**30**wrote:

Hi all,

I just noticed that lmFit() is quite fast for linear model fit even for very big single cell data.

This make me curious that how fast does lmFit() achieve but I haven't found any benchmarking results about that.

If lmFit() is actually the fastest way for simple linear model fit, I guess I would like to always use lmFit() instead of tidyr+purrr+lm() .

If lmFit() is fast because it uses some algorithms where can I find the implemention details ? Assuming I want to write a silimar function using other language like python or julia for my own use.

**50k**• written 6 months ago by heyao •

**30**

I recently had RegParallel accepted to Bioconductor, which can fit independent models via lm(), glm(), bayesglm(), coxph(), et cetera, and parallelise this process (also 'nested' parallel processing is possible). It is not as quick as

lmFit, though. I developed it while having to run conditional logistic regression models on old GWAS data for trios.170