Quantitative Analysis for Management

Fourteenth Edition

Chapter 4
Regression Models

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Learning Objectives
After completing this chapter, students will be able to:

1 Identify variables, visualize them in a scatter diagram,

and use them in a regression model.
2. Develop simple linear regression equations from sample
datasets and interpret the slope and intercept.
3. Calculate the coefficient of determination and the
coefficient of correlation and interpret their meanings.
4. List the assumptions used in regression and use residual
plots to identify problems.
5. Interpret the F test in a linear regression model.

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Learning Objectives
After completing this chapter, students will be able to:
6 Use computer software for regression analysis.
7. Develop a multiple regression model and use it for
prediction purposes.
8 Use dummy variables to model categorical data.
9 Determine which variables should be included in a
multiple regression model.
10 Transform a nonlinear function into a linear one for use
in regression.
11 Understand and avoid mistakes commonly made in the
use of regression analysis.
Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Introduction
 Regression analysis—a very valuable tool for managers
 Understand the relationship between variables
 Predict the value of one variable based on another
variable
 Simple linear regression models have only two variables,
a dependent and an independent variable
 Multiple regression models have three or more variables,
one dependent variable, and two or more independent
variables

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Introduction
 The variable to be predicted is called the dependent
variable or response variable
 Value depends on the value of the independent
variable(s)
 Explanatory or predictor variable
 A scatter diagram or scatter plot is often used to
investigate the relationship between variables
 Independent variable is normally plotted on the X axis
 Dependent variable is normally plotted on the Y axis

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Simple Linear Regression
Regression models are used We estimate with sample data
to test relationships between and make predictions using
variables
Yˆ b0  b1 X
Y   0  1  
where:
where:
Yˆ  predicted Y
Y = dependent variable
X = independent variable
X = independent variable
b0  estimate of  0
B0  intercept
b1 estimate of 1
B1  slope of regression line
 random error

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Triple A Construction
Triple A Construction renovates old homes, and the dollar volume of
renovation work is dependent on the area payroll
Table 4.1 Triple A Construction Figure 4.1 Scatter Diagram of
Company Sales and Local Payroll Triple A Construction Company
Triple Local
Data
A’s Sales Payroll
($100,000s) ($100,000,000s)
6 3

8 4

9 6

5 4

4.5 2

9.5 5

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Triple A Construction
 Predict sales based on area payroll
Y  Sales X Area payroll
 The line Figure 4.1 minimizes the errors
Error = Actual value   (Predicted va lue)
e Y  Yˆ
 Regression analysis minimizes the sum of squared
errors
 Least-squares regression

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Triple A Construction
Formulas for simple linear regression, intercept and slope
Yˆ  b0  b1 X

X 
 X
 average mean  of X values
n

Y 
 Y
 average mean  of Y values
n

b1 
  X  X Y  Y 

 X  X 
2

b0 Y  b1 X

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Triple A Construction
Table 4.2 Regression Calculations for Triple A Construction

Y X  X - X 2 Left parenthesis X minus X bar right parenthesis squared

( X  X )(Y  Y )
Left parenthesis X minus X bar right parenthesis left parenthesis Y minus Y bar right parenthesis

6 3 (3  4)2 1Left parenthesis 3 minus 4 right parenthesis squared equals 1

(3  4)(6  7) 1
Left parenthesis 3 minus 4 right parenthesis left parenthesis 6 minus 7 right parenthesis equals 1

8 4 (4  4)2 0 Left parenthesis 4 minus 4 right parenthesis squared equals 0

(4  4)(8  7) 0Left parenthesis 4 minus 4 right parenthesis left parenthesis 8 minus 7 right parenthesis equals 0

9 6 (6  4)2 4Left parenthesis 6 minus 4 right parenthesis squared equals 4

(6  4)(9  7) 4Left parenthesis 6 minus 4 right parenthesis left parenthesis 9 minus 7 right parenthesis equals 4

5 4 (4  4)2 0 Left parenthesis 4 minus 4 right parenthesis squared equals 0

(4  4)(5  7) 0Left parenthesis 4 minus 4 right parenthesis left parenthesis 5 minus 7 right parenthesis equals 0

4.5 2 (2  4)2 4 Left parenthesis 2 minus 4 right parenthesis squared equals 4

(2  4)(4.5  7) 5
Left parenthesis 2 minus 4 right parenthesis left parenthesis 4.5 minus 7 right parenthesis equals 5

