This is a wrapper function to call the C routines for the scan statistic to refine current candidate segmentations computing from the IGS
ScanStatRefineComp(combZCumSum, combXCumSum, combZPoint, combXPoint,
p, nTotal, grid.cur, grid.LR, max.win, statistic)A cumulative sum of the number of case reads
A cumulative sum of the number of reads
The number of case reads at the grid points
The number of reads at the grid points
The proportion of case reads in the current region
The total number of reads in the current region
The current grid to be computed on
The left and right limits of the existing candidate segmentations that will be refined, indexed by the current grid
The maximum inter-window to be considered for new scan
The type of statistic. Can be 'binomial','rabinowitz' or 'normal'.
Returns a matrix containing the refined candidate change points
The computations are done in C for speed. The three types of statistics are by the use of exact binomial likelihood ('binomial'), score statistic ('rabinowitz') or using normal approximation to the binomial ('normal').