IOE 366 Winter 2016
Minitab Assignment 3 (15pts) SOLUTION
Problem Description:
Gross Domestic Product (GDP) measures the size of an economy. In this assignment, you will
model the GDP growth of China during 1978 2014. Using the given dataset
(Minitab3_Dat

IOE 366 Winter 2016
Minitab Assignment 2 (15pts)
DUE: Monday, February 1st by 1:30PM via CTools
Problem Description:
In this assignment, you will look at the relationship between the size (carats) of a diamond and
its price (Singapore dollars). Based on t

IOE 366 Fall 2015
Minitab Assignment 3 (10pts)
DUE: Thursday, October 8th by 3PM via CTools
Please save your submitted file name as IOE366Minitab3_uniqname
Problem Description:
Gross Domestic Product (GDP) measures the size of an economy. In this assignme

IOE 366 Winter 2007 Final Exam
True or False (5 Questions, 2 Points Each, 10 Points Total) Decide if the following statements are true or false. If the statement is false, identify how to change it to make the statement true. 1. In testing H 0. : 1

IOE 366 Fall 2012
Practice
Part 1. Multiple Choice and Fill-in the Blanks
1. In a single-factor ANOVA problem involving five populations or treatments, which of the following
statements is true about the alternative hypothesis?
A. All five treatment means

IOE 366 F2009 Final Exam Solution Part 1 (20 Points Total). True or False and Fill-in-the-Blank Questions(5 Questions, 2 Point Each, 10 Points Total) 1. The least squares regression line is obtained when the sum of the squared residuals is minimized. True

Topics
Model Significance test
R2, model utility test
Parameter significance test
5
Decomposition of variations
variation explained
by linear relationship
Total variation
of response
(SST, total sum of squares)
(SSR, regression sum of squares)
unexplained

Multiple Linear Regression
Ch. 13.3~13.4
1
Topics
Definition of multiple linear regression
Parameter estimations
2
Multiple Linear Regression
(MLR)
When we have k independent variables (explanatory
variables, regressors, covariates)
Predict a single res

Regression with Categorical
Variables
Ch. 13.4 and 13.5
1
Topics
Logistic regression (Ch. 13.5)
Regression with categorical predictors
(Ch. 13.4)
2
Revisiting Logistic regression
with one covariate
We studied the logistic regression with one
independent v

14
15
16
Example #1: Torque vs. Air pressure
(3) If the company wants to increase torque by 5 Nm, how
much would the company need to increase the air
pressure?
(4) How much torque would we expect when air pressure is
60? What is the error (residual) of ou

2
3
4
Inference #1
12.2 Estimating model parameters
5
Topics
Evaluation of the significance of the estimated
simple regression model
Sum of squares
coefficient of determination
Tests of model significance
6
Model significance
How can we evaluate the signi

Multiple Linear Regression
Ch. 13.4
4
Topics
Model Significance test
R2, model utility test
Parameter significance test
5
Decomposition of variations
variation explained
by linear relationship
Total variation
of response
(SST, total sum of squares)
(SSR,

Inferences #2
12.3 Inferences on the slope parameter
1
2
3
4
5
Topics
Chapter 12.3
Distribution of 1 (= 1 ) (pp. 3-8)
Test and confidence interval of the slope
parameter (pp.9-17)
6
Inferences About 1 (=b1) and
0 (=b0)
Now, we are going to study the prop

Linear Statistical Models
IOE 366
Eunshin Byon, PhD
Assistant Professor
Industrial & Operations Engineering
0
Textbook
Probability and Statistics for Engineering
and the Sciences, 9th Edition Jay L.
Devore
Loose-leaf version is available at campus
booksto

IOE 366 Winter 2015
Lab 1 Assignment (10pts)
DUE: Monday, January 26th by 9AM via CTools
Please save your submitted file name as IOE366Lab1_uniqname
Problem Description:
After watching his Michigan Mens Basketball Team fall short against the Purdue Boiler

Inference #1
12.2 Estimating model parameters
1
Topics
Evaluation of the significance of the estimated
simple regression model
Sum of squares
coefficient of determination
Tests of model significance
2
Model significance
How can we evaluate the significanc

