11-02 Cont Random Variables (2)

11-02 Cont Random Variables (2) - BTRY 4080 STSCI 4080 Fall...

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

BTRY 4080 / STSCI 4080 Fall 2010 258 Section 5.3: Uniform Random Variables Definition: X is a uniform random variable on the interval ( a,b ) if its probability density function is given by f ( x ) = 1 b a if a < x < b 0 otherwise Useful shorthand: f ( x ) = 1 b a I { x ( a,b ) } . Denote X Uniform ( a,b ) , or simply X U ( a,b ) . Parameters are a,b .

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

View Full Document
BTRY 4080 / STSCI 4080 Fall 2010 259 Cumulative distribution function F ( x ) = 0 if x a x a b a if a < x < b 1 if x b If X U (0 , 1) , then F ( x ) = x (i.e., if 0 x 1 ) Mean & Variance E ( X ) = a + b 2 , V ar ( X ) = ( b a ) 2 12
BTRY 4080 / STSCI 4080 Fall 2010 260 Example (Monte Carlo integration, Slides 19-21): Let g ( x ) be (almost) any function defined on the interval [ a,b ] , where a,b are finite. Suppose we wish to compute the integral I = integraldisplay b a g ( u ) du. For example: g ( u ) = sin 2 ( u ) , a = 0 , b = 2 π ; alternatively, g ( u ) = 1 2 π e u 2 / 2 , a = 1 . 645 , b = 1 . 645 . By Proposition 2.1: we can write I = integraldisplay b a g ( u ) du = ( b a ) integraldisplay b a g ( u ) × 1 ( b a ) du = ( b a ) E [ g ( U )] where U Uniform ( a,b ) . Hence, one can compute I by computing the expectation of g ( U ) , a transformed U ( a,b ) random variable.

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

View Full Document
BTRY 4080 / STSCI 4080 Fall 2010 261 In fact: can approximate the value of I by simulating random numbers from a U ( a,b ) ; this is an example of Monte Carlo integration . General algorithm: 1. Generate a random sample of uniform random numbers, say u 1 ...u n , on the interval [ a,b ] 2. Compute y i = g ( u i ) for i = 1 ...n 3. Compute ¯ y as an approximation to E [ Y ] = E [ g ( U )] 4. Compute ˆ I = ( b a y .
BTRY 4080 / STSCI 4080 Fall 2010 262 An example (reviewed): A fact from trigonometry: I = integraldisplay π/ 2 0 cos xdx = sin parenleftBig π 2 parenrightBig = 1 . Here, and proceeding differently from Slides 19-20: Take g ( x ) = cos( x ) Randomly generate a large number of points between 0 and 1 2 π . Suppose I do this n times, getting the random numbers x 1 ...x n . Compute y i = cos( x i ) for i = 1 , 2 ,...n. Compute hatwide I = π 2 ¯ y .

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

View Full Document
BTRY 4080 / STSCI 4080 Fall 2010 263 In R: the runif(n,a,b) function generates n numbers at random from the interval ( a,b ) . Usage for n = 1000, 100000: > x = runif(1000, 0, pi/2) > y = pi/2 * cos(x) > mean(y) [1] 0.9977134 > x = runif(1000, 0, pi/2) > y = pi/2 * cos(x) > mean(y) [1] 0.9771091 > x = runif(100000, 0, pi/2) > y = pi/2 * cos(x) > mean(y) [1] 0.9991868 > x = runif(100000, 0, pi/2) > y = pi/2 * cos(x) > mean(y) [1] 0.9975812 Food for thought: is it possible to use probability theory to choose n ?
BTRY 4080 / STSCI 4080 Fall 2010 264 Section 5.4: Normal Random Variables Definition: X is a normal random variable, X N ( μ,σ 2 ) , if it has pdf given by f ( x ) = 1 σ 2 π e ( x - μ ) 2 2 σ 2 , −∞ < x < Cumulative distribution function (parameters: μ,σ 2 ): F ( x ) = integraltext x −∞ f ( u ) du Mean & Variance: E ( X ) = μ , V ar ( X ) = σ 2

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

View Full Document
BTRY 4080 / STSCI 4080 Fall 2010 265
BTRY 4080 / STSCI 4080 Fall 2010 266 PDF is classical “bell-shaped” curve. Derived by French mathematician Abraham DeMoivre in 1733 as a way to approximate symmetric binomial probabilities (i.e., p = 1 / 2 ; well before Poisson in 1838!); generalized to arbitrary p by Pierre-Simon Laplace (1812).

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

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern