STAT 410
Homework #2
Summer 2017
A. Stepanov
(due Wednesday, June 28, by 3:00 p.m.)
Please include your name ( with your last name underlined )
and your NetID at the top of the first page.
No credit will be given without supporting work.
If the answer is
STAT 410
Homework #4
Summer 2017
A. Stepanov
(due Wednesday, July 12, by 3:00 p.m.)
Please include your name ( with your last name underlined )
and your NetID at the top of the first page.
No credit will be given without supporting work.
1.
Suppose ( U, V
STAT 410
Summer 2017
A. Stepanov
Homework #5
(due Wednesday, July 19, by 3:00 p.m.)
Please include your name ( with your last name underlined )
and your NetID at the top of the first page.
No credit will be given without supporting work.
1.
Let X 1 , X 2
STAT 410
1.
Summer 2017
A. Stepanov
Homework #1
Grades on the last STAT 410 exam were not very good*. Graphed, their distribution
had a shape similar to the p.d.f.
1
,
x 25 ln 5
fX( x) =
a)
Hint:
Should be F X ( 0 ) = 0, F X ( 100 ) = 1.
x
0
=
x
1
1
du =
STAT 410
Homework #3
Summer 2017
A. Stepanov
(due Wednesday, July 5, by 3:00 p.m.)
Please include your name ( with your last name underlined )
and your NetID at the top of the first page.
No credit will be given without supporting work.
If the answer is a
Proc univariate
Gives us basic descriptive statistics, quantiles, extreme observations, and tests of location
with the null hypothesis being that the true population location (the mean or median) is 0
Statements can be added to get other descriptive st
Analysis of Variance with Unbalanced Data
When analyzing a balanced data set, we can use proc anova
With balanced data, the effects are orthogonal and there is unique partitioning of the
sums of squares
When data are not balanced, we no longer have or
Analysis of Variance (ANOVA) Model
We have the following situation
A continuous response assumed to have iid normally distributed errors
One or more nominal categorical predictor variables
No continuous predictor variables
We will be assuming normal
Proc freq
Procedure can be used to create and analyze contingency tables
Data can be given as raw data or as counts via the weight statement
Measures of Tests of Association
H0: we assume no relationship between the categorical variables. The margina
/* Solution code for Homework 1 in Stat 448 section A1 at
University of Illinois, Summer 2017 */
ods html close;
options nodate nonumber;
title;
ods rtf file = 'C:\Stat 448\HW1_Su17_Solution.rtf' nogtitle startpage=no;
ods noproctitle;
/* The raw data in
/* Solution code for Homework 2 in Stat 448 section A1 at
University of Illinois, Summer 2017 */
ods html close;
options nodate nonumber;
title;
ods rtf file='C:\Stat 448\HW2_Su17_Solution.rtf' nogtitle startpage=no;
ods noproctitle;
/* The raw data files
/* Solution code for Homework 3 in Stat 448 section A1 at
University of Illinois, Summer 2017 */
ods html close;
options nodate nonumber;
title;
ods rtf file='C:\Stat 448\HW3_Su17_Solution.rtf' nogtitle startpage=no;
ods noproctitle;
/* The raw data in ab
Notice how the slopes for both NBA players and Sumo wrestlers are now positive. This Is an example of Simpson' 5 Paradox, extreme confounding that makes the overall effect the opposite of what It rally Is.
erse the regraslon equatons given In the output f
STAT 430 Applied Bayesian Analysis Fall 2015
Homework 2
Please submit your assignment on paper. Make sure your answers are completely justified and
clear enough to read! When you use a computer, please include your code and output.
1. [5 pts] Cowles, Prob
STAT 430
1GR, 1UG
Spring 2017
A. Stepanov
Examples for 01/26/2017
Let C be an irreducible closed set of recurrent states.
C ( x ) = P x ( T C < ),
x S.
( probability that the Markov chain that starts in x would be absorbed into C )
C ( x ) = 1,
x C.
C
STAT 430
1GR, 1UG
1.
P =
Spring 2017
A. Stepanov
Practice Problems 3
Consider the Markov chain on cfw_ 0, 1, 2, 3 having transition matrix
0
1
2
3
0
0.1
0.2
0.2
0.5
1
0.3
0.4
0
0.3
2
0.4
0
0.4
0.2
3
0.3
0
0.2
0.5
a)
If the chain starts in state 2, find t
STAT 430
1GR, 1UG
1.
Spring 2017
A. Stepanov
Practice Problems 1
A medical researcher is studying the risk of heart attack in men. She first divides men
into three weight categories: thin, normal, and overweight. By studying the male
ancestors, sons, and
STAT 430
1GR, 1UG
Spring 2017
A. Stepanov
Examples for 01/31/2017
Suppose we have m + k states m absorbing states and k transient states.
Rearrange the states so that the first m states are absorbing and the last k states are transient.
Then
m
k
m
I mm
O
STAT 430
1GR, 1UG
1.
Spring 2017
A. Stepanov
Examples for 02/28/2017
Let T 1 , T 2 , , T k be independent Exponential random variables.
1
Suppose E ( T i ) =
, i = 1, 2, , k.
i
t
That is, f T ( t ) = i e i , t > 0, i = 1, 2, , k.
i
Denote T min = min ( T
STAT 430
Spring 2017
Version B
Page
Earned
Name
Total
/70
ANSWERS
NetID
Exam 1
Be sure to show all your work; your
partial credit might depend on it.
Put your nal answers at the end of
your work, and mark them clearly.
No credit will be
STAT 430
Spring 2017
Version A
Name
Total
/70
ANSWERS
NetID
Exam 1
Be sure to Show all your work; your
partial credit might depend on it.
Put your nal answers at the end of
your work, and mark them clearly.
No credit will be gi
STAT 430
1GR, 1UG
Spring 2017
A. Stepanov
Homework #3
(due Friday, March 3, by 3:00 p.m.)
Please include your name ( with your last name underlined ),
and your NetID at the top of the first page.
No credit will be given without supporting work.
1.
Let 0 <
/*STAT 448 Fall 2016
/*data for exercises 1 and 2*/
data diamonds;
infile 'C:\Stat 448 fall 2016\homework\HW3\diamonds.txt';
input carat 1-4 color $ 6 clarity $ 8-11 certificate $ 13-15 price 17-21;
format carat_cat $30.;
if carat<=0.50 then carat_cat='1-
Homework 2
Due: Friday September 23 at noon
See general homework tips and submit your files via the course website.
In the first exercise, we will investigate the relationship between peanut allergy and early consumption
of peanuts. For exercise 1 use the