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: Lecture Not es IEOR 165 | George Shanthikumar Tu W Th 2-4:30 pm | 3113 Etcheverry Quiz 1 June 16 (2 3 pm) 2 Questions on Estimation HW 1 and 2 2 Sided Notes Quiz 2 June 23 (2 3:30 pm) 2 Questions on Hypothesis Testing HW 3 2 Sided Notes Regression Analysis Recap: Y = a + bx + , where x is the input and Y is the output = , = E 0 Var 2 Data , , = , , xk Yk k 1 n Objectives: : Find Estimates for a and b AND : Find Estimates that minimizes the sum of squared deviations SSD = =- - SSD k 1nYk A Bxk2 = = Ybar 1nk 1nYk = = xbar 1nk 1nxk = = - Sxx k 1 nxk xbar2 = = - (- ) SxY k 1 nxk xbar yk ybar = = - SYY k 1 nyk ybar2 =- Ahat Ybar Bhatxbar | forecast for the mean response = = + * x EYxis Yhat Ahat Bhat x = Bhat SxYSxx = + x a bx = , = = We need to see if EYhat x EAhat a?EBhat b?are they unbiased? Lecture Notes IEOR 165 | George Shanthikumar Tu W Th 2-4:30 pm | 3113 Etcheverry (1) : = Let's calculate EAhat first to show it a = - * EAhat EYbar EBhat x We we first calculate E[Ybar] = = = = + = + * EYbar E1nk 1nYk 1nk 1na bxk a b xbar (2) Substitute: (3) = - * EAhat EYbar EBhat x = + *- * a b xbar EBhat xbar = + - * a b EBhat xbar , We conclude that if Bhat is an unbiased estimator of b then Ahat is unbiased estimator of a (4) = * EBhat 1Sxx ESxY (5) Now what is SxY? = =-- SxY k 1nxk xbarYk Ybar : Substitute = =- +- - * ESxY k 1nxk xbara bxk a b xbar = =-- = k 1nxk xbarxk xbarb bSxx : Therefore = * = EBhat 1Sxx bSxx b (6) So we are able to make the original conclusion....
View Full Document
This note was uploaded on 07/22/2009 for the course IEOR 165 taught by Professor Shanthikumar during the Summer '08 term at University of California, Berkeley.
- Summer '08