Académique Documents
Professionnel Documents
Culture Documents
Statistics
Chapter 6
BUILDING EMPIRICAL MODELS
Tanasanee Phienthrakul
2
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
3
Statistics
Empirical Models
Many problems in engineering and science involve exploring the
relationships between two or more variables.
Regression analysis is a statistical technique that is very useful for
these types of problems.
For example, in a chemical process, suppose that the yield of the
product is related to the process-operating temperature.
Regression analysis can be used to build a model to predict yield at
a given temperature level.
MAHIDOL
UNIVERSITY
Wisdom of the Land
4
Statistics
Empirical Models
MAHIDOL
UNIVERSITY
Wisdom of the Land
5
Statistics
Empirical Models
Empirical Models
Based on the scatter diagram, it is probably reasonable to assume
that the mean of the random variable Y is related to x by the
following straight-line relationship:
where the slope and intercept of the line are called regression
coefficients.
The simple linear regression model is given by
Empirical Models
We think of the regression model as an empirical model.
Suppose that the mean and variance of are 0 and 2, respectively,
then
MAHIDOL
UNIVERSITY
Wisdom of the Land
8
Statistics
Empirical Models
The true regression model is a line of mean values:
Empirical Models
The distribution of Y for a given value of x for the oxygen purity-hydrocarbon data.
MAHIDOL
UNIVERSITY
Wisdom of the Land
10
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
11
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
12
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
15
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
16
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
17
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
18
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
19
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
20
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
21
Statistics
It can be shown that the expected value of the error sum of squares
is E(SSE) = (n 2)2.
MAHIDOL
UNIVERSITY
Wisdom of the Land
23
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
24
Statistics
is the point estimator of the new or future value of the response, Y0.
MAHIDOL
UNIVERSITY
Wisdom of the Land
25
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
26
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
28
Statistics
Correlation
Finding the relationship between two quantitative variables without
being able to infer causal relationships
MAHIDOL
UNIVERSITY
Wisdom of the Land
29
Statistics
Positive relationship
MAHIDOL
UNIVERSITY
Wisdom of the Land
30
Statistics
Positive relationship
18
16
14
12
Height in CM
10
0
0 10 20 30 40 50 60 70 80 90
Age in Weeks
MAHIDOL
UNIVERSITY
Wisdom of the Land
31
Statistics
Negative relationship
Reliability
Age of Car
MAHIDOL
UNIVERSITY
Wisdom of the Land
32
Statistics
No Relationship
MAHIDOL
UNIVERSITY
Wisdom of the Land
33
Statistics
Correlation Coefficient
Statistic showing the degree of relation between two variables
MAHIDOL
UNIVERSITY
Wisdom of the Land
34
Statistics
If the sign is +ve this means the relation is direct (an increase in one
variable is associated with an increase in the other variable and a
decrease in one variable is associated with a decrease in the other
variable).
While if the sign is -ve this means an inverse or indirect relationship
(which means an increase in one variable is associated with a
decrease in the other).
MAHIDOL
UNIVERSITY
Wisdom of the Land
35
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
36
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
37
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
38
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
39
Statistics
For example, suppose that the effective life of a cutting tool depends
on the cutting speed and the tool angle. A possible multiple
regression model could be
(a) The regression plane for the model E(Y) = 50 + 10x1 + 7x2.
(b) The contour plot
MAHIDOL
UNIVERSITY
Wisdom of the Land
41
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
43
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
44
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
45
Statistics
The solution to the normal Equations are the least squares estimators of the
regression coefficients.
MAHIDOL
UNIVERSITY
Wisdom of the Land
46
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
47
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
49
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
50
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
51
Statistics
where
MAHIDOL
UNIVERSITY
Wisdom of the Land
52
Statistics
Matrix Approach
We wish to find the vector of least squares estimators that
minimizes:
MAHIDOL
UNIVERSITY
Wisdom of the Land
53
Statistics
Matrix Approach
MAHIDOL
UNIVERSITY
Wisdom of the Land
54
Statistics
Example
MAHIDOL
UNIVERSITY
Wisdom of the Land
55
Statistics
Example
MAHIDOL
UNIVERSITY
Wisdom of the Land
56
Statistics
Example
MAHIDOL
UNIVERSITY
Wisdom of the Land
57
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
58
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
59
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
60
Statistics
MAHIDOL
UNIVERSITY
Wisdom of the Land
61
Statistics
Categorical Regressors
Many problems may involve qualitative or categorical variables.
The usual method for the different levels of a qualitative variable is to use
indicator variables.