Latin Hypercube Sampling (LHS) is a way of generating random samples of parameter values. It is widely used in Monte Carlo simulation, because it can drastically reduce the number of runs necessary to achieve a reasonably accurate result.
Lonnie Chrisman, PhD, is Lumina's Chief Technical Officer, where he heads engineering and development of Analytica®. He has authored dozens refereed publications in the areas of machine learning, Artificial Intelligence planning, robotics, probabilistic inference, Bayesian networks, and computational biology. He was was in eighth grade when he had his first paid programming job. He was awarded the Alton B. Zerby award 'Most outstanding Electrical Engineering Student in the USA', 1987. He has a PhD in Artificial Intelligence and Computer Science from Carnegie Mellon University; and a BS in Electrical Engineering from University of California at Berkeley.
Lonnie used Analytica for seismic structural analysis of an extension that he built to his own home where he lives with his wife and raised four daughters: So, he really trusts Analytica calculations! Dear Lonnie, I red your comparison between MCS and LHS,Very informative and interesting, thank you. I require your guidance for the below case, appreciate if you share your thoughts. We have been offered to do a calculation of a contingency based on the simulation technic, to run a schedule risk analysis (if to be specific).
The idea beyond is, to identify risk uncertanities, then adopt a specific variable distribution type to this uncertainty and do 3000 iterations. Then apply a P90 approach and quantify the potential amount. After reading your article I become to the conclusion that final amount may be different depending on the application either Monte Carlo or Latin Hypercube. And actually a 1% difference in the final result will be a huge saving for the amount. It will be interesting to hear your thoughts on that?
Powerful Random Sampling and Probability You don't give up any power to gain Risk Solver's ease and speed of use. In fact, Risk Solver gives you more choices for random number generation, more sampling methods, and more analytic distributions than other risk analysis products for Excel. • • • • Random Number Generators Random numbers form the basis of Monte Carlo simulation -- you need to know that simulation software uses the best random number generation algorithms.
Risk Solver's Options dialog lets you easily choose among four high-quality random generators: • Park-Miller 'Minimal' Generator with Bayes-Durham shuffle and safeguards: traditional random number generator with a period of 2 31-2. • Combined Multiple Recursive Generator (CMRG) of L'Ecuyer: period of 2 191, and excellent statistical independence of samples. Fspassengersx working key.
• Well Equidistributed Long-period Linear (WELL1024) generator of Panneton, L'Ecuyer and Matsumoto: period of 2 1024 with very good statistical independence. • Mersenne Twister generator of Matsumoto and Nishimura: period of 2 19937-1, but samples are not as 'equidistributed' as for the WELL1024 and CMRG generators. Sampling Methods Risk Solver Engine can generate Monte Carlo samples from a wide range of probability distributions, using any of three methods: Standard Monte Carlo, Latin Hypercube, and Sobol numbers. Latin Hypercube sampling is a well-known method for reducing sample variance, enabling you to obtain more accurate simulation results with fewer Monte Carlo trials.