Repository files navigation

Source:docs/R/01-figure-timing-assoc.R

Thematlm R package fits linear models in matrix form and avoids callinglm.That makes computation efficient if many predictors need to be tested,while callinglm for every predictor results in a considerable overhead in computation time.

• Vignettes
  • Computation of linear models in matlm
  • Correlated tests statistics

(yet to be implemented)

• Split a set of predictors into batches
  • Parallel computation
• Support different formats to store predictors:matrix,big.matrix, etc
  • Use S3 classes for the interface
• Run GLS models (not only OLS)

• GWAS on your notebook: fast semi-parallel linear and logistic regression for genome-wide association studies