Priors for ordered conditional variance and vector partial correlation
Let the vector X = [X1, ..., Xp]t have a multivariate normal distribution with unknown population mean vector [mu] and variance-covariance matrix [summation operator]. This paper develops minimally informative priors (in the sense of Bernardo) for use when the parameter of interest is either the vector of ordered conditional variances [delta]i2 = Var[Xi | Xj, j < i] (i = 1, ..., p) or the vector partial correlations [varrho]i of X0 with Xi after removal of X1, ..., Xi - 1 (i = 1, ..., p). In each case, the parameter of interest indexes the orbits in the parameter space of a group G whose action is 1-1 or "free", and an algorithm that is generally applicable in this situation is used.
Year of publication: |
1992
|
---|---|
Authors: | Eaves, David ; Chang, Ted |
Published in: |
Journal of Multivariate Analysis. - Elsevier, ISSN 0047-259X. - Vol. 41.1992, 1, p. 43-55
|
Publisher: |
Elsevier |
Keywords: | noninformative priors minimally informatve priors parameter of interest Bayesian inference group models |
Saved in:
Online Resource
Saved in favorites
Similar items by person
-
Moved by Meaning : Attracting, Retaining, and Managing Digital Talent in Government
Ogle, Aaron, (2018)
-
Inference for an anisotropic diffusion model
Eaves, David, (1976)
-
Using calibration weighting to adjust for nonignorable unit nonresponse
Kott, Phillip S., (2010)
- More ...