|
|
|
|
| Perfect Simulation Since the mid-1990's, there has been much work on the development and application of algorithms that will enable the simulation of the invariant measure of a Markov chain, either exactly (that is, by drawing a random sample known to be from this distribution) or approximately, but with computable order of accuracy. These were sparked by the introduction of the ``coupling-from-the-past'' (CFTP) technique of Propp and Wilson, and several variations and extensions of this idea have since appeared in the literature, and have proven effective in areas such as statistical physics, operations research, and the study of spatial point processes, where they provide simple and powerful alternatives to existing CPU consuming, often unsettlingly inaccurate, simulational methods. |     |
| Numerical Techniques for Empirical Likelihood Description pending! |  |
| Rare Events Simulation Description pending! | |
| Psuedo-Perfect Simulation Perfect simulation algorithms have not been entirely embraced by researchers as they tend to have limited application potential. "Psuedo-perfect" is a term used to describe a class of algorithms based on perfect simulation algorithms with some degree of introduced error. At first these ``imperfect perfect sampling'' schemes, which are easy to implement in practice, may sound like an unappealing oxymoron, but extensive preliminary empirical results suggest that there is much to be gained in accuracy and efficiency of these algorithms over a more traditional entirely non-perfect approach. | |