9.5 5 (5  4)2 1Left parenthesis 5 minus 4 right parenthesis squared equals 1

(5  4)(9.5  7) 2.5
Left parenthesis 5 minus 4 right parenthesis left parenthesis 9.5 minus 7 right parenthesis equals 2.5

Y  42
Summation Y equals 42. Y bar equals start fraction 42 over 6 end fraction equals 7
 X 24
Summation X equals 24. X bar equals start fraction 24 over 6 end fraction equals 4

(X  X )2 10
Summation left parenthesis X minus X bar right parenthesis squared equals 10

( X  X )(Y  Y ) 12.5
Summation left parenthesis X minus X bar right parenthesis left parenthesis Y minus Y bar right parenthesis equals 12.5

Y  42 / 6 7 X 24 / 6 4

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Triple A Construction
Regression calculations

X 
X 
24
4
6 6

b1 
  X  X Y  Y  12.5
 1.25
 X  X 
2
10

b0 Y  b1 X  7  1.25 4   2

Therefore Yˆ  2  1.25 X

What are Triple A’s sales next year if the payroll is $600
million?
Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Measuring the Fit of the Regression
Model
 Regression models can be developed for any variables
X and Y
 How helpful is the model in predicting Y?
 With average error, positive and negative errors cancel
each other out
 Three measures of variability
 SST – Total variability about the mean
 SSE – Variability about the regression line
 SSR – Total variability that is explained by the model

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Measuring the Fit of the Regression
Model

 
2
Sum of squares total SST =  Y  Y

 
2
Sum of squares error SSE =  e   Y  Yˆ 2

 
2
Sum of squares regression SSR =  Yˆ  Y

An important relationship SST  SSR  SSE

What are the SST, SSE, and SSR for Triple A
Construction?

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Measuring the Fit of the Regression
Model
Table 4.3 Sum of Squares for Triple A Construction
Y X Y - Y 2 Left parenthesis Y minus Y bar right parenthesis squared

Yˆ
Y cap

Y - Yˆ 2 Left parenthesis Y minus Y cap right parenthesis squared

Yˆ - Y 2 Left parenthesis Y cap minus Y bar right parenthesis squared

6 3 (6  7)2 1 Left parenthesis 6 minus 7 right parenthesis squared equals 1

2  1.25(3) 5.75
2 plus 1.25 left parenthesis 3 right parenthesis equals 5.75

0.0625 1.563

8 4 (8  7)2 1 Left parenthesis 8 minus 7 right parenthesis squared equals 1

2  1.25(4) 7.00
2 plus 1.25 left parenthesis 4 right parenthesis equals 7.00

1 0

9 6 (9  7)2 4 Left parenthesis 9 minus 7 right parenthesis squared equals 4

2  1.25(6) 9.50
2 plus 1.25 left parenthesis 6 right parenthesis equals 9.50

0.25 6.25

5 4 (5  7)2 4 Left parenthesis 5 minus 7 right parenthesis squared equals 4

2  1.25(4) 7.00
2 plus 1.25 left parenthesis 4 right parenthesis equals 7.00

4 0

4.5 2 (4.5  7)2 6.25 Left parenthesis 4.5 minus 7 right parenthesis squared equals 6.25

2 +1.25(2) 4.50
2 plus 1.25 left parenthesis 2 right parenthesis equals 4.50

0 6.25

9.5 5 (9.5  7)2 6.25 left parenthesis 9.5 minus 7 right parenthesis squared equals 6.25

2  1.25(5) 8.25
2 plus 1.25 left parenthesis 5 right parenthesis equals 8.25

1.5625 1.563

Y 7
Y bar equals 7 blank
 (Y  Y ) 2
22.5
Summation left parenthesis Y minus Y bar right parenthesis squared equals 22.5. S S T equals 22.5. blank
(Y  Yˆ )2 6.875
Summation left parenthesis Y minus Y cap right parenthesis squared equals 6.875. S S T equals 6.875.
 (Yˆ  Y ) 2
15.625
Summation left parenthesis Y cap minus Y bar right parenthesis squared equals 15.625. S S R equals 15.625.

