The toolbox includes:
1. fast random number generators from the truncated univariate and multivariate student/normal distributions;
2. (Quasi-) Monte Carlo estimator of the cumulative distribution function of the multivariate student/normal;
3. accurate computation of the quantile function of the normal distribution in the extremes of its tails.
Z. I. Botev (2017), The Normal Law Under Linear Restrictions: Simulation and Estimation via Minimax Tilting, Journal of the Royal Statistical Society, Series B, Volume 79, Part 1, pp. 1-24
What can I do to sample from a truncated multivariate Gaussian with non-zero mean when the number of inequality constraints is greater than the dimensionality of the random vector (matrix A is not squared)?
Thanks for sharing. Best regards
Thanks for making this toolbox available!
- toolbox can now deal with multivariate truncated Student's t-distribution
Create scripts with code, output, and formatted text in a single executable document.