Multiple Discriminant Analysis and Logistic Regression

Chapter 7
Multiple Discriminant Analysis and

Logistic Regression
Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-1

Chapter 7
Logistic Regression
LEARNING OBJECTIVES
Upon completing this chapter, you should be able to
do the following:
• State the circumstances under which a linear
discriminant analysis should be used instead of
multiple regression.
• Identify the major issues relating to types of
variables used and sample size required in the
application of discriminant analysis.
• Understand the assumptions underlying
discriminant analysis in assessing its
appropriateness for a particular problem.
Chapter 7
Nominal Regression
LEARNING OBJECTIVES continued . . .
Upon completing this chapter, you should be able to do
the following:
• Describe the two computation approaches for
discriminant analysis and the method for assessing
overall model fit.
• Explain what a classification matrix is and how to
develop one, and describe the ways to evaluate the
predictive accuracy of the discriminant function.
• Tell how to identify independent variables with
discriminatory power.
• Justify the use of a split-sample approach for validation.
Discriminant Analysis Defined
Multiple discriminant analysis . . . is an appropriate

technique when the dependent variable is categorical (nominal or
nonmetric) and the independent variables are metric. The single
dependent variable can have two, three or more categories.
Examples:
• Gender – Ma
le vs. Female
• Heavy Users
vs. Light Users
• Purchaserrs
s vs. Non-purch
• Good Credit aserrs
s
Risk vs. Poor Cre
• Member vs. N dit Risk
on-Member
• Attorn
rney, Physician or
Pro
rofessor

KitchenAid Survey Results for the Evaluation*
of a New Consumer Product
Purchase Intention Subject X1 X2 X3
Number Durability Performance Style
Group 1
Would purchase 1 8 9 6
2 6 7 5
3 10 6 3
4 9 4 4
5 4 8 2
Group Mean 7.4 6.8 4.0
Group 2
Would not purchase 6 5 4 7
7 3 7 2
8 4 5 5
9 2 4 3
10 2 2 2
Group Mean 3.2 4.4 3.8
Difference between group means 4.2 2.4 0.2

*Evaluations made on a 0 (very poor) to 10 (excellent) rating scale.
Graphic Illustration of
Two-Group Discriminant Analysis
X2
A
B
A’
B’ X1
Discriminant
Function
Z
Discriminant Analysis Decision Process
Stage 1: Objectives of Discriminant Analysis

Stage 2: Research Design for Discriminant Analysis
Stage 3: Assumptions of Discriminant Analysis
Stage 4: Estimation of the Discriminant Model and
Assessing Overall Fit
Stage 5: Interpretation of the Results
Stage 6: Validation of the Results

Stage 1: Objectives of Discriminant Analysis
1. Determine if statistically significant differences exist between the
two (or more) a priori defined groups.
2. Identify the relative importance of each of the independent
variables in predicting group membership.
3. Establish the number and composition of the dimensions of
discrimination between groups formed from the set of
independent variables. That is, when there are more than two
groups, you should examine and "name" each significant
discriminant function. The number of significant functions
determines the "dimensions“ / discriminant functions and what
they represent in distinguishing the groups.
4. Develop procedures for classifying objects (individuals, firms,
products, etc.) into groups, and then examining the predictive
accuracy (hit ratio) of the discriminant function to see if it is
acceptable (> 25% increase).

Stage 2: Research Design for Discriminant Analysis
• Selection of dependent and

independent variables.
• Sample size (total & per variable).
• Sample division for validation.

Converting Metric Variables to Nonmetric
• Most common approach = to use the metric scale

responses to develop nonmetric categories. For
example, use a question asking the typical number
of soft drinks consumed per day and develop a
three-category variable of 0 drinks for non-users, 1
– 5 for light users, and 5 or more for heavy users.
• Polar extremes approach = compares only the
extreme two groups and excludes the middle
group(s).

Rules of Thumb 7–1
Discriminant Analysis Design
• The dependent variable must be nonmetric, representing groups
of objects that are expected to differ on the independent
variables.
• Choose a dependent variable that:
 best represents group differences of interest,
 defines groups that are substantially different, and
 minimizes the number of categories while still meeting the
research objectives.
• In converting metric variables to a nonmetric scale for use as the
dependent variable, consider using extreme groups to maximize
the group differences.
• Independent variables must identify differences between at least
two groups to be of any use in discriminant analysis.
Rules of Thumb 7–1 continued . . .
• The sample size must be large enough to:
 have at least one more observation per group than the number of
independent variables, but striving for at least 20 cases per group.
 have 20 cases per independent variable, with a minimum
recommended level of 5 observations per variable.
 have at least one more observation per group than the number of
independent variables, but striving for at least 20 cases per group.
 have a large enough sample to divide it into an estimation and holdout
sample, each meeting the above requirements.
• Assess the equality of covariance matrices with the Box’s M test, but apply
a conservative significance level of .01.
• Examine the independent variables for univariate normality.
• Multicollinearity among the independent variables can markedly reduce the
estimated impact of independent variables in the derived discriminant
function(s), particularly if a stepwise estimation process is used.

Key Assumptions
• Multivariate normality of the
• Equal variance and covariance

for the groups.

Other Assumptions
• Minimal multicollinearity among
• Group sample sizes relatively equal.
• Linear relationships.
• Elimination of outliers.

Stage 4: Estimation of the Discriminant Model and
Assessing Overall Fit
Selecting An Estimation Method . . .

1. Simultaneous Estimation – all
independent variables are considered
concurrently.
2. Stepwise Estimation – independent
variables are entered into the
discriminant function one at a time.

Estimating the Discriminant Function
The stepwise procedure begins with all

independent variables not in the model, and selects
variables for inclusion based on:
• Statistically significant differences across the
groups (.05 or less required for entry), and
• The largest Mahalanobis distance (D2) between
the groups.

Assessing Overall Model Fit
• Calculating discriminant Z scores

for each observation,
• Evaluating group differences on the
discriminant Z scores, and
• Assessing group membership
prediction accuracy.

Assessing Group Membership
Prediction Accuracy
Major Considerations:
• The statistical and practical rational for
developing classification matrices,
• The cutting score determination,
• Construction of the classification matrices,
and
• Standards for assessing classification
accuracy.

Model Estimation and Model Fit
• Although stepwise estimation may seem “optimal” by
selecting the most parsimonious set of maximally
discriminating variables, beware of the impact of
multicollinearity on the assessment of each variable’s
discriminatory power.
• Overall model fit assesses the statistical significance
between groups on the discriminant Z score(s), but
does not assess predictive accuracy.
• With more than two groups, do not confine your
analysis to only the statistically significant discriminant
function(s), but consider if nonsignificant functions
(with significance levels of up to .3) add explanatory
power.
Calculating the Optimum Cutting Score
Issues . . .
• Define the prior probabilities based either on
the relative sample sizes of the observed
groups or specified by the researcher (either
assumed to be equal or with values set by the
researcher), and
• Calculate the optimum cutting score value as a
weighted average based on the assumed sizes
of the groups (derived from the sample sizes).

Optimal Cutting Score with Equal Samples Sizes
Group A Group B
_ _
ZA ZB
Classify as B
Classify as A (Purchaser)
(Nonpurchaser)

Optimal Cutting Score with Unequal Samples Sizes
Unweighted
Optimal Weighted Cutting Score
Cutting Score
Group B
Group A
_ _
ZA ZB

Establishing Standards of
Comparison for the Hit Ratio
Group sizes determine standards based on:

• Equal Group Sizes
• Unequal Group Sizes – two criteria:
o Maximum Chance Criterion
o Proportional Chance Criterion

Classification Matrix
HBAT’s New Consumer Product
Predicted Group
Would Percent
Actual Would Not Actual Correct
Group Purchase Purchase Total Classification
(1) 22 3 25
88%
(2) 5 20 25
Predicted
80% 27 23 50
Total
Percent Correctly Classified (hit ratio) =
100 x [(22 + 20)/50] = 84%
Assessing Predictive Accuracy
• The classification matrix and hit ratio replace R 2
as the
measure of model fit:
 assess the hit ratio both overall and by group..
 If the estimation and analysis samples both exceed
100 cases and each group exceeds 20 cases,
derive separate standards for each sample. If not,
derive a single standard from the overall sample.
• Analyze the missclassified observations both
graphically (territorial map) and empirically
(Mahalanobis D2).
Rules of Thumb 7–3 Continued . . .
Assessing Predictive Accuracy
• There are multiple criteria for comparison to the hit ratio:
 The maximum chance criterion for evaluating the hit ratio is
the most conservative, giving the highest baseline value to
exceed.
 Be cautious in using the maximum chance criterion in
situations with overall samples less than 10 and/or group
sizes under 20.
 The proportional chance criterion considers all groups in
establishing the comparison standard and is the most
popular.
 The actual predictive accuracy (hit ratio) should exceed the
any criterion value by at least 25%.
Three Methods . . .
1. Standardized discriminant weights,
2. Discriminant loadings (structure
correlations), and
3. Partial F values.