SST 22.5 SSE 6.875 SSR 15.625

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Measuring the Fit of the Regression
Model
Figure 4.2 Deviations from the Regression Line and from
the Mean

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Coefficient of Determination
 The proportion of the variability in Y explained by the
regression equation
 The coefficient of determination is r 2 .
2 SSR SSE
r  1 
SST SST
 For Triple A Construction
2 15.625
r   0.6944
22.5
About 69% of the variability in Y is explained by the
equation based on payroll (X)

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Correlation Coefficient
 An expression of the strength of the linear relationship
 Always between 1 and  1
 The correlation coefficient is r

r  r 2
 For Triple A Construction

r  0.6944  0.8333

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Four Values of the Correlation Coefficient

Figure 4.3 Four Values of the Correlation Coefficient

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
Assumptions of the Regression Model
 With certain assumptions about the errors, statistical
tests can be performed to determine the model’s
usefulness
1. Errors are independent
2. Errors are normally distributed
3. Errors have a mean of zero
4. Errors have a constant variance
 A plot of the residuals (errors) often highlights glaring
violations of assumptions

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Residual Plots
Figure 4.4A Pattern of
Errors Indicating
Randomness

Figure 4.4B Nonconstant

Error Variance

Figure 4.4C Pattern of

Errors Indicating
Relationship Is Not Linear

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Variance and Standard Deviation
Errors are assumed to have a constant variance  2
This is estimated suing mean squared error (MSE) s2 .
SSE
s 2  MSE =
n k  1
where
n = number of observations in the sample
k = number of independent variables
The standard error of the estimate (standard deviation of
the regression) is s.
What is the MSE for Triple A Construction?
What is the standard error of the estimate?
Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Testing the Model for Significance
We start with the general linear model Y  0  1 X  
If 1 0, the null hypothesis is that there is no relationship
between X and Y
The alternate hypothesis 1 0  is that a linear
relationship exists
The F statistic is based on the ratio of MSE and MSR
degrees of freedom for the numerator df1 k
MSE
F degrees of freedom for the denominator
MSR
df2 n  k  1

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Testing the Model for Significance
1. If there is very little error, the MSE would be small, and
the F statistic would be large—the model is useful
2. If the F statistic is large, the significance level (p-value)
will be low,—unlikely would have occurred by chance
3. When the F value is large, we can reject the null
hypothesis and accept that there is a linear relationship
between X and Y

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Steps in a Hypothesis Test
1. Specify null and alternative hypotheses
H0 : 1  0
H1 : 1  0

2. Select the level of significance   Common values are

0.01 and 0.05.
3. Calculate the value of the test statistic
MSR
F 
MSE

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Steps in a Hypothesis Test
4. Make a decision using one of the following methods
a. Reject the null hypothesis if the test statistic is greater than the
F value from the table in Appendix D. Otherwise, do not reject the
null hypothesis:
Reject if Fcalculated  F , df , df
1 2

df1 k
df2 n  k  1
b. Reject the null hypothesis if the observed significance level, or
p-value, is less than the level of significance  . Otherwise, do not
reject the null hypothesis:
p-value P (F  calculated test statistic)
Reject if p-value  
Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Triple A Construction Example
 Step 1
H0 : 1  0 (no linear relationship between X and Y)
H1 : 1  0 (linear relationship exists between X and Y)
 Step 2
Select   0.05
 Step 3
– Calculate the value of the test statistic
SSR 15.6250
MSR   15.6250
k 1
MSR 15.6250
F    9.09
MSE 1.7188
Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Triple A Construction Example
 Step 4
 Reject the null hypothesis if the test statistic is greater
than the F value in Appendix D
df1  k 1
df2  n  k  1  6  1  1  4
The value of F associated with a 5% level of
significance and with degrees of freedom 1 and 4 is
found in Appendix D.
F0.05, 1, 4  7.71
Fcalculated  9.09
Reject H0 because 9.09  7.71
Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Triple A Construction
Figure 4.5 F Distribution for Triple A Construction Test for
Significance

We can conclude there

is a statistically
significant relationship
between X and Y

The r 2 value of 0.69 means about 69% of the variability in

sales (Y) is explained by local payroll (X)
Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 The Analysis of Variance (ANOV A) Table
 With software models, an A N O V A table is typically
created that shows the observed significance level
(p-value) for the calculated F value
– This can be compared to the level of significance  
to make a decision
Table 4.4 Analysis of Variance Table for Regression
blank

