I think this question has been addressed many times on Cross Validated: proposing a negative value when the target distribution is of no consequence since the target density is equal to zero at this negative value. A Metropolis-Hasting algorithm that is described in the question as a random-walk version of MH thus works in such a context: for each proposal with a negative variance, the chain repeats its current value. See, e.g., - [MCMC Metropolis-Hastings' jumping distribution for non-negative parameters][1] - [Narrow distribution and Hasting-Metropolis][2] - [Elementary MCMC pseudocode][3] [1]: https://stats.stackexchange.com/q/260230/7224 [2]: https://stats.stackexchange.com/q/180372/7224 [3]: https://stats.stackexchange.com/q/47459/7224