Compare the moments of the data and the fitted univariate generalised lambda distribution.
After fitting the distribution, it is often desirable to see whether the
moments of the data matches with the fitted distribution. This function computes
the theoretical and actual moments especially for
Fitted distribution parameters, usually output from
Data set used
Naming the method used in fitting the distribution, by default this is "ML".
A matrix showing the mean, variance, skewness and kurtosis of the fitted distribution in comparison to the data set.
Absolute difference in each of the four moments from the data under each of the distibutional fits.
Sometimes it is difficult to find RPRS type of fits to data set, so
fun.comp.moments.ml.2 is used to compare the theoretical
moments of RMFMKL.ML and STAR methods
with respect to the dataset fitted.
1 2 3 4 5 6 7 8 9
## Generate random normally distributed observations. # junk<-rnorm(1000,3,2) ## Fit the dataset using fun.data.ml # fit<-fun.data.fit.ml(junk) ## Compare the resulting fits. It is usually the case the maximum likelihood ## provides better estimation of the moments than the starship method. # fun.comp.moments.ml(fit,junk)