
> To get the covariance matrix of the random effects:
>
>> getVarCov(fm1)
> Random effects variance covariance matrix
> (Intercept) age
> (Intercept) 5.41510 -0.321060
> age -0.32106 0.051269
> Standard Deviations: 2.327 0.22643
>
>
> One way to extract the standard deviations shown by the print method above is:
>
>> diag(sqrt(getVarCov(fm1)))
> (Intercept) age
> 2.3270339 0.2264276
> Warning message:
> In sqrt(getVarCov(fm1)) : NaNs produced
You can avoid the warning message if you extract the diagonal first
then take the square root.
sqrt(diag(getVarCov(fm1)))
>
>
> And to get the estimate of the error standard deviation:
>
>> fm1$sigma
> [1] 1.31004
>
>
> hth,
>
> Kingsford Jones
>
>> Thanks,
>> Ben
>>
>> ______________________________________________
>> R-help at r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
>> and provide commented, minimal, self-contained, reproducible code.
>>
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
More information about the R-help
mailing list