0% found this document useful (0 votes)
3 views13 pages

Chapter 6 Variable Screening Methods

Chapter 6 discusses variable screening methods, specifically stepwise regression and all-possible-regressions selection procedures, which help simplify complex models by identifying significant predictors. Stepwise regression involves iterative testing of independent variables to determine their contribution to the model, while all-possible-regressions focuses on finding the best subset of variables based on criteria like R-squared and mean square error. The chapter also highlights caveats of these methods, including the risk of Type I and II errors and the potential for nonsensical model selection.

Uploaded by

q4vsj7qj5r
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
3 views13 pages

Chapter 6 Variable Screening Methods

Chapter 6 discusses variable screening methods, specifically stepwise regression and all-possible-regressions selection procedures, which help simplify complex models by identifying significant predictors. Stepwise regression involves iterative testing of independent variables to determine their contribution to the model, while all-possible-regressions focuses on finding the best subset of variables based on criteria like R-squared and mean square error. The chapter also highlights caveats of these methods, including the risk of Type I and II errors and the potential for nonsensical model selection.

Uploaded by

q4vsj7qj5r
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Variable Screening Methods

Chapter 6

Chapter 06 1

Contents

 Introduction: Why Use a Variable Screening


Method?
 Step Regression
 All-Possible-Regressions Selection
Procedure
 Caveats

Chapter 06 2

1
6.1 Introduction: Why Use a Variable
Screening Method?
 The model with numerous multivariable
interactions and squared terms is too
complex to be of use in practice.
 Variable screening procedures
 Stepwise regression
 All-possible-regressions-selection

Chapter 06 3

6.2 Stepwise Regression

 To run a stepwise regression, the user first


identifies the dependent variable (response) y,
and the set of potentially important
independent variables, x1 , x2 , , xk , where k is
generally large.

Chapter 06 4

2
6.2 Stepwise Regression

 Step 1.
 The software program fits all possible one-
variable models to the data,
E  y    0  1 xi

where xi is the ith independent variable,


i  1, 2, , k.

Chapter 06 5

6.2 Stepwise Regression

 For each model, test

H 0 : 1  0
H a : 1  0

Using the t-test (or the equivalent F-test) for a


single  parameter.
 The independent variable that produces the

largest (absolute) t-value is declared the best one-


*
variable predictor of y . Call this independent
variable x1 .

Chapter 06 6

3
6.2 Stepwise Regression

 Step 2.
 The stepwise program now begins to search
through the remaining (k-1) independent variables
for the best two-variable model of the form
E  y    0  1 x1   2 xi

 The t-values for the test H 0 :  2  0 are computed


for each of the (k-1) models, and the variable
having the largest t is retained. Call this
variable x2 .

Chapter 06 7

6.2 Stepwise Regression

 Before proceeding to Step 3, the stepwise routine


will go back and check the t-value of ̂1 after ˆ2 x2
has been added to the model.
 If the t-value has become insignificant at some
specified  level (say   0.05 ), the variable x1 is
removed and a search is made for the
independent variable with a  parameter that will
yield the most significant t-value in the presence
of ˆ2 x2 .

Chapter 06 8

4
6.2 Stepwise Regression

 Step 3.
 The stepwise regression procedure now checks
for a third independent variable to include in the
model with x1 and x2 .

E  y    0  1 x1   2 x2  3 xi

 The criterion is again to include the independent


variable with the largest t-value. Call this best third
variable x3 .

Chapter 06 9

6.2 Stepwise Regression

 The programs now recheck the t-values


corresponding to the x1 and x2 coefficients,
replacing the variables that yield nonsignificant t-
values.
 This procedure is continued until no further
independent variables can be found that yield
significant t-values (at the specified  level) in the
presence of the variables already in the model.

Chapter 06 10

5
Example 6.1

Chapter 06 11

Figure 6.1 StatTools stepwise regression


results for executive salaries
Stepwise Regression for Y Multiple Adjusted StErr of
R-Square
Summary R R-Square Estimate
0.9595 0.9206 0.9164 0.075117921

Degrees of Sum of Mean of


F-Ratio p-Value
ANOVA Table Freedom Squares Squares
Explained 5 6.1523 1.2305 218.0606 < 0.0001
Unexplained 94 0.5304 0.0056

Standard Confidence Interval 95%


Coefficient t-Value p-Value
Regression Table Error Lower Upper
Constant 9.9619 0.1011 98.5777 < 0.0001 9.7613 10.1626
X1 0.0273 0.0010 26.5005 < 0.0001 0.0252 0.0293
X3 0.2247 0.0164 13.7424 < 0.0001 0.1922 0.2572
X4 0.0005 0.0000 11.0643 < 0.0001 0.0004 0.0006
X2 0.0291 0.0033 8.7188 < 0.0001 0.0225 0.0357
X5 0.0020 0.0005 3.9469 0.0002 0.0010 0.0029

Chapter 06 12

6
6.2 Stepwise Regression

 Forward selection
 Nearly identical to the stepwise procedure.
 The only difference is that the forward selection
technique provides no option for rechecking the t-
values corresponding to the x’s that have entered
the model in an earlier step.

