Likelihood p-values ancillaries and the vector quantile function
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact rbg24.
Likelihood p-values and ancillaries have been around for
much longer than most would acknowledge, yet continue to be clouded by
lack of agreement and direction. Asymptotics from Daniels to
Barndorff-Nielsen has has extended core versions to give highly
accurate approximations in more general contexts, but with variable
and parameter essentially of the same dimension. More recently the
vector quantile function obtained by inverting coordinate distribution
functions to coordinate quantile functions has clarified the role of
continuity and enabled the further extension to sample spaces with
dimension larger than the parameter. We survey these developments and
discuss two examples,
nonlinear regression and Cauchy analysis; equivocal results are resolved.
This talk is part of the Statistics series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|