Interpretation of the Results
Two or More Functions . . .

1. Rotation of discriminant functions
2. Potency index

Graphical Display of Discriminant
Scores and Loadings
• Territorial Map = most common method.

• Vector Plot of Discriminant Loadings,
preferably the rotated loadings = simplest
approach.

Plotting Procedure for Vectors
Three Steps . . .
1. Selecting variables,
2. Stretching the vectors, and
3. Plotting the group centroids.

Territorial
Figure Map for Three
5.9 Territoral Group
Map For
Discriminant Analysis
Three Group Discriminant Analysis
4
2 Over 5 years
Function 2
0 X1 - Customer Type
1 to 5 years
-1 Less than 1 year Group Centroids
-2 Over 5 years
-3 1 to 5 years
-4 Less than 1 year

-6 -4 -2 0 2 4
Function 1
Interpreting and Validating Discriminant Functions

• Discriminant loadings are the preferred method to
assess the contribution of each variable to a
discriminant function because they are:
 a standardized measure of importance (ranging
from 0 to 1).
 available for all independent variables whether
used in the estimation process or not.
 unaffected by multicollinearity.
• Loadings exceeding ±.40 are considered substantive
for interpretation purposes.

Interpreting and Validating Discriminant Functions

• If there is more than one discriminant function, be sure
to:
 use rotated loadings.
 assess each variable’s contribution across all the
functions with the potency index.
• The discriminant function must be validated either with
a holdout sample or one of the “Leave-one-out”
procedures.

• Utilizing a Holdout Sample

• Cross-Validation

Discriminant Analysis
Learning Checkpoint
1. When should multiple discriminant analysis

be used?
2. What are the major considerations in the
application of discriminant analysis?
3. Which measures are used to assess the
validity of the discriminant function?
4. How should you identify variables that
predict group membership well?

Description of HBAT Primary Database Variables
Variable Description Variable Type
Data Warehouse Classification Variables
X1 Customer Type nonmetric
X2 Industry Type nonmetric
X3 Firm Size nonmetric
X4 Region nonmetric
X5 Distribution System nonmetric
Performance Perceptions Variables
X6 Product Quality metric
X7 E-Commerce Activities/Website metric
X8 Technical Support metric
X9 Complaint Resolution metric
X10 Advertising metric
X11 Product Line metric
X12 Salesforce Image metric
X13 Competitive Pricing metric
X14 Warranty & Claims metric
X15 New Products metric
X16 Ordering & Billing metric
X17 Price Flexibility metric
X18 Delivery Speed metric
Outcome/Relationship Measures
X19 Satisfaction metric
X20 Likelihood of Recommendation metric
X21 Likelihood of Future Purchase metric
X22 Current Purchase/Usage Level metric
X23 Consider Strategic Alliance/Partnership in Future nonmetric 6-36
Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall.
Chapter 7
Logistic Regression: Regression with a Binary
Dependent Variable
LEARNING OBJECTIVES
do the following:
• State the circumstances under which logistic
regression should be used instead of multiple
regression.
• Identify the types of dependent and independent
variables used in the application of logistic
regression.
• Describe the method used to transform binary
measures into the likelihood and probability
measures used in logistic regression.
6-37
Chapter 7
Logistic Regression: Regression with a Binary
Dependent Variable
LEARNING OBJECTIVES continued . . .

do the following:
• Interpret the results of a logistic regression
analysis and assessing predictive accuracy, with
comparisons to both multiple regression and
discriminant analysis.
• Understand the strengths and weaknesses of
logistic regression compared to discriminant
analysis and multiple regression.
6-38
Logistic Regression Defined
Logistic Regression . . . is a specialized
form of regression that is designed to predict
and explain a binary (two-group) categorical
variable rather than a metric dependent
measure. Its variate is similar to regular
regression and made up of metric
independent variables. It is less affected than
discriminant analysis when the basic
assumptions, particularly normality of the
independent variables, are not met.
6-39
Logistic Regression May Be Preferred . . .
When the dependent variable has only two groups, logistic

regression may be preferred for two reasons:
• Discriminant analysis assumes multivariate normality and equal
variance-covariance matrices across groups, and these
assumptions are often not met. Logistic regression does not
face these strict assumptions and is much more robust when
these assumptions are not met, making its application
appropriate in many situations.
• Even if the assumptions are met, some researchers prefer
logistic regression because it is similar to multiple regression. It
has straightforward statistical tests, similar approaches to
incorporating metric and nonmetric variables and nonlinear
effects, and a wide range of diagnostics.
6-40
Logistic Regression Decision Process
Stage 1: Objectives of Logistic Regression

