Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

46
Stats 443.3 & 851.3 Summary

description

Block Matrices Let the n × m matrix be partitioned into sub-matrices A 11, A 12, A 21, A 22, Similarly partition the m × k matrix

Transcript of Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Page 1: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Stats 443.3 & 851.3

Summary

Page 2: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

The Woodbury Theorem

11 1 1 1 1 1A BCD A A B C DA B DA

where the inverses11 1 1 1, and exist.A C C DA B

Page 3: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

11 12

21 22

q

n m n qp m p

A AA

A A

Block Matrices

Let the n × m matrix

be partitioned into sub-matrices A11, A12, A21, A22,

11 12

21 22

p

m k m pl k l

B BB

B B

Similarly partition the m × k matrix

Page 4: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

11 12 11 12

21 22 21 22

A A B BA B

A A B B

Product of Blocked Matrices

Then

11 11 12 21 11 12 12 22

21 11 22 21 21 12 22 22

A B A B A B A BA B A B A B A B

Page 5: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

11 12

21 22

p

n n n pp n p

A AA

A A

The Inverse of Blocked Matrices

Let the n × n matrix

be partitioned into sub-matrices A11, A12, A21, A22,

11 12

21 22

p

n n n pp n p

B BB

B B

Similarly partition the n × n matrix

Suppose that B = A-1

Page 6: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

11 12

21 22

p

n n n pp n p

A AA

A A

Summarizing

Let

11 12

21 22

p

n pp n p

B BB B

Suppose that A-1 = B

then

11 1 121 22 21 11 22 21 11 12 22 21B A A B A A A A A A

11 1 112 11 12 22 11 12 22 21 11 12B A A B A A A A A A

1 11 1 1 1 111 11 12 22 21 11 11 12 22 21 11 12 21 11B A A A A A A A A A A A A A

1 11 1 1 1 1

22 22 21 11 12 22 22 21 11 12 22 21 12 22B A A A A A A A A A A A A A

Page 7: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Symmetric Matrices

• An n × n matrix, A, is said to be symmetric if

Note:AA

11

111

AA

ABAB

ABAB

Page 8: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

The trace and the determinant of a square matrix

11 12 1

21 22 2

1 2

n

nij

n n nn

a a aa a a

A a

a a a

Let A denote then n × n matrix

Then

1

n

iii

tr A a

Page 9: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

11 12 1

21 22 2

1 2

det the determinant of

n

n

n n nn

a a aa a a

A A

a a a

also

where1

n

ij ijj

a A

cofactor of ij ijA a

the determinant of the matrix

after deleting row and col.th thi j

11 1211 22 12 21

21 22

deta a

a a a aa a

ji1

Page 10: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

1. 1, I tr I n

Some properties

2. , AB A B tr AB tr BA

1 13. AA

122 11 12 22 2111 12

121 22 11 22 21 11 12

4. A A A A AA A

AA A A A A A A

22 11 12 21 if 0 or 0A A A A

Page 11: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Special Types of Matrices

1. Orthogonal matrices– A matrix is orthogonal if PˊP = PPˊ = I– In this cases P-1=Pˊ .– Also the rows (columns) of P have length 1 and

are orthogonal to each other

Page 12: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Special Types of Matrices(continued)

2. Positive definite matrices– A symmetric matrix, A, is called positive definite

if:

– A symmetric matrix, A, is called positive semi definite if:

022 112211222

111 nnnnn xxaxxaxaxaxAx

0 allfor

x

0 xAx

0 allfor

x

Page 13: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Theorem The matrix A is positive definite if0,,0,0,0 321 nAAAA

nnnn

n

n

n

aaa

aaaaaa

AA

aaaaaaaaa

Aaaaa

AaA

21

22212

11211

332313

232212

131211

32212

12112111

and

,,,

where

Page 14: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Special Types of Matrices(continued)

3. Idempotent matrices– A symmetric matrix, E, is called idempotent if:

– Idempotent matrices project vectors onto a linear subspace

EEE

xExEE

xE

x

Page 15: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Eigenvectors, Eigenvalues of a matrix

Page 16: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

DefinitionLet A be an n × n matrixLet and be such thatx

with 0Ax x x

then is called an eigenvalue of A andand is called an eigenvector of A andx

Page 17: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Note:

0A I x

1If 0 then 0 0A I x A I

thus 0 A I

is the condition for an eigenvalue.

Page 18: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

11 1

1

det = 0n

n nn

a aA I

a a

= polynomial of degree n in .

Hence there are n possible eigenvalues 1, … , n

Page 19: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Thereom If the matrix A is symmetric with distinct eigenvalues, 1, … , n, with corresponding eigenvectors

1 1 1then n n nA x x x x

1, , nx x

Assume 1 i ix x

1 1

1

0, ,

0n

n n

xx x

x

PDP

Page 20: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

The Generalized Inverse of a matrix

Page 21: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

DefinitionB (denoted by A-) is called the generalized inverse (Moore – Penrose inverse) of A if

1. ABA = A2. BAB = B3. (AB)' = AB4. (BA)' = BA

Note: A- is unique

Page 22: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Hence B1 = B1AB1 = B1AB2AB1 = B1 (AB2)'(AB1) '

