[R-sig-ME] Back-transforming binomial standard errors

[ONKELINX, Thierry]

Dear Adam,

Personally I would keep the data in the logit scale. If you want some kind of se measurement in the original scale, then I suggest to calculate confidence interval in the logit scale, back-transform the interval and then calculate the width of the interval.

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 at 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 at r-project.org [mailto:r-sig-mixed-models-bounces at r-project.org] Namens Adam Hayward
Verzonden: vrijdag 23 maart 2012 11:03
Aan: r-sig-mixed-models at r-project.org
Onderwerp: [R-sig-ME] Back-transforming binomial standard errors

Dear R users,

I am using model predictions from binomial GLMMs and Gaussian LMMs to run GAMs to describe the change in several traits across ages. I can back-transform the binomial model predictions, to rescale them for GAM analysis, but then want to weight these predictions by the standard error of the prediction (because less confidence is attached to older ages because fewer individuals are measured). Because I have standard errors from both Gaussian and binomial models, I feel the standard errors from the binomial GLMMs should also be transformed back to the normal scale, but cannot find information on the proper way to do this. I wonder if anyone knows of a solution to this problem?

Best wishes,
Adam


--
Adam Hayward
Post-Doctoral Research Associate
Department of Animal and Plant Sciences
Alfred Denny Building
University of Sheffield
Western Bank
Sheffield S10 2TN
UK

	[[alternative HTML version deleted]]

_______________________________________________
R-sig-mixed-models at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models