Stage 2: Research Design for Logistic Regression
Stage 3: Assumptions of Logistic Regression
Stage 4: Estimation of the Logistic Regression Model
and Assessing Overall Fit
6-41
Stage 1: Objectives of Logistic Regression
Logistic regression is best suited to address two

research objectives . . .
• Identifying the independent variables that
impact group membership in the dependent
variable.
• Establishing a classification system based on
the logistic model for determining group
membership.
6-42
Stage 2: Research Design for
Logistic Regression
• The binary nature of the dependent variable (0 – 1)
means the error term has a binomial distribution
instead of a normal distribution, and it thus invalidates
all testing based on the assumption of normality.
• The variance of the dichotomous variable is not
constant, creating instances of heteroscedasticity as
well.
• Neither of the above violations can be remedied
through transformations of the dependent or
independent variables. Logistic regression was
developed to specifically deal with these issues.
6-43
Stage 3: Assumptions of Logistic
Regression
• The advantages of logistic regression are

primarily the result of the general lack of
assumptions.
• Logistic regression does not require any specific
distributional form for the independent variables.
• Heteroscedasticity of the independent variables is
not required.
• Linear relationships between the dependent and
independent variables are not required.
6-44
Stage 4: Estimation of Logistic Regression Model
and Assessing Overall Fit
• Transforming the dependent variable

• Estimating the coefficients
• Transforming a probability into odds and
logit values
• Model estimation
• Assessing the goodness of fit
6-45
Estimating the Coefficients
Two basic steps . . .

1. Transforming a probability into odds and logit values
2. Model estimation using a maximum likelihood
approach, not least squares as in multiple
regression
• The estimation process maximizes the likelihood
that an event will occur – the event being a
respondent is assigned to one group versus
another
6-46
Transforming a Probability into Odds
and Logit Values
o The logistic transformation has two basic steps:
 Restating a probability as odds, and
 Calculating the logit values.
o Instead of using ordinary least squares to
estimate the model, the maximum likelihood
method is used.
o The basic measure of how well the maximum
likelihood estimation procedure fits is the
likelihood value.
6-47
Model Estimation Fit – Between Model
comparisons . . .
Comparisons of the likelihood values follow three

steps:
1. Estimate a Null Model – which acts as the
“baseline” for making comparisons of improvement
in model fit.
2. Estimate Proposed Model – the model containing
the independent variables to be included in the
logistic regression.
3. Assess – 2LL Difference.
6-48
Comparison to Multiple Regression . . .
Correspondence of Primary Elements of Model Fit

Multiple Regression Logistic Regression
Total Sum of Squares -2LL of Base Model
Error Sum of Squares -2LL of Proposed Model
Regression Sum of Squares Difference of -LL for
Base and Proposed Models
F test of model fit Chi-square Test of -
2LL Difference
Coefficient of determination “Pseudo” R2 measures
6-49
• Testing for significance of the coefficients –

based on the Wald statistic
• Interpreting the coefficients
• Directionality of the relationship
• Magnitude of the relationship of metric
independent variables
• Interpreting nonmetric independent variables
6-50
Directionality of the Relationship
A positive relationship means an increase in the
independent variable is associated with an increase in the
predicted probability, and vice versa. But the direction of
the relationship is reflected differently for the original and
exponentiated logistic coefficients.
• Original coefficient signs indicate the direction of the
relationship.
• Exponentiated coefficients are interpreted differently
since they are the logarithms of the original coefficients
and do not have negative values. Thus, exponentiated
coefficients above 1.0 represent a positive relationship
and values less than 1.0 represent negative
relationships.
6-51
Magnitude of the Relationship . . .
The magnitude of metric independent variables is

interpreted differently for original and exponentiated
logistic coefficients:
• Original logistic coefficients – are less useful in

