6.3.12. statsmodels.sandbox.distributions.sppatch¶
patching scipy to fit distributions and expect method
This adds new methods to estimate continuous distribution parameters with some fixed/frozen parameters. It also contains functions that calculate the expected value of a function for any continuous or discrete distribution
It temporarily also contains Bootstrap and Monte Carlo function for testing the distribution fit, but these are neither general nor verified.
Author: josef-pktd License: Simplified BSD
6.3.12.1. Functions¶
distfitbootstrap(sample, distr[, nrepl]) |
run bootstrap for estimation of distribution parameters |
distfitmc(sample, distr[, nrepl, distkwds]) |
run Monte Carlo for estimation of distribution parameters |
expect(self[, fn, args, loc, scale, lb, ub, ...]) |
calculate expected value of a function with respect to the distribution |
expect_discrete(self[, fn, args, loc, lb, ...]) |
calculate expected value of a function with respect to the distribution |
expect_v2(self[, fn, args, loc, scale, lb, ...]) |
calculate expected value of a function with respect to the distribution |
fit_fr(self, data, *args, **kwds) |
estimate distribution parameters by MLE taking some parameters as fixed |
nnlf_fr(self, thetash, x, frmask) |
|
printresults(sample, arg, bres[, kind]) |
calculate and print(Bootstrap or Monte Carlo result |