Comments - Poker, Probability, Monte Carlo, and R - Data Science Central2019-10-19T01:06:10Zhttps://www.datasciencecentral.com/profiles/comment/feed?attachedTo=6448529%3ABlogPost%3A723761&xn_auth=noI also used Monte Carlo simul…tag:www.datasciencecentral.com,2018-05-28:6448529:Comment:7253732018-05-28T14:13:45.092ZVincent Granvillehttps://www.datasciencecentral.com/profile/VincentGranville
<p>I also used Monte Carlo simulations to compute confidence intervals and perform statistical tests of hypotheses, even when the distribution is known (t-test) but especially when it is intractable.</p>
<p>I also used Monte Carlo simulations to compute confidence intervals and perform statistical tests of hypotheses, even when the distribution is known (t-test) but especially when it is intractable.</p> Another way to think of Monte…tag:www.datasciencecentral.com,2018-05-24:6448529:Comment:7237992018-05-24T15:23:51.338ZGregory Grahamhttps://www.datasciencecentral.com/profile/GregoryGraham
<p>Another way to think of Monte Carlo methods is to think of them as ways to compute an intractable or inconvenient integral or sum. You need a process to generate points randomly within in a set and a map from set elements to boolean values that tell you if a point is in an interesting subset, then the "answer" is just the ratio. Estimating pi by dropping pennies randomly in a unit square and counting how many are in the inscribed circle, or dealing random poker hands and counting pairs,…</p>
<p>Another way to think of Monte Carlo methods is to think of them as ways to compute an intractable or inconvenient integral or sum. You need a process to generate points randomly within in a set and a map from set elements to boolean values that tell you if a point is in an interesting subset, then the "answer" is just the ratio. Estimating pi by dropping pennies randomly in a unit square and counting how many are in the inscribed circle, or dealing random poker hands and counting pairs, both are approaches to solving tricky integrals.</p>