AMDA-2008-Session 2 - --U u u F x x Accept-Reject Method f....

Info iconThis preview shows pages 1–10. Sign up to view the full content.

View Full Document Right Arrow Icon
Generation of Random Variates
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Probability Integral Transform F. on distributi the has ) ( F variable random then the Unif(0,1) ~ U If } ) ( : inf{ ) ( F Let cdf. a is F Suppose - - u u x F x u =
Background image of page 2
Exponential Distribution ) Exp( as d distribute is lnU - X variable random then the ,1) Uniform(0 as d distribute is U If λ =
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Gamma Distribution freedom. of degrees 2n on with distributi square - chi the called is on distributi then the 2 If . and n parameters on with distributi Gamma a follows ) ln(U - thenY variables random ,1) Uniform(0 d distribute y identicall t independen are U ,..., U , U If n 1 j j n 2 1 = = = β
Background image of page 4
Beta Distribution on. distributi ,1) Uniform(0 get the then we 1 If . and m parameters with on distributi Beta a follows ) ln( ) ln( thenY variables random ,1) Uniform(0 d distribute y identicall t independen are U ,..., U , U If 1 1 n m 2 1 = = = + = = + n m n U U n m j j m j j
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Normal Distribution (Box-Muller Algorithm) N(0,1) from draws t independen are x and x . 3 ) 2 sin( ) ln( 2 x ) 2 cos( ) ln( 2 x Define 2. ,1) Uniform(0 iid , U Generate . 1 2 1 2 1 2 2 1 1 2 1 U U U U U π - = - =
Background image of page 6
Cauchy Distribution ) Cauchy(0,1 is 2 1 tan then Unif(0,1) ~ U if Then . 2 1 tan ) ( 2 tan 1 F(x) is cdf The x all for ) 1 ( 1 f(x) by given is on distributi ) Cauchy(0,1 the of pdf The 1 2 - - = + = + =
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 8
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 10
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: --U u u F x x Accept-Reject Method f. to according d distribute is Y variate The otherwise 1 Return to . 3 Mg(X) f(X) U if X Y Accept 2. Unif(0,1) ~ U g, ~ X Generate 1. constant. a is M where x, all for Mg(x) f(x) such that pdfs be g and f Let = Example N(0,1) from generate to method reject -accept apply the can Then we . e 2/ M Hence 1. at x attained is which , by bounded is ) 1 ( g(x) f(x) Now, on. distributi N(0,1) from generate want to We ons. distributi ) Cauchy(0,1 and N(0,1) of pdfs be g and f Suppose 2 2 2 = = + =-x e x Discrete Distributions ) p (Assume k. X put then p If Unif(0,1). ~ U Generate . be X variable random the of on distributi y probabilit Let the 1-k 2 1 2 1 = = < k n n p U p p p x x x...
View Full Document

Page1 / 10

AMDA-2008-Session 2 - --U u u F x x Accept-Reject Method f....

This preview shows document pages 1 - 10. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online