Geometry of Goodness-of-Fit Testing in High Dimensional Low Sample Size Modelling - Frank Critchley, Germain Van Bever, Paul Marriott, Radka Sabolova
-
last edited by Geo-Sci-InfoAuthors : Frank Critchley, Germain Van Bever, Paul Marriott, Radka Sabolova
DOI URL : http://dx.doi.org/10.1007/978-3-319-25040-3_61
Video : http://www.youtube.com/watch?v=VnS93MMajNg
Slides: Sabolova_geometry of goodness.pdf
Presentation : https://www.see.asso.fr/node/14262
Creative Commons Attribution-ShareAlike 4.0 InternationalAbstract:
We introduce a new approach to goodness-of-fit testing in the high dimensional, sparse extended multinomial context. The paper takes a computational information geometric approach, extending classical higher order asymptotic theory. We show why the Wald – equivalently, the Pearson X2 and score statistics – are unworkable in this context, but that the deviance has a simple, accurate and tractable sampling distribution even for moderate sample sizes. Issues of uniformity of asymptotic approximations across model space are discussed. A variety of important applications and extensions are noted.