Simple Linear Regression
Chapters 12.1~12.2
1
Topics
Simple Linear Regression (Ch. 12.1)
Estimating Model Parameters (Ch. 12.2)
2
Example 1
Automobile Assembly Compare Air Pressure and Torque
Q. Does one variable (air
pressure) provide information
on the

Linear Statistical Models
IOE 366
Eunshin Byon, PhD
Assistant Professor
Industrial & Operations Engineering
0
Images taken from McKinsey, IBM, Forbes and New York Times websites
1
Textbook
Probability and Statistics for Engineering
and the Sciences, Enhan

Example 1
Consider a bank that is run by two clerks. Suppose that when
Elizabeth enters the system he discovers that Winnie is being
served by Clerk 1 and Dr. Lavieri is being served by Clerk 2.
Suppose also that Elizabeths service will begin as soon as e

Real Applications of Markov Decision Processes
Author(s): Douglas J. White
Reviewed work(s):
Source: Interfaces, Vol. 15, No. 6 (Nov. - Dec., 1985), pp. 73-83
Published by: INFORMS
Stable URL: http:/www.jstor.org/stable/25060766 .
Accessed: 12/04/2012 09:

Linear Statistical Models
IOE 366
Eunshin Byon, PhD
Assistant Professor
Industrial & Operations Engineering
1
Images taken from McKinsey, IBM, Forbes and New York Times websites
2
Textbook
Probability and Statistics for
Engineering and the Sciences,
Enhan

Three major approaches
1. Backward Elimination: Start with a complicated
model and simplify.
2. Forward Selection: Start with a simple model
and build.
3. Stepwise Selection: Combines the backward
elimination and forward selection.
8
Backward Elimination

Nonlinear Regression
Ch. 13.2
1
Topics
Regression with transformed variables
Logistic Regression
2
Regression with transformed
variables
Is the following model a linear regression model?
2
= 0 + 1 +
Any model that is linear in the regression
coefficie

Inferences #2
12.3 Inferences on the slope parameter
1
2
3
Topics
Chapter 12.3
Distribution of 1 (= 1 ) (pp. 3-8)
Test and confidence interval of the slope
parameter (pp.9-17)
6
Inferences About 1 (=b1) and
0 (=b0)
Now, we are going to study the propertie

2
3
4
Example #1: Torque vs Air
Pressure
R e g r e s s io n A n a l y s is : T o r q u e ( N m ) v e r s u s A ir P r e s s u r e (p s i )
The regression equation is
Torque (Nm) = - 14.2 + 1.59 Air Pressure (psi)
Predictor
Constant
Air Pres
S = 2.680
Coef

Topics
Chapter 12.4
Confidence interval for mean response and
prediction interval for future observation
Chapter 12.5
Correlation
2
3
4
Mean Response at x*
Fitted line =0 + 1 is a random variable
and follows t-distribution.
=
0 +1 0 +1
+
0
where
0 +1

3
4
Confidence Interval for mean
response
(1- )100% confidence interval of mean response
at x*:
0 + 1 , 2 0+ 1
2
= 0+1 , 2
2
1
2
+
10
Prediction of Individual Y|x*
Now, we want to obtain an interval for the
value of future observation at .
11
Predict

Inferences #2
12.3 Inferences on the slope parameter
1
2
3
Inferences About 1
0
)
) and
Now, we are going to study the properties of
the least square estimates 1 and 0.
Question 1: Are 1 and 0 random variables?
(A) True
(B) False
Question 2: Are 1 and 0 r

Example 1: Oil production
Fitted line with transformed variables
Analysis of Variance
Source
DF SS
MS
F
P
Regression 1 16.8991 16.8991 1005.24 0.00
Error
29 0.4875 0.0168
Total
30 17.3866
11

Variable Selection
Ch. 13.5
1
Topics
Variable selection by 2
Backward Elimination
Forward Selection
Stepwise Selection
2
What is a Variable selection?
In practice, many predictors are available; some
of them are influential while others are not.
Often we