17
How do we generate the statistics of a function of a random variable? Why is the method called “Monte Carlo?” How do we use the uniform random number generator to generate other distributions? Are other distributions directly available in matlab? How do we accelerate the brute force approach? Probability distributions and moments Web links: http://www.riskglossary.com/link/monte_carlo_me onte Carlo Simulation SOURCE: http://pics.hoobly.com/full/AA7G6VQPPN2A.j

How do we generate the statistics of a function of a random variable? – Why is the method called “Monte Carlo?” How do we use the uniform random number

Embed Size (px)

Citation preview

  • Slide 1

Slide 2 How do we generate the statistics of a function of a random variable? Why is the method called Monte Carlo? How do we use the uniform random number generator to generate other distributions? Are other distributions directly available in matlab? How do we accelerate the brute force approach? Probability distributions and moments Web links: http://www.riskglossary.com/link/monte_carlo_method.htm http://physics.gac.edu/~huber/envision/instruct/montecar.htm Monte Carlo Simulation SOURCE: http://pics.hoobly.com/full/AA7G6VQPPN2A.jpg Slide 3 Basic Monte Carlo Given a random variable X and a function h(X): sample X: [x 1,x 2,,x n ]; Calculate [h(x 1 ),h(x 2 ),,h(x n )]; use to approximate statistics of h. Example: X is U[0,1]. Use MCS to find mean of X 2 x=rand(10); y=x.^2; %generates 10x10 random matrix mean=sum(y)/10 x =0.4017 0.5279 0.1367 0.3501 0.3072 0.3362 0.3855 0.3646 0.5033 0.2666 mean=0.3580 What is the true mean SOURCE: http://schools.sd68.bc.ca/ed611/akerley/question.jpg SOURCE: http://www.sz-wholesale.com/uploadFiles/041022104413s.jpg Slide 4 Obtaining distributions Histogram: y=randn(100,1); hist(y) Slide 5 Cumulative density function Cdfplot(y) [f,x]=ecdf(y); Slide 6 Histogram of average x=rand(100); y=sum(x)/100; hist(y) Slide 7 Histogram of average x=rand(1000); y=sum(x)/1000; hist(y ) What is the law of large numbers? Slide 8 Distribution of x 2 x=rand(10000,1); x2=x.^2; hist(x2,20) Slide 9 Other distributions Other distributions available in matlab For example, Weibull distribution r=wblrnd(1,1,1000); hist(r,20) Slide 10 Correlated Variables For normal distribution can use Matlabs mvnrnd R = MVNRND(MU,SIGMA,N) returns a N-by- D matrix R of random vectors chosen from the multivariate normal distribution with 1-by-D mean vector MU, and D-by-D covariance matrix SIGMA. Slide 11 Example mu = [2 3]; sigma = [1 1.5; 1.5 3]; r = mvnrnd(mu,sigma,20); plot(r(:,1),r(:,2),'+') What is the correlation coefficient? Slide 12 Problems Monte Carlo Use Monte Carlo simulation to estimate the mean and standard deviation of x 2, when X follows a Weibull distribution with a=b=1. Calculate by Monte Carlo simulation and check by integration the correlation coefficient between x and x 2, when x is uniformly distributed in [0,1] Slide 13 Latin hypercube sampling X = lhsnorm(mu,SIGMA,n) generates a latin hypercube sample X of size n from the multivariate normal distribution with mean vector mu and covariance matrix SIGMA. X is similar to a random sample from the multivariate normal distribution, but the marginal distribution of each column is adjusted so that its sample marginal distribution is close to its theoretical normal distribution. Slide 14 Comparing MCS to LHS mu = [2 2]; sigma = [1 0; 0 3]; r = lhsnorm(mu,sigma,20); sum(r)/20 ans = 1.9732 2.0259 r = mvnrnd(mu,sigma,20); sum(r)/20 ans =2.3327 2.2184 Slide 15 Evaluating probabilities of failure Failure is defined in terms of a limit state function that must satisfy g(r)>0, where r is a vector of random variables. Probability of failure is estimated as the ratio of number of negative gs, m, to total MC sample size, N The accuracy of the estimate is poor unless N is much larger than 1/P f For small P f Slide 16 problems probability of failure 1.Derive formula for the standard deviation of estimate of P f 2.If x is uniformly distributed in [0,1], use MCS to estimate the probability that x2>0.95 and estimate the accuracy of your estimate from the formula. 3. Calculate the exact value of the answer to Problem 2 (that is without MCS). Source: Smithsonian Institution Number: 2004-57325 Slide 17 Separable Monte Carlo Usually limit state function is written in terms of response vs. capacity g=C(r)-R(r)>0 Failure typically corresponds to structures with extremely low capacity or extremely high response but not both Can take advantage of that in separable MC Slide 18 Reading assignment Ravishankar, Bharani, Smarslok B.P., Haftka R.T., Sankar B.V. (2010)Error Estimation and Error Reduction in Separable Monte Carlo Method AIAA Journal,Vol 48(11), 22252230. Source: www.library.veryhelpful.co.uk/ Page11.htm