Goodness-of-fit tests for noisy directional data
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Richard Samworth.
The spherical convolution model provides a setup where each genuine
observation Xi belonging to S2 the unit sphere of R3, is contaminated
by a small random rotation. The aim of the present work is to
provide nonparametric adaptive minimax goodness-of-fit testing
procedures on f, the density of Xi from noisy
observations. More precisely, let f0 being the uniform density on S2,
we consider the problem
of testing the the null hypothesis f = f0 with alternatives expressed
in L2 norm over Sobolev
class.
This talk is part of the Statistics series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|