My Math Forum  

Go Back   My Math Forum > College Math Forum > Advanced Statistics

Advanced Statistics Advanced Probability and Statistics Math Forum


Reply
 
LinkBack Thread Tools Display Modes
September 28th, 2017, 04:34 AM   #1
Newbie
 
Joined: Sep 2017
From: australia

Posts: 1
Thanks: 0

variance of ith deleted residual

From linear model, $y = X\beta + \epsilon$, if $\hat{\sigma}^2 = \frac{|y - Xb|^2}{n-p}$ is the variance of error and $\hat{\sigma}_{-i}^2 = \frac{|y_{-i} - X_{-i}b_{-i}|^2}{n-p-1}$ is the estimate of the error variance σ obtained by fitting all the
observations except the i-th. Use the fact that $b - b_{-i} = \frac{(X^TX)^{-1}x_ie_i}{1 - H_{i,i}}$ (can be proved) to show that $\hat{\sigma}_{-i}^2 = \frac{(n - p)\hat{\sigma}^2 - e_i^2/(1-H_{i,i})}{n-p-1}$ where $e_i = y_i - \hat{y_i}$ and $H_{i,i} = x_i(X^TX)^{-1}x_i^T$ is the hat matrix.

So i used the fact $b - b_{-i} = \frac{(X^TX)^{-1}x_ie_i}{1 - H_{i,i}}$, made $b_{-i}$ the subject and sub it in $\hat{\sigma^2_{-i}}$ but no luck simplifying the to desired answer. ANy hints will be helpful.
Xstud is offline  
 
Reply

  My Math Forum > College Math Forum > Advanced Statistics

Tags
deleted, ith, residual, variance



Thread Tools
Display Modes


Similar Threads
Thread Thread Starter Forum Replies Last Post
Arrive specific place time with variance 0 u r neg variance BenFRayfield Complex Analysis 0 January 20th, 2014 06:42 AM
Scatterplot of Residual (Help me, Please) daivinhtran Advanced Statistics 0 October 16th, 2011 01:20 PM
Vector difference residual ProhibitedUsername Linear Algebra 2 July 3rd, 2009 12:34 PM





Copyright © 2017 My Math Forum. All rights reserved.