This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Chapter 4 Stat 211 Prof Parzen STANDARD DISTRIBUTIONS FOR APPLIED STATISTICS In statistical practice there are a small number of distinguished distributions which researchers use as models for observed data. The continuous distributions that are fundamental to modeling data are described using parameters and standard distributions such as Uniform (0,1), Exponential(1) and Normal(0,1). A continuous random variable U is said to have a (standard) Uniform(0,1) distribution if it has probability density ( 29 ( 29 ; 1, 0 1 0, otherwise; f y f y U y = = < < = We often use U as a symbol for a Uniform(0,1) random variable. We write U=Uniform(0,1) to mean the random variable U on left of the equation equals in distribution (has the same distribution) as the distribution on the right side of the equation. DEFINITION: Uniform(a,b) distributions where a<b are specified numbers called parameters of the distribution is defined ( 29 ( 29 ( 29 ; , 1 , f y Uniform a b b a a y b =- < < . A continuous random variable Y is said to have (standard) Exponential(1) distribution if it has probability density ( 29 ( 29 ; , 0, otherwise. y f y f y Y e y- = = = We often use W as a symbol for an Exponential(1) random variable and write W =Exponential(1) DEFINITION: A random variable Y is said to have Exponential distribution with location parameter and scale parameter if Y W = + , where W = Exponential(1). Equivalently the probability density of Y is ( 29 ( 29 1 ; ; 1 exp , , otherwise ; | , y f y Y f W y y f y Y - = - =- = = To emphasize that the probability density depends on parameters and we write it ( 29 1 ; | , ; . y f y Y f W - = Equivalent notation: ( 29 1 Y Exponential = + Very important in practice is case = . Then equivalent statements are: Y = Exponential (where = means equal in distribution), Y is Exponential ( 29 0, . STANDARD NORMAL DISTRIBUTION A continuous random variable Y is said to have (standard) Normal(0,1) distribution if it has probability density ( 29 ( 29 ( 29 ; f y f y Y y = = where ( 29 y has a universal meaning as ( 29 ( 29 2...
View Full Document
This note was uploaded on 03/27/2008 for the course STAT 211 taught by Professor Parzen during the Fall '07 term at Texas A&M.
- Fall '07