[R-sig-ME] Computational speed - MCMCglmm/lmer

Hadley Wickham hadley at rice.edu
Wed Jun 23 18:47:11 CEST 2010

> Forgive me for sounding grouchy but I find this whole discussion
> misguided.  Worrying about the speed of fitting a model and niceties
> of the model formulation before doing elementary checks on the data is
> putting the cart before the horse.  Why is gender coded as 0, 1 and 2?
>  Why, when there was a maximum of 90 days of monitoring, is there one
> id with 435 observations and another with 180 observations.

Especially when you look at (e.g.) subset(drink.df, id == 8396125) and
notice that drinks appear to be repeated in blocks of five.  Looks
like a data processing error - but has it also happened for other

I also wonder why the date has been removed from the data. It seems
like this would be an important covariate (St Patrick's day, match
days, birthdays, ...).  And I hope weekday isn't Monday-Friday...


Assistant Professor / Dobelman Family Junior Chair
Department of Statistics / Rice University

More information about the R-sig-mixed-models mailing list