how to run models on 100 simualted data automatically?

Question

[statfa]

Hi,

I want to compare some models. As I have noticed, they generate 100 simulated data sets and run the models on each one of those data sets and average the results. As you know, running a model 100 times is way too much. I'm sure there must be some automatic methods for that. Do you have any idea? I read about Mont Carlo algorithm but I'mnot sure how to use it. Maybe I should define a loop?

Thank you

Answer 1

[Kevin Blighe]

You could save the model formulae in a list object in R, and then use mclapply() (https://stat.ethz.ch/R-manual/R-devel/library/parallel/html/mclapply.html) to run the models in parallel.

For further information, take a look at my final section of code here: R functions edited for parallel processing