Results 271 to 280 of about 4,815,078 (315)

Unimodality and exponential families

Communications in Statistics, 1973
Relationships between uninodality, strong unimodality and canonical exponential families axe studied. Furthermore, some considerations axe given pertaining to the duality viewpoint as applied to the sampling and the likelihood aspects of statistical models.
O Barndorff-Nielsen
exaly   +4 more sources

Exponential Families

Graduate Studies in Mathematics, 2018
θ is the canonical parameter and t(x) the canonical statistic. Here x is a continuous or discrete, possibly vector valued random variable. The function h(x) is here written in the exponent; sometimes it is brought outside as a multiplicative factor in an
N. Kiefer
semanticscholar   +2 more sources

Cuts in Natural Exponential Families

Theory of Probability and Its Applications, 1996
The concept of cuts [\textit{O. E. Barndorff-Nielsen}, Exponential families and conditioning. Sc. D. Thesis, Univ. Copenhagen (1973; Zbl 0297.62001)], which is intimately connected to the concepts of \(S\)-ancillarity and \(S\)-sufficiency, has been studied in the context of general exponential families.
O E Barndorff-Nielsen
exaly   +4 more sources

Exponential families [PDF]

open access: yes, 2012
Exponential families of distributions are parametric dominated families in which the logarithm of probability densities take a simple bilinear form (bilinear in the parameter and a statistic). As a consequence of that special form, sampling models in those families admit a finite-dimensional sufficient statistic irrespective of the sample size, and ...
Hallin, M.   +2 more
core   +4 more sources

Home - About - Disclaimer - Privacy