Berger.Normal {ClinicalRobustPriors}R Documentation

Normal Log-Odds with Normal and Berger's Priors

Description

Compute the distributions (prior, likelihood and posterior) and moments for the Normal/Normal conjugate model and Berger/Normal robust model. The plots are processed in Log-Odds and OR Scale.

Usage

Berger.Normal(mu,ym,tau,sigma,n0,n,min.value=NULL,max.value=NULL,OR.xlim=NULL)

Arguments

mu the location parameter in Log-Odds Scale for Normal and Berger's Priors.
ym the location parameter in Log-Odds Scale for Normal Likelihood.
tau the scale parameter in Log-Odds for Normal and Berger's Priors.
sigma the scale parameter in Log-Odds Normal Likelihood.
n0 number of prior observations.
n sample size.
min.value minimum value in Log-Odds scale for the plots. The default min.value is 5.
max.value maximum value in Log-Odds scale for the plots. The default max.value is -5.
OR.xlim maximum value for the OR scale in the plot of the Berger/Normal model. The default OR.xlim is c(0,2).

Author(s)

Jairo A. Fuquene P. <jairo.a.fuquene@uprrp.edu>

References

Berger, J. O. (1985), Statistical Decision Theory and Bayesian Analysis, second edn, Springer-Verlag.

Fuquene, J. A., Cook, J. D. & Pericchi, L. R. (2008), A Case for Robust Bayesian priors with Applications to Binary Clinical Trials. UT MD Anderson Cancer Center Department of Biostatistics Working Paper Series. Working Paper 44. 2008. http://www.bepress.com/mdandersonbiostat/paper44.

Spiegelhalter, D. J., Abrams, K. R. & Myles, J. P. (2004), Bayesian Approaches to Clinical Trials and Health-Care Evaluation, Wiley, London.

Examples

#######################
# Example 1: 
#######################
Berger.Normal(-1.97,-0.73,0.31,0.15,406,170)
#######################
# Example 2
#######################
Berger.Normal(-1.97,-0.73,0.31,0.15,406,170,min.value=-3.5,max.value=0,OR.xlim=c(0,1))
#######################
# Example 3
#######################
Berger.Normal(-1.97,-0.73,0.15,0.31,406,170)

[Package ClinicalRobustPriors version 1.1-2 Index]