===================== INSTRUCTIONS ==============================

This document contains instructions for installing and using rGLM
package for R.


1. Install

For Linux users, download the compiled R package file for Linux:
rGLM_1.1.tar.gz
For Windows users, download the compiled R package file for Windows:
rGLM_1.1.zip
Then use the following function in R to install the package
>install.packages(pkgs=filename,repos=NULL)
where "filename" should be replaced with the corresponding file name.

Moreover, install the following packages,
>install.packages(pkgs="hapassoc")
>install.packages(pkgs="glmpath")
>install.packages(pkgs="gtools")



2. Use

Use
>library(rGLM)
>library(hapassoc)
>library(glmpath)
>library(gtools)
to load the packages into R.

Use
>?rGLM
>?one.rGLM.test
>?apply.rGLM.test
to read the instruction.


3. Example 

Using the example data file: hypoDat  
 
          > data(genoDat)
          > example.pre.hapassoc<-pre.hapassoc(genoDat, 3)
          > example.rGLM<-rGLM(affected ~ h000+ h010 + h011 + h100 + pooled,
                              example.pre.hapassoc,lambda=0 )
 
       
          > example.rGLM$beta 
          #    Intercept        h000        h010        h011        h100      pooled 
          #   -1.13877694  0.90310223 -0.42658772  0.08630562 -0.35713887  0.22989182 
           
          > example.rGLM<- rGLM(affected ~ h000+ h010 + h011 + h100 + pooled,
                               example.pre.hapassoc,lambda=1 ) 
           
          > example.rGLM$beta 
          #    Intercept       h000       h010       h011       h100     pooled 
          #    -1.1759560  0.7817717 -0.1555806  0.0000000  0.0000000  0.0000000 
  
 
          > example.test<-apply.rGLM.test(nonSNPcolumns=1,hypoDat=genoDat,
                                         lambda=c(0.2,0.5,0.8),Bpermu=100)  
          #This may take a few minutes, but you can shorten the run time
	  #by having fewer permutations for testing purpose, e.g. Bpermu=10.
          > example.test$permu.pvalue
          # [1] 0.2
          # The results may be different due to permutation.
 

4. Reference

rGLM: 
Guo W, Lin S. (2009). Generalized linear modeling with regularization 
for detecting common disease rare haplotype association. 
Genetics Epidemiology. DOI: 10.1002/gepi.20382. 

hapassoc:
Burkett K, Graham J, McNeney B. 2006. hapassoc: Software
for likelihood inference of trait associations with SNP haplotypes
and other attributes. Journal of Statistical Software {16}:1-19.


-----------------------------------------------------------------
If you have any questions, please email Wei Guo at:
guowei@stat.osu.edu