help with glmer
You should use log(time) as an offset, not time. I prefer to include it in the model formula, but that's largely a question of style. @SteveCandy: with a cloglog link in a binomial-outcome model, using log(time) as an offset allows a natural way to scale the probability of mortality within the time for which an individual has been observed. I recently added a bullet point about using time rather than log(time) as an offset here: https://bbolker.github.io/mixedmodels-misc/glmmFAQ.html#convergence-warnings Another example of this approach: https://www.researchgate.net/profile/Alexander_Shenkin/publication/328148029_Interactive_effects_of_tree_size_crown_exposure_and_logging_on_drought-induced_mortality/links/5bc0645f299bf1004c5ac9f9/Interactive-effects-of-tree-size-crown-exposure-and-logging-on-drought-induced-mortality.pdf
On Thu, Nov 29, 2018 at 8:07 PM Steve Candy <burwood70 at gmail.com> wrote:
Hi Sachiin
I do not understand why "time" is included as an offset and even before
that what the variable "number of years" refers to. An offset does not
allow any scaling by a corresponding regression coefficient so you have to
be very careful to determine whether a predictor variable can validly be
included as an offset.
cheers
Steve
--
Dr Steven G. Candy
Director/Consultant
SCANDY STATISTICAL MODELLING PTY LTD
(ABN: 83 601 268 419)
70 Burwood Drive
Blackmans Bay, TASMANIA, Australia 7052
Mobile: (61) 0439284983
[[alternative HTML version deleted]]
_______________________________________________ R-sig-mixed-models at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models