Looking Back
One-Sample tests
One-Factor Experiments:
Theory and Applications
_
= Tests for one factor at one level with data
from one population
n random samples (x1, x2, , xn) are drawn from a population.
H o : = 0
vs. H1: 0, > 0, or < 0
(T-tests)
H0:
IE 361 take-home exam 3
10
HaLee DuPree
Page 1 of
I Problem 1
A study was made by a retail merchant to determine the relation between weekly advertising
expenditures and sales. The following data were recorded:
Advising costs ($)
40
20
25
20
30
50
Sales (
IE 361 Quiz 6
Please write your name and class ID number in the upper right corner on the back
An inventory manager believes that his inventory levels follow a Poisson distribution. He
has recorded the inventory levels over 32 days and summarized the freq
Descriptive Statistics vs. Inferential Statistics
Population
ab
Lecture3
Sample
cd
b
ef gh i jk l m n
Inferential
Statistics
InferentialStatistics
(HypothesisTesting)
o p q rs t u v w
xy
gi
o
c
n
Descriptive
Statistics
ryu
z
Descriptive statistics to summ
Lecture2
NormalDistribution&Applications
MinitabApplications
SamplingDistributions
NormalDistribution&
Applications
Read the relevant chapters of the textbook.
Read the relevant chapters of the textbook.
1
A Normal Distribution
A normal distribution, a.k.
Learning Objectives
Use multiple regression techniques to
build empirical models to engineering
data.
Understand how the method of least
squares extends to fitting multiple
regression models.
Assess regression model adequacy.
Test hypotheses and const
Simple and Multiple Linear Regression Models
Simple Linear Regression
Regression
Regression analysis is used to investigate and model the
relationship between a response variable and one or
more predictors (or predictor variables).
Multiple Linear Regress
Expectations
After completing the lecture on descriptive statistics and
graphical summery, you should be able to:
Explain how decisions are often based on incomplete
information
Lecture1
DescriptiveStatistics&GraphicalSummary
Explain key definitions:
p
Lecture4
TestsforNormality
InferentialStatistics:Part2
(HypothesisTesting)
(Read the relevant chapters of the textbook)
Anderson-Darling test*
Ryan-Joiner (similar to Shapiro-Wilk) test
Kolmogorov-Smirnov test
Anderson-Darling tests for a normal distribut
Motivation
Parametric tests (which we have studied so far) are
based on the assumption that we are working with
random samples from normally distributed population(s).
Lecture5
Slight departures from normality are acceptable.
An advantage of a parametri