F14-SLRinMatrices

# F14-SLRinMatrices - PubH 7405: REGRESSION ANALYSIS SL...

This preview shows pages 1–14. Sign up to view the full content.

PubH 7405: REGRESSION ANALYSIS SL REGRESSION IN MATRIX TERMS

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
BASIC REGRESSION MATRICES n n x x x Y Y Y 1 1 1 2 1 2 1 X Y X is special, called “ Design Matrix
The dimension of “ Design Matrix ”X could be changed to handle more than one predictor: more columns ; the first column (filled with “1”) is not included when doing “Regression through the origin” (i.e. no intercept).

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
X is called the Design Matrix . There are two reasons for the name: (1) By the model, the values of X are under the controlled of investigators: entries are fixed/designed , (2) The design/choice is consequential : the larger the variation in x’s the more precise the estimate of the slope.
REGRESSION OPERATIONS i i i n n i n n y x y y y y x x x y y y y y y y 2 1 2 1 2 2 1 2 1 1 1 1 ] [ ] [ Y X Y Y ' ' Order is important ; cannot form YX’

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
2 2 1 2 1 1 1 1 1 1 1 i i i n n x x x n x x x x x x X X' Here, we can form XX’ but it is a different n-by-n matrix which we do not need.
If Y is a (column) vector, Y’Y is like a “Sum of Squares” – a scalar. We’ll use it to form SSE Y’Y, X’Y, and X’X form “ sufficient statistics

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
INVERSE OF A 2x2 MATRICE | A | or A; of " " the is bc) ad ( D 1 t determinan A A D a D c D b D d d c b a
A singular matrix does not have an inverse because its “determinants” is zero: 0 (6)(7) - (2)(21) D : and 0 0 21 6 ) 1 ( 7 2 ) 3 ( : have We 21 7 6 2 A

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
REGRESSION EXAMPLE 0 ) ( ) )( ( 2 _ 2 2 x x n x x x n D x x x n X X'
2 _ 2 _ _ 2 _ _ 2 _ 2 _ 2 _ 2 _ 2 _ 2 _ 2 1 ) ( 1 ) ( ) ( ) ( 1 ) ( ) ( ) ( ) ( ) ( x x x x x x x x x x x n x x n n x x n x x x n x x x n x X X' Entries are functions of mean and variance of X

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
SIMPLE LINEAR REGRESSION MODEL ε X β Y ε β X Y or ; 1 1 1 ,..., 2 , 1 ; 1 1 2 2 1 2 1 1 0 2 1 2 1 1 0 nx x nx nx n n n i i i X X X Y Y Y n i X Y