determining the magnitude of the relationship since the
reflect the change in the logit (logged odds) value.
• Exponentiated coefficients – directly reflect the

magnitude of the change in the odds value. But their
impact is multiplicative and a coefficient of 1.0 denotes
no change (1.0 times the independent variable = no
change).
6-52
Logistic Regression
• Logistic regression is the preferred method for two-
group (binary) dependent variables due to its
robustness, ease of interpretation and diagnostics.
• Sample size considerations for logistic regression are
primarily focused on the size of each group, which
should have 10 times the number of estimated model
coefficients (the number of variables).
• Sample size should be met in both the analysis and
holdout samples.
• Model significance tests are made with a chi-square
test on the differences in the log likelihood values (-
2LL) between two models.
6-53
Logistic Regression
• Coefficients are expressed in two forms: original and
exponentiated to assist in interpretation.
• Interpretation of the coefficients for direction and
magnitude is:
 Direction can be directly assessed in the original
coefficients (positive or negative signs) or indirectly in
the exponentiated coefficients (less than 1 are
negative, greater than 1 are positive).
 Magnitude is best assessed by the exponentiated
coefficient, with the percentage change in the
dependent variable shown by: Percentage change =
(Exponentiated Coefficient – 1.0) * 100
6-54
• Involves ensuring both the internal and

external validity of the results.
• The most common form of estimating external
validity is creation of a holdout or validation
sample and calculating the hit ratio.
• A second approach is cross-validation,
typically achieved with a jackknife or “leave-
one-out” process of calculating the hit ratio.
6-55
Description of HBAT Primary Database Variables
Variable Description Variable Type
Data Warehouse Classification Variables
X1 Customer Type nonmetric
X2 Industry Type nonmetric
X3 Firm Size nonmetric
X4 Region nonmetric
X5 Distribution System nonmetric
Performance Perceptions Variables
X6 Product Quality metric
X7 E-Commerce Activities/Website metric
X8 Technical Support metric
X9 Complaint Resolution metric
X10 Advertising metric
X11 Product Line metric
X12 Salesforce Image metric
X13 Competitive Pricing metric
X14 Warranty & Claims metric
X15 New Products metric
X16 Ordering & Billing metric
X17 Price Flexibility metric
X18 Delivery Speed metric
Outcome/Relationship Measures
X19 Satisfaction metric
X20 Likelihood of Recommendation metric
X21 Likelihood of Future Purchase metric
X22 Current Purchase/Usage Level metric
X23 Consider Strategic Alliance/Partnership in Future nonmetric 6-56

Multiple Discriminant Analysis and Logistic Regression

Uploaded by

Multiple Discriminant Analysis and Logistic Regression

Uploaded by

Chapter 7

Multiple Discriminant Analysis and

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-1

Multiple discriminant analysis . . . is an appropriate

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-4

Difference between group means 4.2 2.4 0.2

Stage 1: Objectives of Discriminant Analysis

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-7

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-8

• Selection of dependent and

• Sample size (total & per variable).

• Sample division for validation.

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-9

• Most common approach = to use the metric scale

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-10

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-12

• Equal variance and covariance

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-13

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-14

Selecting An Estimation Method . . .

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-15

The stepwise procedure begins with all

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-16

• Calculating discriminant Z scores

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-17

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-18

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-20

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-21

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-22

Group sizes determine standards based on:

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-23

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-27

Two or More Functions . . .

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-28

• Territorial Map = most common method.

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-29

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-30

-4 Less than 1 year

Interpreting and Validating Discriminant Functions

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-32

Interpreting and Validating Discriminant Functions

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-33

• Utilizing a Holdout Sample

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-34

1. When should multiple discriminant analysis

Copyright © 2010 Pearson Education, Inc., publishing as Prentice-Hall. 5-35

LEARNING OBJECTIVES continued . . .

When the dependent variable has only two groups, logistic

Stage 1: Objectives of Logistic Regression

Logistic regression is best suited to address two

• The advantages of logistic regression are

• Transforming the dependent variable

Two basic steps . . .

Comparisons of the likelihood values follow three

Correspondence of Primary Elements of Model Fit

• Testing for significance of the coefficients –

The magnitude of metric independent variables is

• Original logistic coefficients – are less useful in

• Exponentiated coefficients – directly reflect the

• Involves ensuring both the internal and

You might also like