search for: betadraws

...tor of values from 1 to m # Prior - list of A, betabar # A is nvar x nvar prior preci matrix # betabar is nvar x 1 prior mean # Mcmc # R is number of draws # keep is thinning parameter # s is scaling parameter for random walk # beta0 is initial beta # # Output: # list of betadraws # # Model: Pr(y=j) = exp(x_j'beta)/sum(exp(x_k'beta) # # Prior: beta ~ N(betabar,A^-1) # # check arguments # X=Data$X y=Data$y m=Data$m nvar=ncol(X) nobs=length(y) # check for Prior # if(missing(Prior)) { betabar=c(rep(0,nvar)); A=diag(rep(.01,nvar))} else { if(is.null(Prio...

Hi R-users, I have the following problem: I am trying to learn something about bayes methodology and started paying around bayesm package, but could not replicate the Conjunctive model's estimates as they appear in Rossi et al "Bayesian Statistics and Marketing", 2005, JWS, pages 264-265, Table CS4.4. I have downloaded in my working directory the documents from

Hello, I have built a multi-variate probit model using the package "bayesm", which requires that the X data is constructed using the function "CreateX". I've gone through the documentation and run my model, but wanted to be sure about my interpretation of the results for the coefficients - beta. Steps: 1) I have 5 choices for the dependent variable Y, so p=5 2) I have 8

Hello, I have built a multi-variate probit model using the package "bayesm", which requires that the X data is constructed using the function "CreateX". I've gone through the documentation and run my model, but wanted to be sure about my interpretation of the results for the coefficients - beta. Steps: 1) I have 5 choices for the dependent variable Y, so p=5 2) I have 8