[R-sig-ME] Interpreting variances in lme with varIdent weights

[ONKELINX, Thierry]

Dear Ellison,

Correlation and variance structures in nlme work only on the residuals, not on the random effects.

Best regards,

Thierry


ir. Thierry Onkelinx
Instituut voor natuur- en bosonderzoek / Research Institute for Nature and Forest
team Biometrie & Kwaliteitszorg / team Biometrics & Quality Assurance
Kliniekstraat 25
1070 Anderlecht
Belgium
+ 32 2 525 02 51
+ 32 54 43 61 85
Thierry.Onkelinx op inbo.be
www.inbo.be

To call in the statistician after the experiment is done may be no more than asking him to perform a post-mortem examination: he may be able to say what the experiment died of.
~ Sir Ronald Aylmer Fisher

The plural of anecdote is not data.
~ Roger Brinner

The combination of some data and an aching desire for an answer does not ensure that a reasonable answer can be extracted from a given body of data.
~ John Tukey


-----Oorspronkelijk bericht-----
Van: r-sig-mixed-models-bounces op r-project.org [mailto:r-sig-mixed-models-bounces op r-project.org] Namens S Ellison
Verzonden: dinsdag 30 juli 2013 12:32
Aan: r-sig-mixed-models op r-project.org
Onderwerp: [R-sig-ME] Interpreting variances in lme with varIdent weights

 We've managed to get ourselves confused in interpreting lme's output and would appreciate clarification; I and a colleague differ on interpreting the words used in lme's help pages and output, and I see his point; it can be read two ways.

Using varIdent weights, lme provides a factor for each varIdent stratum. The question is whether that factor applies to standard deviations for _all_ random effects or just to the sd for the residual term within each stratum.

Any guidance appreciated.

S Ellison
LGC

*******************************************************************
This email and any attachments are confidential. Any use...{{dropped:13}}