[R] R-squared of a distribution fitting

Duarte Viana viana.sptd at gmail.com
Mon Aug 10 15:11:42 CEST 2009


Hello,

I am fitting a parameterized log-normal distribution to a sample
distribution (pdf). I am using the function "fitdistr" in package MASS
to calculate the distribution parameters according to the maximum
likelihood procedure and test for the goodness of fit using a
chi-squared test (as I have binned data). However I would like to
calculate the R-squared associated to the fit, since I will need to
have a dispersion measure. Can someone help me on this? Is there a
simple way of doing this?

Thanks in advance,

Duarte




More information about the R-help mailing list