##################################################################
# This R code inputs a dataset (from a textfile), creates analysis
# variables from the dataset, and then carries out three testing
# procedures decribed in Gilbert, Rossini, and Shankarappa (2005),
# "Two-sample tests for comparing intra-individual genetic
# sequence diversity between populations", Biometrics, 2005, 
# 61:107-118. These testing procedures are referred to in the 
# paper as the "pooled mean diversities" test (Tpoolmn), the
# "pooled median diversities" test (Tpoolmed), and the
# "mean subject-specific diversities" test (Tsubjmn).
#
# The procedures are carried out below on the dataset of 
# synonomous distances in HIV infected children, that was used 
# in the Example of Gilbert, Rossini, and Shankarappa (2005).
#################################################################

# Read in the synonomous intra-individual pairwise sequence distances:
datamat <- matrix(scan('Synonomousdistances.txt'),ncol=5,byrow=T)

# Data columns of datamat:
# 1. strand1: an integer that indicates the sequence number from an individual
# 2. strand2: an integer that indicates the sequence number from an individual
# 3. group: 1 if group 1; 2 if group 2
# 4. id: an integer that indicates the individual within a group  
# 5. distance: pairwise distance between sequence strand1 from id and
#              sequence strand2 from id 

# Carry out the three tests:
source('diverstest.r')
diverstest(datamat)

# The ouput is written to the file diverstest.out