fastlm.R

## Relatively fast linear regression

fastlm = function(xx,yy)
{
  ## compute betahat (regression coef) and pvalue with Ftest
  ## for now it does not take covariates

  df1 = 2
  df0 = 1
  ind = !is.na(xx) & !is.na(yy)
  xx = xx[ind]
  yy = yy[ind]
  n = sum(ind)
  xbar = mean(xx)
  ybar = mean(yy)
  xx = xx - xbar
  yy = yy - ybar

  SXX = sum( xx^2 )
  SYY = sum( yy^2 )
  SXY = sum( xx * yy )

  betahat = SXY / SXX

  RSS1 = sum( ( yy - xx * betahat )^2 )
  RSS0 = SYY

  fstat = ( ( RSS0 - RSS1 ) / ( df1 - df0 ) )  / ( RSS1 / ( n - df1 ) )
  pval = 1 - pf(fstat, df1 = ( df1 - df0 ), df2 = ( n - df1 ))
  res = list(betahat = betahat, pval = pval)

  return(res)
}

## ------------------------------
## August 6, 2012
## Hae Kyung Im
## haky@uchicago.edu
##
## Department of Health Studies
## Biostatistics Laboratory
## University of Chicago

## Please cite:
## Eric R Gamazon, R. Stephanie Huang, Eileen Dolan, Nancy Cox, and Hae Kyung Im, (2012)
## Integrative Genomics: Quantifying significance of phenotype-genotype
## relationships from multiple sources of high-throughput data
## Frontiers of Genetics - under review