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: 1 STAT 1301 Probability & Statistics Lecture 14 Lecture 14 Exponential and Gamma Distributions Introduction • In many applications one needs to model the random time of some kind. Examples are: – The time it takes to service a customer – The lifetime of a component – The time a patient survives after an operation • Such a random time T can be regarded as a random variable with distribution defined by some pdf f(t) with t in [0, ). So • The survival function is defined as . ) ( ( b a dt t f b) T a P . ) ( ( s dt t f s) T P Exponential Distribution • The simplest model for a random time with no upper bound on its range is the exponential distribution. • A random time T has an exponential distribution if the pdf of T is f ( t; ) = e t , if t 0. = 0, if t < 0. Mean & Variance • Mean & variance: = E(T) = 1/ , 2 = V(T) = 1 2 = V(T) = 1/ . 2 cdf • The cdf of an exponential distribution can be easily calculated. So survival function . 1 ) ; ( t e t F t • So, survival function • The exponential distribution is often used as a model for the distribution of waiting times. The distribution is closely related to the Poisson process. . , ) ( t e t T P t Poisson Process • Counts of arrivals: The distribution of the number of arrivals N(t) in a fixed time interval of length t is Poisson ( t ) , and the number of arrivals in disjoint time intervals are independent. • Times between arrivals: The distribution of the waiting time W 1 until the first arrival is Exponential( ) , and W 1 and the subsequent waiting times W 2 , W 3 , … between each arrival...
View
Full
Document
This note was uploaded on 05/04/2011 for the course STAT 1301 taught by Professor Smslee during the Spring '08 term at HKU.
 Spring '08
 SMSLee
 Statistics, Probability

Click to edit the document details