Skip to content

Matrix Algebra Useful for Statistics

Best in textbook rentals since 2012!

ISBN-10: 0470009616

ISBN-13: 9780470009611

Edition: 1982

Authors: Shayle R. Searle

List price: $169.95
Shipping box This item qualifies for FREE shipping.
Blue ribbon 30 day, 100% satisfaction guarantee!
what's this?
Rush Rewards U
Members Receive:
Carrot Coin icon
XP icon
You have reached 400 XP and carrot coins. That is the daily max!

Description:

An easy to understand guide to matrix algebra and its uses in statistical analysis. Presents material in an explanatory style instead of the formal theorem-proof format; the only background necessary is high school algebra. The self-contained text includes numerous applied illustrations, numerical examples, and exercises.
Customers also bought

Book details

List price: $169.95
Copyright year: 1982
Publisher: John Wiley & Sons, Incorporated
Publication date: 3/20/2006
Binding: Paperback
Pages: 480
Size: 6.20" wide x 9.20" long x 1.01" tall
Weight: 1.342
Language: English

Introduction
The scope of matrix algebra
General description of a matrix
Subscript notation
Summation notation
Dot notation
Definition of a matrix
Vectors and scalars
General notation
Illustrative examples
Exercises
Basic Operations
The transpose of a matrix
A reflexive operation
Vectors
Partitioned matrices
Example
General specification
Transposing a partitioned matrix
Partitioning into vectors
The trace of a matrix
Addition
Scalar multiplication
Subtraction
Equality and the null matrix
Multiplication
The inner product of two vectors
A matrix-vector product
A product of two matrices
Existence of matrix products
Products with vectors
Products with scalars
Products with null matrices
Products with diagonal matrices
Identity matrices
The transpose of a product
The trace of a product
Powers of a matrix
Partitioned matrices
Hadamard products
The Laws of algebra
Associative laws
The distributive law
Commutative laws
Contrasts with scalar algebra
Exercises
Special Matrices
Symmetric matrices
Products of symmetric matrices
Properties of AA' and A'A
Products of vectors
Sums of outer products
Elementary vectors
Skew-symmetric matrices
Matrices having all elements equal
Idempotent matrices
Orthogonal matrices
Definitions
Special cases
Quadratic forms
Positive definite matrices
Exercises
Determinants
Expansion by minors
First- and second-order determinants
Third-order determinants
n-order determinants
Formal definition
Basic properties
Determinant of a transpose
Two rows the same
Cofactors
Adding multiples of a row (column) to a row (column)
Products
Elementary row operations
Factorization
A row (column) of zeros
Interchanging rows (columns)
Adding a row to a multiple of a row
Examples
Diagonal expansion
The Laplace expansion
Sums and differences of determinants
Exercises
Inverse Matrices
Introduction: solving equations
Products equal to I
Cofactors of a determinant
Derivation of the inverse
Conditions for existence of the inverse
Properties of the inverse
Some simple special cases
Inverses of order 2
Diagonal matrices
I and J matrices
Orthogonal matrices
Idempotent matrices
Equations and algebra
Solving linear equations
Algebraic simplifications
Computers and inverses
The arithmetic of linear equations
Rounding error
Left and right inverses
Exercises
Rank
Linear combinations of vectors
Linear transformations
Linear dependence and independence
Definitions
General characteristics
Linearly dependent vectors
At least two a's are nonzero
Vectors are linear combinations of others
Partitioning matrices
Zero determinants
Inverse matrices
Testing for dependence (simple cases)
Linearly independent (LIN) vectors
Nonzero determinants and inverse matrices
Linear combinations of LIN vectors
A maximum number of LIN vectors
The number of LIN rows and columns in a matrix
The rank of a matrix
Rank and inverse matrices
Permutation matrices
Full-rank factorization
Basic development
The general case
Matrices of full row (column) rank
Vector spaces
Euclidean space
Vector spaces
Spanning sets and bases
Many spaces of order n
Subspaces
The range and null space of a matrix
Exercises
Canonical Forms
Elementary operators
Row operations
Transposes
Column operations
Inverses
Rank and the elementary operators
Rank
Products of elementary operators
Equivalence
Finding the rank of a matrix
Some special LIN vectors
Calculating rank
A general procedure
Reduction to equivalent canonical form
Row operations
Column operations
The equivalent canonical form
Non-uniqueness of P and Q
Existence is assured
Full-rank factorization
Rank of a product matrix
Symmetric matrices
Row and column operations
The diagonal form
The canonical form under congruence
