The Bivariate Normal Distribution
This is Section 4.7 of the 1st edition (2002) of the book Introduction to Probability, by D. P. Bertsekas and J. N. Tsitsiklis. The
material in this section was not included in the 2nd edition (2008).
Let U and V be two i
Induced Hearing Deficit Generates Experimental Paranoia
Author(s): Philip G. Zimbardo, Susan M. Andersen, Loren G. Kabat
Source: Science, New Series, Vol. 212, No. 4502 (Jun. 26, 1981), pp. 1529-1531
Published by: American Association for the Advancement
ix)
Week 5 Tutorial Questions
Consider the following general linear regression model:
anxu :mebmn + em 1) 2,304? [31X] +52% +53qu + Q
where g ~ N(Q, all).
Assume that X is of full rank and that (X X)" exists. Furthermore, assume that all of the
exp
":Neer- 4. tt\! Sot.^d.^
cfw_l"e- \ae.Jcp^ - co4h cj.rsk gr'-es o\^ iqaf,icor-grgy1
a
t
, ffRfiensttl.p b,erb^ten \ a,rc) Y t , ttOIatiAS atl
a
$Clrio-|.*el.!
\pil\
cg)^at:atncfw_,
cfw_3o
\
CArrs-
Ar'\
Of
h^e-
o h.er
Nn X , oG on r.nn?i
a.ZLg
l,r.n,'t.S b
UNIVERSITY OF CAPE TOWN
DEPARTMENT OF STATISTICAL SCIENCES
STA 2005S
CLASS TEST 1 (30 AUGUST 2006)
TIME: 100 minutes
MARKS: 45
1. Suppose that X(21) follows a multivariate normal distribution with density
function
f (x) =
1
2 |1/2
1
13
exp 5x1 + 3x2 x1 x2
1
Lecture 21. The Multivariate Normal Distribution
21.1 Denitions and Comments
The joint moment-generating function of X1 , . . . , Xn [also called the moment-generating
function of the random vector (X1 , . . . , Xn )] is dened by
M (t1 , . . . , tn ) =
1
Lecture 21. The Multivariate Normal Distribution
21.1 Denitions and Comments
The joint moment-generating function of X1 , . . . , Xn [also called the moment-generating
function of the random vector (X1 , . . . , Xn )] is dened by
M (t1 , . . . , tn ) =
UNIVERSITY OF CAPE TOWN
DEPARTMENT OF STATISTICAL SCIENCES
STA2005S - TEST 2
Time: 1 hour 30 minutes
Total Marks: 40
Date: 1 October 2009
No. of Pages: 2 (Plus Tables)
1. Describe the following three basic principles of experimental design. Clearly explai
UNIVERSITY OF CAPE TOWN
DEPARTMENT OF STATISTICAL SCIENCES
STA2005S - TEST 2 SOLUTIONS
1. Principles of experimental design:
(a) Randomization is the process of allocating treatments to experimental units/subjects.
It allows us to control experimental err
UNIVERSITY OF CAPE TOWN
DEPARTMENT OF STATISTICAL SCIENCES
STA2005S
NOVEMBER 2007 EXAMINATION
INTERNAL EXAMINERS: Mr A Clark, Dr B Erni
INTERNAL ASSESSOR: A. Prof. J Juritz
EXTERNAL EXAMINER: Dr C Lombard
AVAILABLE MARKS: 100
MAXIMUM MARKS: 100
TIME ALLOW
UNIVERSITY OF CAPE TOWN
DEPARTMENT OF STATISTICAL SCIENCES
STA2005S
NOVEMBER 2010 EXAMINATION
INTERNAL EXAMINERS: Dr K. Leask, Dr B. Erni, Dr J. Nyirenda
EXTERNAL EXAMINER: Prof. N. le Roux
AVAILABLE MARKS: 101
MAXIMUM MARKS: 100
PAGES: 8 + 6 TABLES
TIME
UNIVERSITY OF CAPE TOWN
DEPARTMENT OF STATISTICAL SCIENCES
STA2005S
NOVEMBER 2008 EXAMINATION
INTERNAL EXAMINERS: Mr A Clark, Dr B Erni
INTERNAL ASSESSOR: Dr F Little
EXTERNAL EXAMINER: Dr C Lombard
AVAILABLE MARKS: 100
MAXIMUM MARKS: 100
TIME ALLOWED: 3
UNIVERSITY OF CAPE TOWN
DEPARTMENT OF STATISTICAL SCIENCES
STA2005S
NOVEMBER 2010 EXAMINATION
INTERNAL EXAMINERS: Dr K Leask, Dr B Erni, Dr J Nyirenda
EXTERNAL EXAMINER: Prof N Le Roux
PAGES: 8 + 6 TABLES
AVAILABLE MARKS: 100
MAXIMUM MARKS: 100
TIME ALLOW
Chapter 4
Linear regression and
ANOVA
Regression and analysis of variance (ANOVA) form the basis of many investigations. In this chapter we describe how to undertake many common tasks
in linear regression (broadly dened), while Chapter 5 discusses many ge
i
i
book 2009/6/8 14:41 page 93 #113
i
i
Chapter 3
Linear regression and ANOVA
Regression and analysis of variance form the basis of many investigations. In this chapter
we describe how to undertake many common tasks in linear regression (broadly dened),
P YW SQP F
`aW`XVUTR$IHGE
D @' 7 5 ' )' % #!
