Stats331
Introduction to Regression Models
Chapter 1
Chapter objectives
•
Model Building.
•
Data Collection.
•
Uses of Regression.
2
Chapter 1 Introduction to
Regression Models
30/04/2017
Model Building
•
Medical researchers use mouse physiology as a model for
human physiology.
•
The hope is the response of mouse to a specific drug will
suggest what response to expect in human.
30/04/2017
Chapter 1 Introduction to
Regression Models
3
•
An engineer constructs a scale model of a proposed building.
•
The scale model may be used to help route the plumbing, but
may give no information about the acoustics of rooms inside the
building.
30/04/2017
Chapter 1 Introduction to
Regression Models
4
•
A good model captures enough important features of the object
that it represents to be useful for a specific purpose.
30/04/2017
Chapter 1 Introduction to
Regression Models
5
6
What is Regression Modeling?
Chapter 1 Introduction to
Regression Models
6
30/04/2017
•
Regression modeling is an activity (a collection of statistical
techniques) that leads to a
mathematical description
(model or
law) of a process in terms of a set of associated variables.
•
The values of one variable (response variable) frequently
depend on the levels of several others (explanatory variables).
30/04/2017
Chapter 1 Introduction to
Regression Models
7
Example
•
The yield of a certain production process may depend on
temperature, pressure, catalyst, and the rate of throughput.
•
The number of defective seals on toothpaste tubes may depend
on the temperature and the pressure of the sealing process.
30/04/2017
Chapter 1 Introduction to
Regression Models
8
•
The term regression was originally used in 1885 by Sir Francis
Galton in his analysis of the relationship between the heights
of children and parents.
30/04/2017
Chapter 1 Introduction to
Regression Models
9
Sir Galton was the first to apply the word regression to
biological and psychological data.
Specifically, Galton observed the heights of children versus
the heights of their parents.
He discovered that taller than average parents tended to
have children who were also taller than average,
but not as
tall as their parents.
Galton characterized this as regression toward mediocrity.
30/04/2017
10
Chapter 1 Introduction to
Regression Models
Mathematical Models
•
A deterministic model.
•
Statistical or probabilistic model.
30/04/2017
Chapter 1 Introduction to
Regression Models
11
Deterministic Model
Makes no allowance for statistical or measurement error, has no
variance nor uncertainty.
If we know the value of one variable, we can determine the value
of the other
exactly
.

Unit conversions (E.g., miles to kilometers, meter to cm)

Known scientific formulas (E.g. water volume and weight)
12
12
30/04/2017
Chapter 1 Introduction to
Regression Models
Example (1)
Chapter 1 Introduction to
Regression Models
13
y = temperature in
Fahrenheit
y =
32
+
1.8
x
x = temperature in Celsius
30/04/2017
This is an example of
deterministic relationship
(theorybased models).
Example
•