Two special provisions
Full-rank factorization
Non-negative definite matrices
Diagonal elements and principal minors
Congruent canonical form
Full-rank factorization
Quadratic forms as sums of squares
Full row (column) rank matrices
Exercises
Generalized Inverses
The Moore-Penrose inverse
Generalized inverses
Derivation from row operations
Derivation from the diagonal form
Other names and symbols
An algorithm
An easy form
A general form
Arbitrariness in a generalized inverse
Symmetric matrices
Non-negative definite matrices
A general algorithm
The matrix X'X
Exercises
Solving Linear Equations
Equations having many solutions
Consistent equations
Definition
Existence of solutions
Tests for consistency
Equations having one solution
Deriving solutions using generalized inverses
Obtaining a solution
Obtaining many solutions
All possible solutions
Combinations of solutions
Linearly independent solutions
An invariance property
Equations Ax = 0
General properties
Orthogonal solutions
Orthogonal vector spaces
A complete example
Least squares equations
Exercises
Partitioned Matrices
Orthogonal matrices
Determinants
Inverses
Schur complements
Generalized inverses
Direct sums
Direct products
Exercises
Eigenvalues and Eigenvectors
Introduction: age distribution vectors
Derivation of eigenvalues
Elementary properties of eigenvalues
Eigenvalues of powers of a matrix
Eigenvalues of a scalar-by-matrix product
Eigenvalues of polynomials
The sum and product of eigenvalues
Calculating eigenvectors
A general method
Simple roots
Multiple roots
The similar canonical form
Derivation
Uses
Symmetric matrices
Eigenvalues all real
Symmetric matrices are diagonable
Eigenvectors are orthogonal
Rank equals number of nonzero eigenvalues
Dominant eigenvalues
Factoring the characteristic equation
Exercises
Appendix to Chapter 11
Proving the diagonability theorem
The number of nonzero eigenvalues never exceeds rank
A lower bound on r(A - [lambda subscript k]I)
Proof of the diagonability theorem
All symmetric matrices are diagonable
Other results for symmetric matrices
Spectral decomposition
Non-negative definite (n.n.d.) matrices
Simultaneous diagonalization of two symmetric matrices
The Cayley-Hamilton theorem
The singular-value decomposition
Exercises
Miscellanea
Orthogonal matrices-a summary
Idempotent matrices-a summary
The matrix aI + bJ-a summary
Non-negative definite matrices-a summary
Canonical forms and other decompositions-a summary
Matrix Functions
Functions of matrices
Matrices of functions
Iterative solution of nonlinear equations
Vectors of differential operators
Scalars
Vectors
Quadratic forms
Vec and vech operators
Definitions
Properties of vec
Vec-permutation matrices
Relationships between vec and vech
Other calculus results
Differentiating inverses
Differentiating traces
Differentiating determinants
Jacobians
Aitken's integral
Hessians
Matrices with elements that are complex numbers
Exercises
Applications in Statistics
Variance-covariance matrices
Correlation matrices
Matrices of sums of squares and cross-products
Data matrices
Uncorrected sums of squares and products
Means, and the centering matrix
Corrected sums of squares and products
The multivariate normal distribution
Quadratic forms and X[superscript 2]-distributions
Least squares equations
Contrasts among means
Exercises
The Matrix Algebra of Regression Analysis
General description
Linear models
Observations
Nonlinear models
Estimation
Several regressor variables
Deviations from means
The statistical model
Unbiasedness and variances
Predicted y-values
Estimating the error variance
Partitioning the total sum of squares
Multiple correlation
The no-intercept model
Analysis of variance
Testing linear hypotheses
Stating a hypothesis
The F-statistic
Equivalent statements of a hypothesis
Special cases
Confidence intervals
Fitting subsets of the x-variables
Reductions in sums of squares: the R([characters not reproducible]) notation
An Introduction to Linear Statistical Models
General description
The normal equations
A general form
Many solutions
Solving the normal equations
Generalized inverses of X'X
Solutions
Expected values and variances
Predicted y-values
Estimating the error variance
Error sum of squares
Expected value
Estimation
Partitioning the total sum of squares
Coefficient of determination
Analysis of variance
The R([characters not reproducible]) notation
Estimable functions
Testing linear hypotheses
Confidence intervals
Some particular models
The one-way classification
Two-way classification, no interactions, balanced data
Two-way classification, no interactions, unbalanced data
The R([characters not reproducible]) notation (Continued)
References
Index