Evaluation for density and distribution function of convolution of gamma
distributions in R. Two related exact methods and one approximate method are
implemented with efficient algorithm and C++ code. A quick guide for choosing
correct method and usage of this package is given in package vignette. For the
detail of methods used in this package, we refer the user to
pcoga2dim to make it faster and more robust.
dcoga to make it can handle wider ranges of parameters and x.
Add new function
pcoga_approx for approximation method, that can impove the speed of code under three or more variables case.
microbenchmark from Suggests according to the requirement from CRAN.
Move vignette to inst in order to pass the cran check with devel R.
starn, in order to meet the requirement of solaris.
RcppGSL from import.
Create 'coga.h' and 'coga_RcppExports.h' to make C++ code can be called directly.
Modify parameter shape and rate recycling work. When the length of one parameter is not a multiple of another,
rcoga will return a warning.
pcoga2dim, in order to achieve higher performance under situation of convolution of two gamma distributions.
pcoga2dim_diff_shape, in order to implementing the recurrence identity of shape parameter of convolution of two gamma distributions distribution function.
Update CRAN URL and BugReport URL from bitbucket to github.
dcogafor density function of convolution of gamma distributions,
pcogafor distribution function of convolution of gamma distributions, and
rcogafor simulating sample from convolution of gamma distributions.