Hi there! I'm trying to use the R package MSBVAR to generate a conditional forecast from a bayesian VAR. The condition that I am imposing for the forecast is observed values for all but one of the variables. I then want to forecast the path of that one variable, given observed values for all others. I have no problem importing the data and estimating the VAR, however, when I try and use the command "hc.forecast" I get the following errors: Error in solve.default((hstar.update), (crossprod(X.update, Y.update) + : system is computationally singular: reciprocal condition number = 3.6882e-17 Error in chol.default(vcv.Bh) : the leading minor of order 88 is not positive definite This is how I am using the command: conditional<-hc.forecast(flatvar,condition,20,burnin=3000,gibbs=5000) where flat var is a bayesian VAR with a flat prior, condition is a matrix that specifies the condition mentioned above (observed values, and 0's for the variable I want to forecast), 20 is the number of steps I want to forecast. Any help is very much appreciated. I'm new to this so if I am leaving out information please let me know! [[alternative HTML version deleted]]