CBA29864321$0(&$"
$B
I6 C1QI!$
' x & cfw_ " ' cfw_ V V V b 1
#B 70!)l@alWIH"%0@'7@10%6BW6CPC1#
a cfw_ cfw_ ')
!$!H"!64 q #B 70!l@afx
) p4 ')
6A4CV0!l@aw
cfw_ V 9 ' "' ' V ' 1 & T '4 9) V )4" p'
nW@0' ` 0
Quadratic forms
Definitionofquadraticforms
Let cfw_x1, x2 , ., xn be n (non random) variables. A quadratic form Q is, by
definition, an expression such as :
Q=
ij
aij xi xj
where the aij (the coefficients of the form) are real numbers.
So a quadratic form
Quadratic forms
Definitionofquadraticforms
Let cfw_x1, x2 , ., xn be n (non random) variables. A quadratic form Q is, by
definition, an expression such as :
Q=
ij
aij xi xj
where the aij (the coefficients of the form) are real numbers.
So a quadratic form
SOME THEOREMS ON QUADRATIC FORMS AND NORMAL VARIABLES
1. T HE M ULTIVARIATE N ORMAL D ISTRIBUTION
The n 1 vector of random variables, y , is said to be distributed as a multivariate normal
with mean vector and variance covariance matrix (denoted y N (, )
NOTES ON THE
R-PRACS
&
ED-2
R-code
Hi guys, here are some of the notes I promised:
So what does the rep function do, lets look at its action
Firstly
you see, the : fuction automatically creates a column vector of ascending or
descending numbers(inclusive
Page 1
Chapter 12
Multivariate normal distributions
The multivariate normal is the most useful, and most studied, of the standard joint distributions in probability. A huge body of statistical theory depends on the properties of families of random variabl
DISTRIBUTION OF LINEAR TRANSFORMATIONS AND QUADRATIC FORMS
STEPHEN D. KACHMAN
1. Introduction Statistics arising out of the analysis of linear models typically take on one of four forms: Linear Transformations (Ay), Quadratic Forms (y Qy), and Ratios of (
Nonlinear Dynamics, Psychology, and Life Sciences, Vol. 8, No. 3, July, 2004. 2004 Society for Chaos Theory in Psychology & Life Sciences
Dynamical Models of Love
J. C. Sprott1, University of Wisconsin, Madison Abstract. Following a suggestion of Strogatz
CONTAMINATED SITE STATISTICAL APPLICATIONS GUIDANCE DOCUMENT NO. 5 12-5
CONTAMINATED SITES STATISTICAL APPLICATIONS GUIDANCE DOCUMENT NO.
NONPARAMETRIC METHODS
A guide for data analysts and interpreters on statistical
methods that do not require a distrib
Extra Examples for Experimental Design, STA2005S
1. To guard against the unexpected, as many or more patients should be assigned
to the control regiment as are assigned to the experimental one. This sounds
expensive and is. But things happen. You get the
Improved Learning in a Large-Enrollment Physics Class
Louis Deslauriers, et al.
Science 332, 862 (2011);
DOI: 10.1126/science.1201783
This copy is for your personal, non-commercial use only.
If you wish to distribute this article to others, you can order