This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Stat 704 Data Analysis I Probability Review Timothy Hanson Department of Statistics, University of South Carolina 1 / 29 Course information Logistics: LeConte College 210A, Tuesday & Thursday 3:304:45pm. Instructor: Tim Hanson, Leconte 219C, phone 7773859. Office hours: Tuesday/Thursday 910:30am and by appointment. Required text: Applied Linear Statistical Models (5th Edition), by Kutner, Nachtsheim, Neter, and Li. Online notes at http://www.stat.sc.edu/ ∼ hansont/stat704/stat704.html Grading: homework 50%, two exams 25% each. Stat 704 has a corequisite of Stat 712 (Casella & Berger level mathematical statistics). You need to be taking this, or have taken this already. 2 / 29 A.3 Random Variables def’n : A random variable is defined as a function that maps an outcome from some random phenomenon to a real number. More formally, a random variable is a map or function from the sample space of an experiment, S , to some subset of the real numbers R ⊂ R . Restated: A random variable measures the result of a random phenomenon. Example 1 : The height Y of a randomly selected University of South Carolina statistics graduate student. Example 2 : The number of car accidents Y in a month at the intersection of Assembly and Gervais. 3 / 29 cdf, pdf, pmf Every random variable has a cumulative distribution function (cdf) associated with it: F ( y ) = P ( Y ≤ y ) . Discrete random variables have a probability mass function (pmf) f ( y ) = P ( Y = y ) = F ( y ) F ( y ) = F ( y ) lim x → y F ( x ) . (A.11) Continuous random variables have a probability density function (pdf) such that for a < b P ( a ≤ Y ≤ b ) = integraldisplay b a f ( y ) dy . For continuous random variables, f ( y ) = F ′ ( y ) . Question : Are the two examples on the previous slide continuous or discrete? 4 / 29 A.3 Expected value The expected value , or mean of a random variable is, in general, defined as E ( Y ) = integraldisplay ∞ −∞ y dF ( y ) . For discrete random variables this is E ( Y ) = summationdisplay y : f ( y ) > y f ( y ) . (A.12) For continuous random variables this is E ( Y ) = integraldisplay ∞ −∞ y f ( y ) dy . (A.14) 5 / 29 E ( · ) is linear Note : If a and c are constants, E ( a + cY ) = a + cE ( Y ) . (A.13) In particular, E ( a ) = a E ( cY ) = cE ( Y ) E ( Y + a ) = E ( Y ) + a 6 / 29 A.3 Variance The variance of a random variable measures the “spread” of its probability distribution. It is the expected squared deviation about the mean : var ( Y ) = E { [ Y E ( Y )] 2 } (A.15) Equivalently, var ( Y ) = E ( Y 2 ) [ E ( Y )] 2 (A.15a) Note : If a and c are constants, var ( a + cY ) = c 2 var ( Y ) (A.16) In particular, var ( a ) = var ( cY ) = c 2 var ( Y ) var ( Y + a ) = var ( Y ) Note : The standard deviation of Y is sd ( Y ) = radicalbig var ( Y ) ....
View
Full
Document
This note was uploaded on 12/14/2011 for the course STAT 704 taught by Professor Staff during the Fall '11 term at South Carolina.
 Fall '11
 Staff
 Statistics, Probability

Click to edit the document details