Download presentation
Presentation is loading. Please wait.
1
A Summary of Random Variable Simulation Ideas for Today and Tomorrow
2
Uniform X is uniformly distributed on the interval [a,b] We write X~unif(a,b) Uses the basis for generating all random variables can be used as a model for a quantity that is known to vary between a and b for which little else is known
3
Uniform method of generation use a random number generator included in software or write your own generator to generate Y~unif(0,1) set X=(b-a)Y+a
4
Normal X is normally distributed with mean and variance Uses model errors in various processes quantities that are sums of lots of other quantities We write X~N(, )
5
Normal method of generation generate Y~N(0,1) Box-Muller method Polar-Marsaglia method set
6
Let U 1 and U 2 be independent unif(0,1) rv’s. The Polar-Marsaglia Method Let V 1 =2U 1 -1 and V 2 =2U 2 -1. If, let Then X 1 =CV 1 and X 2 =CV 2 are independent and normally distributed with mean 0 and variance 1.
7
Exponential Uses lifetimes We write X~exp(rate= ) waiting times service times interarrival times X is exponentially distributed with rate
8
Exponential method of generation The inverse cdf method: invert the cdf set X=F -1 (U) where U~unif(0,1)
9
Double Exponential X has a bilateral (double) exponential distribution with location parameter and shape parameter as a “jump process” in finance we write X~DE(, )
10
method of generation the pdf is consider the case Double Exponential this is a “back-to-back” exponential with rate simulate Y~exp(rate= ) flip a fair coin to add shift X=Y+
11
Gamma X has the gamma distribution with shape parameter and scale parameter Uses sum of exponential event times time to complete a task consisting of consecutive exponential events We write
12
Gamma method of generation the pdf is use accept-reject sampling to generate set
13
Weibull X has the Weibull distribution with shape parameter and scale parameter Uses time to complete a task time to equipment failure We write differs from exponential in that failure probability can vary over time used in reliability testing
14
Weibull method of generation the pdf is set X=F -1 (U) the cdf is invert
15
Beta X has the beta distribution with parameters and well represents bounded rv’s with various kinds of skew (many shapes!) distribution of random proportions rough model in the absence of data We write Uses
16
Beta method of generation the pdf is generate independently set
17
Pareto X has the Pareto distribution with parameter modeling stock price returns modeling incomes we write Uses monitoring production processes
18
Pareto method of generation the pdf is set X=F -1 (U) the cdf is invert
19
Cauchy X has the Cauchy distribution with location parameter and scale parameter mostly interesting for theoretical reasons we write Uses
20
Cauchy method of generation simulate Y~Cauchy(0,1) by inverse cdf method the pdf is let
21
logistic X has the logistic distribution with location parameter and scale parameter growth models we write Uses logistic regression
22
logistic method of generation set X=F -1 (U) the pdf is the cdf is invert:
23
Gumbel X has the Gumbel distribution with location parameter and scale parameter modeling extreme events we write Uses is the natural log of a Weibull with
24
Gumbel method of generation invert the cdf or, take the natural log of a Weibull generated with
25
Log-Normal We write X~LN(, ) model quantities that are products of a large number of random quantities Note: and are not the mean and variance! ln(X) ~ N(, ) Uses time to perform a task, especially a very quick task (pdf spikes near 0 for small )
26
Log-Normal method of generation let generate Y~N(, )
27
Poisson counts the number of events that occur in a unit of time when events are occurring at a constant rate counts the number of events that occur in a unit of time when events are occuring with exponential inter- occurrence times so, we can count events occurring before 1 unit of time by where Y i are iid exponentials.
28
Poisson Specifically, to generate a Poisson rv with rate,we will generate exponential rate inter- arrival times. Note that if U~unif(0,1), So, we also know that
29
Poisson Algorithm: Let a=e -1, b=1, counter=0 Generate U~unif(0,1) and let b=bU If b<a, done: return counter otherwise, counter = counter+1
Similar presentations
© 2024 SlidePlayer.com Inc.
All rights reserved.