DF SS MS F Significance F

Regression k SSR MSR SSR / k M S R = S S R over K

MSR / MSE
Start fraction M S R over M S E end fraction

P (F  MSR/MSE)
P left parenthesis F is greater than M S R over M S E right parenthesis

Residual n k 1
n minus k minus 1

SSE MSE SSE / ( n  k  1)

M S E = start fraction S S E over left parenthesis n minus k minus 1 right parenthesis end fraction Blank blank

Total n 1 n minus 1

SST Blank blank blank

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Multiple Regression Analysis
 Extensions to the simple linear model
 Models with more than one independent variable

Y  0  1 X1   2 X 2  K   k X k  

where
Y = dependent variable (response variable)
xi  i th independent variable (predictor or explanatory
variable)
0  intercept (value of Y when all X i  0)
1  coefficient of the ith independent variable
k = number of independent
variables
 random error

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Multiple Regression Analysis
 To estimate these values, a sample is taken the following
equation developed
Yˆ  b0  b1 X1  b2 X 2  K  bk X k
where

Yˆ  predicted value of Y
b0  sample intercept (an estimate of  0 )
b1  sample coefficient of the ith variable (an
estimate of  i )

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Jenny Wilson Realty Example
 Develop a model to determine the suggested listing price for houses
based on the size and age of the house
Yˆ  b0  b1 X1  b2 X 2
where
Yˆ  predicted value of dependent variable (selling price)
b0  Y intercept

X1 and X 2  value of the two independent variables (square footage

and age), respectively
b1 and b2  slopes for X1 and X 2 respectively
– Selects a sample of houses that have sold recently and records
the data

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Jenny Wilson Realty Example
Table 4.5 Jenny Wilson Real Estate Data
Selling Square
Age Condition
Price ($) Footage

95,000 1,926 30 Good

119,000 2,069 40 Excellent

124,800 1,720 30 Excellent

135,000 1,396 15 Good

142,800 1,706 32 Mint

145,000 1,847 38 Mint

159,000 1,950 27 Mint

165,000 2,323 30 Excellent

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Jenny Wilson Realty Example
Table 4.5 [Continued]

Selling Square
Age Condition
Price ($) Footage

182,000 2,285 26 Mint

183,000 3,752 35 Good

200,000 2,300 18 Good

211,000 2,525 17 Good

215,000 3,800 40 Excellent

219,000 1,740 12 Mint

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
Jenny Wilson Realty Example (4 of 10)
Program 4.4A Input Screen for Jenny Wilson Realty
Multiple Regression in Excel

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Jenny Wilson Realty Example
Program 4.4B Excel Output Screen for Jenny Wilson Realty Multiple
Regression Example

Yˆ b0  b1 X1  b2 X 2
146,630.89  43.28 X1  2898.69 X 2
Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Evaluating the Multiple Regression Model

 Similar to simple linear regression models

 The p-value for the F test and r 2 interpreted the same
 The hypothesis is different because there is more than
one independent variable
 The F test is investigating whether all the coefficients are
equal to 0 at the same time

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Evaluating the Multiple Regression Model

 To determine which independent variables are significant,

tests are performed for each variable
H0 : 1  0
H1 : 1  0
 The test statistic is calculated and if the p-value is lower
than the level of significance  , the null hypothesis is
rejected

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Jenny Wilson Realty Example
 Full model is statistically significant
 Useful in predicting selling price
p-value for F test = 0.002 r 2  0.6719
 Are both variables significant? H0 : 1  0
 For X1 (square footage) H1 : 1  0
For a  0.05, p-value = 0.0013 null hypothesis is rejected
 For X1 (age)

For a  0.05, p-value = 0.0039 null hypothesis is rejected

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Binary or Dummy Variables
1. Binary (or dummy or indicator) variables are special
variables created for qualitative data
2. A dummy variable is assigned a value of 1 if a particular
condition is met and a value of 0 otherwise
3. The number of dummy variables must equal one less
than the number of categories of the qualitative variable

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Jenny Wilson Realty Example
A better model can be developed if information about the
condition of the property is included
X 3 1 if the house is in excellent condition, X 3 0
otherwise
X 4 1 if the house is in mint condition, and X 4 0
otherwise.
1. Two dummy variables are used to describe the three
categories of conditions
2. No variable is needed for “good” condition since if both
X 3 0 and X 4 0, the house is in good condition.
Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Jenny Wilson Realty Example
Program 4.5A Input Screen for Jenny Wilson Realty
Example with Dummy Variables in Excel

