bayesCR {rotations} | R Documentation |
Bayes credible regions
Description
Find the radius of a 100(1-\alpha)
% credible region for the central orientation and concentration parameter using
non-informative Bayesian methods.
Usage
bayesCR(x, type, S0, kappa0, tuneS, tuneK, burn_in, m = 5000, alp = 0.1)
## S3 method for class 'SO3'
bayesCR(x, type, S0, kappa0, tuneS, tuneK, burn_in, m = 5000, alp = 0.1)
## S3 method for class 'Q4'
bayesCR(x, type, S0, kappa0, tuneS, tuneK, burn_in, m = 5000, alp = 0.1)
Arguments
x |
|
type |
Angular distribution assumed on R. Options are |
S0 |
initial estimate of central orientation |
kappa0 |
initial estimate of concentration parameter |
tuneS |
central orientation tuning parameter, concentration of proposal distribution |
tuneK |
concentration tuning parameter, standard deviation of proposal distribution |
burn_in |
number of draws to use as burn-in |
m |
number of draws to keep from posterior distribution |
alp |
alpha level desired, e.g. 0.05 or 0.10. |
Details
Compute the radius of a 100(1-\alpha)
% credible region for the central orientation and concentration parameter
as described in bingham2009b and bingham2010. The posterior mode is returned along with the radius
of the credible region centered at the posterior mode.
bingham2009b bingham2010
Value
list of
-
Shat,Qhat
Mode of the posterior distribution for the central orientation S -
Radius
Radius of the credible region centered at the posterior mode
See Also
fisheretal
, prentice
, chang
, zhang
Examples
#Not run due to time constraints
Rs <- ruars(20, rvmises, kappa = 10)
#Compare the region size of the moment based theory mean estimator to the
#Bayes region.
region(Rs, method = "direct", type = "theory", estimator = "mean", alp=0.1, m = 100)
bayesCR <- region(Rs, type = "Mises", method = "Bayes", estimator = "mean", S0 = mean(Rs),
kappa0 = 10, tuneS = 5000, tuneK = 1, burn_in = 1000, alp = .01, m = 5000)
bayesCR$Radius #Region size is give by "Radius"
bayesCR$Shat #The Bayes region is centered around the posterior mode: "Shat"