= B1B2'A'B1

'A'= B1B2'A' = B1AB2 = B1AB2AB2

= (B1A)(B2A)B2 = (B1A)'(B2A)'B2 = A'B1'A'B2

'B2

= A'B2'B2= (B2A)'B2

= B2AB2 = B2

The general solution of a system of Equations

Ax b

x A b I A A z

The general solution

x A b I A A z

where is arbitrary

Page 23: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

1 1then C B BB A A A

Let C be a p×q matrix of rank k < min(p,q),

then C = AB where A is a p×k matrix of rank k and B is a k×q matrix of rank k

Page 24: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

The General Linear Model

npnn

p

p

pn xxx

xxxxxx

y

yy

21

22221

11211

2

1

2

1

,,Let Xβy

ondistributi , a has where 2I0εεβXy N

Page 25: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Geometrical interpretation of the General Linear Model

p

npnn

p

p

pn xxx

xxxxxx

y

yy

xxXβy

1

21

22221

11211

2

1

2

1

,,Let

ondistributi , a has where 2I0εεβXy N

X

xxxβXyμ

of columns by the spanned spacelinear in the lies

221 ppE

Page 26: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Estimation

The General Linear Model

Page 27: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

n

iiip

n

iiip

n

iii

n

ii yxxxxxx

11

112

1121

1

21

n

iiip

n

iiip

n

ii

n

iii yxxxxxx

12

122

1

221

121

n

iiipp

n

iip

n

iipi

n

iipi yxxxxxx

11

22

121

11

the Normal Equations

Page 28: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

yXβXX

The Normal Equations

npnn

p

p

n xxx

xxxxxx

y

yy

21

22221

11211

2

1

, where Xy

Page 29: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Solution to the normal equations

yXβXX ˆ

. of is matrix theIf rank fullX

yXXXβ 1ˆ

Page 30: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Estimate of 2

βXyβXy ˆˆ1ˆ 2

n

yXXXXIy 1

n1

βXyyy ˆ1

n

Page 31: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Properties of The Maximum Likelihood Estimates

Unbiasedness, Minimum Variance

Page 32: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

yXXXβ

1ˆ EE

ββXXXXyXXX

11 E

βcβcβc

ˆˆ EE

22ˆ n

pnE

βXyβXy ˆˆ1ˆ 22

pnpn

ns

s2 is an unbiased estimator of 2.

Unbiasedness

Page 33: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Distributional Properties

Least square Estimates (Maximum Likelidood estimates)

Page 34: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

The General Linear Model

and yXXXXIy 1

pns 1 2. 2

XXXAyAyXXXβ 11 whereˆ 1.

yBy

yXXXXIy 1

1 Now 22

2

spnU

XXXXIB 1 2

1 where

IβXy 2, ~

nN

The Estimates

Page 35: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Theorem

.0 with ,~ 2. 22

2

pnspnU

12, ~ ˆ 1. XXββ

pN

tindependen are and ˆ 3. 2sβ

Page 36: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

The General Linear Model

with an intercept

Page 37: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

npnn

p

p

pn xxx

xxxxxx

y

yy

21

22221

11211

2

1

0

2

1

1

11

,,Let Xβy

ondistributi , a has i.e. 2IβXy

N

ondistributi , a has where 2I0εεβXy

N

The matrix formulation (intercept included)

Then the model becomes

Thus to include an intercept add an extra column of 1’s in the design matrix X and include the intercept in the parameter vector

Page 38: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

The Gauss-Markov Theorem

An important result in the theory of Linear models

Proves optimality of Least squares estimates in a more general setting

Page 39: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

The Gauss-Markov TheoremAssume

IyβXy 2var and E

Consider the least squares estimate of

ˆ 1 yXXXβ

β

nn yayaya

2211

1

ˆ

yayXXXcβc

, an unbiased linear estimator of βc

and

Let nn ybybyb

2211ybdenote any other unbiased linear estimator of βc

βcyb ˆvarvarthen

Page 40: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Hypothesis testing for the GLM

The General Linear Hypothesis

Page 41: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Testing the General Linear Hypotheses

The General Linear Hypothesis H0: h111 + h122 + h133 +... + h1pp = h1

h211 + h222 + h233 +... + h2pp = h2

...hq11 + hq22 + hq33 +... + hqpp = hq

where h11h12, h13, ... , hqp and h1h2, h3, ... , hq are known coefficients. In matrix notation

11

qppqhβH

Page 42: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Testing hβH

:0H

βXyβXy

hβHHXXHhβH

ˆˆ

ˆˆ

statistictest 1

111

pn

qF

pnqFFH , if Reject 0

Page 43: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

An Alternative form of the F statistic

pnRSS

qRSSRSSF H

0

0 assuming Squares of Sum Residual 0

HRSSH

0 assuming Squares of Sum Residual HRSS not

Page 44: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Confidence intervals, Prediction intervals, Confidence Regions

General Linear Model

Page 45: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

cXXcβc 12

ˆ st pn

One at a time (1 – )100 % confidence interval for βc

(1 – )100 % confidence interval for 2 and .

2

2/1

2

22/

2

to

spnspn

22/1

22/

to

pnspns

Page 46: Stats 443.3 & 851.3 Summary. The Woodbury Theorem where the inverses.

Multiple Confidence Intervals associated with the test hβH

:0H

Theorem: Let H be a q × p matrix of rank q.

then

ccHXXHcβHc

allfor ,ˆ 1spnqqF

form a set of (1 – )100 % simultaneous confidence interval for cβHc

allfor

cβHcc

allfor Consider