STAT 8200 Final Exam Sample
SHOW ALL WORK!
Name:
1. Suppose that we wish to study the eects of three factors on cotton yields: nitrogen
added, planting depth, and planting date. The nitrogen and depth factors have
two levels each, and the date factor has
STAT 8200 Design and Analysis of Experiments
Lecture Notes
Basics of Experimental Design
Terminology
Response (Outcome, Dependent) Variable: (y) The variable whos
distribution is of interest.
Could be quantitative (size, weight, etc.) or qualitative (pas
These last two results can be demonstrated as follows:
(i y )2
y
SSA = n
i
since
yi = + ai + ei
and
y = + a + e ,
it follows that
(ai + ei a e )2
SSA = n
i
(i )2
=n
where i = ai + ei , = a + e .
i
iid
2
Notice that 1 , . . . , a N (0, a + 2 /n). Therefore
STAT 8200 Design and Analysis of Experiments
Lecture Notes
Basics of Experimental Design
Terminology
Response (Outcome, Dependent) Variable: (y ) The variable whos
distribution is of interest.
Could be quantitative (size, weight, etc.) or qualitative (pa
rdc7
v 6 $
DriD@PSID%op7rS%5V'do27r5rFidy0diPfH
u y y e y p f y y e x z x y u
8PkgtkPHtPA
t
t
t
8
t
A
8
t
t
t
t
t
t
A
A
8
t
t
ttq
tD
y pxy m y
A8osPlv
t
q
t
q
t
q
t
q
ry yv
u y
xz e
w
z e j e
Dtocfw_
qAo8~pcfw_PtPy7P82k2At%rP8PC2xPPklPt0pksx
x
STAT 8200 Design of Experiments for Research Workers
Lab 8 Due: Friday, Dec. 3
Example:
An experiment is designed to study pigment dispersion in paint. Four dierent
methods of mixing a particular pigment are studied. The procedure consists of preparing
a
S TAT 8 200
- ~ D esign o f E xperiments f or R esearch W orkers
L ab 7 - ~_'Fttesday,Dwmbel"30
I
:;:> I
Example:
: '"
S even different h ardwood c oncentrations a re b eing s tudied t o d etermine t heir effect
o n t he p aper p roduced. However, t he p
STAT 8200 Design of Experiments for Research Workers
Lab 7 Due: Tuesday, November 30
Example:
Seven dierent hardwood concentrations are being studied to determine their eect
on the paper produced. However, the pilot plant can only produce three runs each
S TAT 8 200 -
Design o f E xperiments f or R esearch W orkers
L ab 6 - &e: T h'M)"s~-4
so/v-hof"\
Example:
S uppose t hat in t he r edwing flaxseed example, t he e xperiment was c onducted i n t he s ame
way as described i n l ecture, w ith t he e xcepti
STAT 8200 Design of Experiments for Research Workers
Lab 6 Due: Thursday, Nov. 4
Example:
Suppose that in the redwing axseed example, the experiment was conducted in the same
way as described in lecture, with the exception that in each of the six plots pe
STAT 8200 Design of Experiments for Research Workers
Lab 5 Due: Friday, Oct. 22
This lab is intended to highlight several ideas in the analysis of two-way layouts:
1. For unbalanced data, there are three distinct types of sums of squares whose values
are
STAT 8200 Design of Experiments for Research Workers
Lab 4 Due: Tuesday, October 19
Example:
Nitrogen dioxide (NO2 ) is an automobile emission pollutant, but less is known
about its eects than other pollutants such as particulate matter. Several animal mo
STA 8200 Design of Experiments for Research Workers
Lab 3 Due Friday, October 1
Example:
As part of the production of a liquid medication, the producer, a large pharmaceutical
company, mixes batches of medication in large vats. To determine the degree to
STAT 8200 Design of Experiments for Research Workers
Homework 6 Due Tuesday, December 7
SHOW ALL WORK
Read Chs. 14 and 16 of our text (the book by Oehlert). In addition do the following
problems.
1. Do problem 14.4 on p.382 of our text. In answering this
*
Illustration of the analysis of a crossover study with PROC MIXED
The Mixed Procedure
Model Information
Data Set
Dependent Variable
Covariance Structure
Estimation Method
Residual Variance Method
Fixed Effects SE Method
Degrees of Freedom Method
WORK.MI
Analysis of a BIBD with PROC GLM - Intrablock Analysis
1
The GLM Procedure
Class Level Information
Class
Levels
Values
car
5
12345
add
5
12345
Number of Observations Read
Number of Observations Used
20
20
Analysis of a BIBD with PROC GLM - Intrablock Anal
final1.sas:
options ls=78;
data diet1;
infile 'diet1.dat';
input group $ animalno week bodywgt;
run;
proc glm data=diet1;
class group week animalno;
model bodywgt=group animalno(group) week group*week / ss3;
contrast 'Vit. E vs control' group 2 -1 -1 ;
co
S TAT 8 200 F inal E xam - December 5 , 2 013
S HOW A LL W ORK!
N a me: _
_,!l'-f-L-4,_.S"i._.W=eA.:._-4k~l~V'-
1. We wish t o s tudy t he effect of drought stress on height g rowth o f r ed m aple
seedlings. T he f actors o f i nterest are t he a mount o
STAT 8200 Midterm Exam II November 14, 2013
SHOW ALL WORK!
Name:
1. Suppose that a crop scientist wanted to study the effects of three factors on cotton
yields: nitrogen added, planting depth, and planting date. The nitrogen factor
has three levels; tw
S TAT 8 200- Lab 1 0
T he d ata collected from t he above design appear below a nd i n file steak.dat o n
t hg course web page.
Judge
(J1)
(J2)
(J3)
(J4)
(J5)
(J6)
(.17)
(J8)
cfw_.19)
7
5
6
6
4
4
5
6
4
Scores
886
766
856
757
542
663
566
548
466
J udge
Sco
Two-way ANOVA model and contrasts to analyze the paint on pavement example 1
The GLM Procedure
Class Level Information
Class
Levels
paint
4
1234
pavement
3
123
Number of Observations Read
Number of Observations Used
Values
36
36
Two-way ANOVA model and co