The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.
bgev_mle() was rewritten. It now uses a multistart
Nelder-Mead search on a reparametrised scale (log(sigma),
log(delta)), seeded by quantile matching plus loose
data-driven box starts. Estimation is restricted to
delta > 0 (bimodality requires it, and for
delta < 0 the likelihood is unbounded at
x = mu); the distribution functions still accept the full
delta > -1.DEoptim
object ($optim$bestmem), bgev_mle() now
returns $par, $se, $loglik and
diagnostics. This is a breaking change.se) are returned from the inverse
observed-information Hessian, for an admissible (regular) optimum only;
near the parameter-dependent support boundary they are not reliable and
are returned as NA.convergence,
agree, admissible (a positive-definite-Hessian
acceptance gate that rejects spurious optima), boundary,
and optimum.likelihood = "grouped_likelihood" added for discrete or
rounded data, using the interval likelihood
F(x + h/2) - F(x - h/2); tied data under the continuous
density now raises a warning.bgev_profile_likelihood() for the profile
log-likelihood of a parameter.distCheck() renamed to dist_check().DEoptim and lhs; added
numDeriv and graphics.These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.