I need to implement a program that generate a sample from a 3 variated $pdf$ using the Metropolis algorithm (and its variations). I was thinking to use a 3-variated normal distribution as my proposal distribution, but I am having some difficult and doubts doing it. For example, I've seen this simulation in R: http://blog.abhranil.net/2014/02/08/r-code-for-multivariate-random-walk-metropolis-hastings-sampling/

1) He uses metropolis random walk with mean $X^t$ and a given covariance matrix. It seens he uses the fact that this distribution is symmetric. I know it is a normal, but is it always symmetric?

2) What would be better: Draw from a trivariated normal directly or draw each parameter from univariated normal? In the last case, we can't adjust covariance, so it looks less efficient and I don't even know it is valid.

Thanks in advance!


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.