Hi.

Try ‘BayesLogit’. Here is an example streight forward from the package:

data(spambase)

## A subset of the data.

sbase = spambase[seq(1,nrow(spambase),10),]

X = model.matrix(is.spam ~ word.freq.free + word.freq.1999, data=sbase)

y = sbase$is.spam

## Run logistic regression which is Bayesian as default.

output = logit(y, X, samp=1000, burn=100);

For a general purpose package STAN is the best available. It has comprehensive documentation and a large and growing user community. 

Hi Bich,

Using STAN is a good option as Kevin already suggested above.

Here is the manual:

http://www.uvm.edu/~bbeckage/Teaching/DataAnalysis/Manuals/stan-reference-2.8.0.pdf

Here is the google group where they can support you very fast:

http://discourse.mc-stan.org/

Hi Bich,

Take a look at this example:They compare results using GLM and Bayesian modeling fit using STan. The code is also there with some explanation.

https://rpubs.com/kaz_yos/stan-glm1

They compare results using GLM and Bayesian modeling fit using STan. The code is also there with some explanation.

Bascially, you need:

- To arrange the data in a list: something like:

dat