[R-pkgs] Update for R package KScorrect for K-S goodness-of-fit tests
We wanted to announce v. 1.4.0 of the R package 'KScorrect', which
carries out the Lilliefors correction to the Kolmogorov-Smirnoff (K-S)
test for use in (one-sample) goodness-of-fit tests.
Aside from several minor changes, the biggest change is that the Monte
Carlo algorithm now supports parallel implementation, using the
platform-independent 'doParallel' and 'foreach' infrastructure. For
complex distributions (such as Weibull, gamma, and mixture of normals),
running in parallel can significantly reduce computation time.
It's well-established that it inappropriate to use the K-S test when
sample statistics are used to estimate parameters, which results in
substantially increased Type-II errors. This warning is mentioned in the
ks.test Help page, but no general solution is currently available for
non-normal distributions. The 'KScorrect' package corrects for the bias
by using Monte Carlo simulation, a solution first recommended by
Lilliefors (1967) but not widely heeded.
Distribution functions are provided in the package for the loguniform
and univariate mixture of normal distributions, which are not included
in the R base installation.
Simple examples are provided by calling example(KScorrect) or example(LcKS).