dmom {mombf} | R Documentation |
dmom
and dimom
return the density for the moment and inverse moment
priors, in the univariate and multivariate setting.
pmom
and pimom
return the distribution function for the univariate
moment and inverse moment priors.
qmom
and qimom
return the quantiles for the univariate
moment and inverse moment priors.
dmom(x, V1 = 1, g = 1, n = 1, theta0) dimom(x, V1 = 1, g = 1, n = 1, nu = 1, theta0, logscale = FALSE) pmom(q, V1 = 1, g = 1, n = 1) pimom(q, V1 = 1, g = 1, n = 1, nu = 1) qmom(p, V1 = 1, g = 1, n = 1) qimom(p, V1 = 1, g = 1, n = 1, nu = 1)
x |
In the univariate setting, x is a vector with the
values at which to evaluate the density. In the multivariate setting
it is a matrix with an observation in each row. |
q |
Vector of quantiles. |
p |
Vector of probabilities. |
theta0 |
Location parameter. Defaults to 0. |
V1 |
Scale matrix. Defaults to 1 in univariate setting and the identity matrix in the multivariate setting. |
g |
Prior parameter. See details. |
n |
Prior parameter. See details. |
nu |
Prior parameter. The
tails of the inverse moment prior are proportional to the tails of a
multivariate T with nu degrees of freedom. |
logscale |
For logscale==TRUE , dimom returns the
natural log of the prior density. |
Define the quadratic form q(theta)= (theta-theta0)' * V1^{-1} * (theta-theta0) / (n*g).
The moment prior density is proportional to
q(theta)*dmvnorm(theta,theta0,n*g*V1).
The inverse moment prior density is proportional to
q(theta)^(-(nu+d)/2) * exp(-1/q(theta))
.
pmom, pimom and qimom use closed-form expressions, while qmom uses
nlminb to find quantiles numerically.
dmom
returns the value of the moment prior density.
dimom
returns the value of the inverse moment prior density.
David Rossell
See http://rosselldavid.googlepages.com for technical reports.
g2mode
to find the
prior mode corresponding to a given g
. mode2g
to find the g value corresponding to a given prior mode.
#evaluate and plot the moment and inverse moment priors library(mombf) g <- 1 thseq <- seq(-3,3,length=1000) plot(thseq,dmom(thseq,g=g),type='l',ylab='Prior density') lines(thseq,dimom(thseq,g=g),lty=2,col=2)