Chapter 06 13

6.2 Stepwise Regression

 Backward elimination
 Initially fits a model containing terms for all
potential independent variables.
 The variable with the smallest t (or F) statistics is
identified and dropped from the model if the t-
value is less than some specified critical value.
 This process is repeated until no further
nonsignificant independent variables can be found.

Chapter 06 14

7
Figure 6.2 StatTools backward stepwise
regression for executive salaries
Backward Stepwise Regression for Y Multiple Adjusted StErr of
R-Square
Summary R R-Square Estimate
0.9595 0.9206 0.9164 0.075117921

Degrees of Sum of Mean of


F-Ratio p-Value
ANOVA Table Freedom Squares Squares
Explained 5 6.1523 1.2305 218.0606 < 0.0001
Unexplained 94 0.5304 0.0056

Standard Confidence Interval 95%


Coefficient t-Value p-Value
Regression Table Error Lower Upper
Constant 9.9619 0.1011 98.5777 < 0.0001 9.7613 10.1626
X1 0.0273 0.0010 26.5005 < 0.0001 0.0252 0.0293
X2 0.0291 0.0033 8.7188 < 0.0001 0.0225 0.0357
X3 0.2247 0.0164 13.7424 < 0.0001 0.1922 0.2572
X4 0.0005 0.0000 11.0643 < 0.0001 0.0004 0.0006
X5 0.0020 0.0005 3.9469 0.0002 0.0010 0.0029

Chapter 06 15

6.3 All-Possible-Regressions Selection


Procedure
 R 2 Criterion
SSE
R2  1 
SS Total 

 The objective of the R 2 criterion is to find a subset


model (i.e., a model containing a subset of the k
independent variables) so that adding more
variables to the model will yield only small
increases in R 2 .

Chapter 06 16

8
6.3 All-Possible-Regressions Selection
Procedure
2
 Adjusted R or MSE Criterion

 MSE 
Ra2  1   n  1  
 SS Total  

 Ra2 increases only if MSE decreases.


 An equivalent procedure is to search for the
model with the minimum, or near minimum, MSE.

Chapter 06 17

6.3 All-Possible-Regressions Selection


Procedure
 Cp Criterion
 Total Mean Square Error (TMSE)
 n 2

n n


TMSE  E   yˆi  E  yi       E  yˆi   E  yi    Var  yˆ 
2
i
 i 1  i 1 i 1

 The objective is to compare the TMSE for the


subset regression model with  , the variance of
2

the random error for the true model, using the


ratio
TMSE

2

Chapter 06 18

9
6.3 All-Possible-Regressions Selection
Procedure
 A good estimator of the ratio  is given by

SSE p
Cp   2  p  1  n
MSEk

 The C p criterion selects as the best model the


subset model with
 A small value of C p (i.e., a small total mean square error)
 A value of C p near p+1, a property that indicates that
slight or no bias exists in the subset regression model.

Chapter 06 19

6.3 All-Possible-Regressions Selection


Procedure
 PRESS Criterion
n


2
PRESS   yi  yˆ 
 i  
i 1

 Since small differences yi  yˆ i  indicates that the


model is predicting well, we desire a model with a
small PRESS.

Chapter 06 20

10
Figure 6.3 MINITAB all-possible-regressions
selection results for executive salaries

Chapter 06 21

Example 6.2

Chapter 06 22

11
Figure 6.4 MINITAB plots of all-possible-
regressions selection criteria for Example 6.2

Chapter 06 23

6.4 Caveats

 Be wary of using the stepwise (or best subset)


model as the final model for predicting y for
several reasons.
 First, the probability of making at least one Type I
error or at least one Type II error is often quite
high.
 Second, analysts typically do not include higher-
order terms or interactions in the list of potential
predictors for stepwise regression.

Chapter 06 24

12
6.4 Caveats

 Third, even if the analyst includes some higher-


order terms and interactions as potential
predictors, the stepwise and best subsets
procedures will more than likely select a
nonsensical model.
 Finally, make sure you do not abandon your
common sense or intuition when applying
stepwise regression.

Chapter 06 25

13

You might also like