Generalized tCCH g-Prior Distribution for Coefficients in BMA Models
Creates an object representing the tCCH mixture of g-priors on coefficients for BAS.
tCCH(alpha = 1, beta = 2, s = 0, r = 3/2, v = 1, theta = 1)
alpha |
a scalar > 0, recommended alpha=.5 (betaprime) or 1. |
beta |
a scalar > 0. The value is not updated by the data; beta should be a function of n for consistency under the null model. |
s |
a scalar, recommended s=0 a priori |
r |
r arbitrary; in the hyper-g-n prior sets r = (alpha + 2) |
v |
0 < v |
theta |
theta > 1 |
Creates a structure used for bas.glm
.
returns an object of class "prior", with the family and hyerparameters.
Merlise Clyde
n <- 500 tCCH(alpha = 1, beta = 2, s = 0, r = 1.5, v = 1, theta = 1 / n)
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.