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Jenny Wilson Realty Example
Program 4.5B Output Screen for Jenny Wilson Realty
Example with Dummy Variables in Excel

Yˆ 121,658  56.43 X1  3,962 X 2  33,162 X 3  47,369 X 4

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Jenny Wilson Realty Example
Program 4.5B Output Screen for Jenny Wilson Realty
Example with Dummy Variables in Excel 2016
Coefficient of determination, r 2  0.898

Yˆ 121,658  56.43 X1  3,962 X 2  33,162 X 3  47,369 X 4

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Model Building
 The best model is a statistically significant model with a
high r 2 and few variables
 As more variables are added to the model, the r 2
value increases
 For this reason, the adjusted r 2 value is often used to
determine the usefulness of an additional variable
 The adjusted r 2 takes into account the number of
independent variables in the model

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Model Building
2 SSR SSE
The formula for r r2  1 
SST SST

2 SSE n  k  1
The formula for adjusted r 2
Adj r 1 
SST n  1

1. As the number of variables increases, the adjusted r 2

gets smaller unless the increase due to the new variable
is large enough to offset the change in k
2. In general, if a new variable increases the adjusted r 2
it should probably be included in the model

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Model Building
1. Stepwise regression systematically adds or deletes
independent variables
2. A forward stepwise procedure puts the most
significant variable in first, adds the next variable that
will improve the model the most
3. Backward stepwise regression begins with all the
independent variables and deletes the least helpful

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Model Building
1. In some cases, variables contain duplicate information
2. When two independent variables are correlated, they
are said to be collinear
3. When more than two independent variables are
correlated, multicollinearity exists
4. When multicollinearity is present, hypothesis tests for
the individual coefficients are not valid but the model
may still be useful

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Colonel Motors
In some situations, variables are not linearly related
Transformations may be used to turn a nonlinear model into a
linear model
Table 4.6 Automobile Weight Versus MPG
Weight Weight
MPG (1,000s LB.) MPG (1,000s LB.)
12 4.58 20 3.18

13 4.66 23 2.68

15 4.02 24 2.65

18 2.53 33 1.70

19 3.09 36 1.95

19 3.11 42 1.92

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Colonel Motors
Figure 4.6A Linear model for MPG data

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Colonel Motors
Program 4.6 Excel Output with Linear Regression Model
for MPG Data

Useful model Small F test for significance Good r 2 value

Yˆ  47.6  8.2 X1 or MGP  47.6  8.2 weight in 1,000 lb. 

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Colonel Motors
Figure 4.6B Nonlinear Model for MPG Data

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Colonel Motors
 The nonlinear model is quadratic
 The easiest approach—develop a new variable
X 2  weight 
2

New model

Yˆ  b0  b1 X1  b2 X 2

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Colonel Motors
Program 4.7 Excel Output with Nonlinear Regression
Model for MPG Data

Yˆ  79.8  30.2 X1  3.4 X 2

Improved model Small F test for significance Adjusted
R2 and R2 both increased.
Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Cautions ((Warnings) and
Pitfalls((Mistakes) in Regression Analysis
1. If the assumptions are not met, the statistical test may
not be valid
2. Correlation does not necessarily mean causation
3. Multicollinearity makes interpreting coefficients
problematic, but the model may still be good
4. Using a regression model beyond the range of X is
questionable, as the relationship may not hold outside
the sample data

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
 Cautions and Pitfalls in Regression
Analysis
5. A t-test for the intercept b0 may be ignored as this point
is often outside the range of the model
6. A linear relationship may not be the best relationship,
even if the F test is significant
7. Even though a relationship is statistically significant it
may not have any practical value
8. A nonlinear relationship can exist even if a linear
relationship does not

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved
Copyright

This work is protected by United States copyright laws and is

provided solely for the use of instructors in teaching their
courses and assessing student learning. Dissemination or sale of
any part of this work (including on the World Wide Web) will
destroy the integrity of the work and is not permitted. The work
and materials from it should never be made available to students
except by instructors using the accompanying text in their
classes. All recipients of this work are expected to abide by these
restrictions and to honor the intended pedagogical purposes and
the needs of other instructors who rely on these materials.

Copyright © 2024, 2018, 2015 Pearson Education, Inc. All Rights Reserved