You are on page 1of 87

Binary Logistic Regression

with SPSS
Karl L. Wuensch
Dept of Psychology
East Carolina University

Download the Instructional


Document
http://core.ecu.edu/psyc/wuenschk/SPSS
/SPSS-MV.htm
.
Click on Binary Logistic Regression .
Save to desktop.
Open the document.

When to Use Binary Logistic Regression


The criterion variable is dichotomous.
Predictor variables may be categorical or
continuous.
If predictors are all continuous and nicely
distributed, may use discriminant function
analysis.
If predictors are all categorical, may use
logit analysis.

Wuensch & Poteat, 1998


Cats being used as research subjects.
Stereotaxic surgery.
Subjects pretend they are on university
research committee.
Complaint filed by animal rights group.
Vote to stop or continue the research.

Purpose of the Research

Cosmetic
Theory Testing
Meat Production
Veterinary
Medical

Predictor Variables

Gender
Ethical Idealism (9-point Likert)
Ethical Relativism (9-point Likert)
Purpose of the Research

Model 1: Decision = Gender


Decision 0 = stop, 1 = continue
Gender 0 = female, 1 = male
Model is .. logit =

lnODDS ln

bX

1 Y

Y is the predicted probability of the event


which is coded with 1 (continue the research)
rather than with 0 (stop the research).

Iterative Maximum Likelihood


Procedure
SPSS starts with arbitrary regression
coefficents.
Tinkers with the regression coefficients to
find those which best reduce error.
Converges on final model.

SPSS
Bring the data into SPSS
http://core.ecu.edu/psyc/wuenschk/SPSS/L
ogistic.sav

Analyze, Regression, Binary Logistic

Decision Dependent
Gender Covariate(s), OK

Look at the Output


Case Processing Summary
a

Unweighted Cases
Selected Cases

N
Included in Analysis
Missing Cases
Total

Unselected Cases
Total

315
0
315
0
315

Percent
100.0
.0
100.0
.0
100.0

a. If weight is in effect, see classification table for the total


number of cases.

We have 315 cases.

Block 0 Model, Odds


Look at Variables in the Equation.
The model contains only the intercept
(constant, B0), a function of the marginal
distribution of the decisions.
Variables in the Equation
Step 0

Constant

B
-.379

S.E.
.115

Wald
10.919

df
1


Y
.379
ln ODDS ln

Sig.
.001

Exp(B)
.684

Exponentiate Both Sides


Exponentiate both sides of the equation:
e-.379 = .684 = Exp(B0) = odds of deciding to
continue the research.
Y
128
Exp( .379) .684

187
1 Y

128 voted to continue the research, 187 to stop


it.

Probabilities

Randomly select one participant.


P(votes continue) = 128/315 = 40.6%
P(votes stop) = 187/315 = 59.4%
Odds = 40.6/59.4 = .684
Repeatedly sample one participant and
guess how e will vote.

Humans vs. Goldfish


Humans Match Probabilities

(suppose p = .7, q = .3)


.7(.7) + .3(.3) = .49 + .09 = .58

Goldfish Maximize Probabilities

.7(1) = .70

The goldfish win!

SPSS Model 0 vs. Goldfish


Look at the Classification Table for Block 0.
Classification Tablea,b
Predicted

Step 0

Observed
decision

stop
continue

Overall Percentage

decision
stop
continue
187
0
128
0

Percentage
Correct
100.0
.0
59.4

a. Constant is included in the model.


b. The cut value is .500

SPSS Predicts STOP for every participant.


SPSS is as smart as a Goldfish here.

Block 1 Model
Gender has now been added to the
model.
Model Summary: -2 Log Likelihood = how
poorly model fits the data.
Model Summary
Step
1

-2 Log
Cox & Snell
likelihood
R Square
399.913a
.078

Nagelkerke
R Square
.106

a. Estimation terminated at iteration number 3 because


parameter estimates changed by less than .001.

Block 1 Model
For intercept only, -2LL = 425.666.
Add gender and -2LL = 399.913.
Omnibus Tests: Drop in -2LL = 25.653 =
Model 2.
df = 1, p < .001.
Omnibus Tests of Model Coefficients
Step 1

Step
Block
Model

Chi-square
25.653
25.653
25.653

df
1
1
1

Sig.
.000
.000
.000

Variables in the Equation


ln(odds) = -.847 + 1.217Gender

ODDS e

a bGender

Variables in the Equation


Step
a
1

gender
Constant

B
1.217
-.847

S.E.
.245
.154

a. Variable(s) entered on step 1: gender.

Wald
24.757
30.152

df
1
1

Sig.
.000
.000

Exp(B)
3.376
.429

Odds, Women
ODDS e

.847 1.217 ( 0 )

.847

0.429

A woman is only .429 as likely to decide to


continue the research as she is to decide
to stop it.

Odds, Men
ODDS e .847 1.217 (1) e .37 1.448

A man is 1.448 times more likely to vote to


continue the research than to stop the research.

Odds Ratio
male _ odds
1.448

3.376 e1.217
female _ odds .429
1.217 was the B (slope) for Gender, 3.376 is the
Exp(B), that is, the exponentiated slope, the
odds ratio.
Men are 3.376 times more likely to vote to
continue the research than are women.

Convert Odds to Probabilities


For our women,
ODDS
0.429

0.30
1 ODDS 1.429

For our men,


ODDS
1.448

0.59
1 ODDS 2.448

Classification
Decision Rule: If Prob (event) Cutoff,
then predict event will take place.
By default, SPSS uses .5 as Cutoff.
For every man, Prob(continue) = .59,
predict he will vote to continue.
For every woman Prob(continue) = .30,
predict she will vote to stop it.

Overall Success Rate


Look at the Classification Table
Classification Tablea
Predicted

Step 1

Observed
decision

stop
continue

decision
stop
continue
140
47
60
68

Overall Percentage
a. The cut value is .500

140 68 208

66%
315
315

SPSS beat the Goldfish!

Percentage
Correct
74.9
53.1
66.0

Sensitivity
P (correct prediction | event did occur)
P (predict Continue | subject voted to Continue)
Of all those who voted to continue the research,
for how many did we correctly predict that.

68
68

53%
68 60 128

Specificity
P (correct prediction | event did not occur)
P (predict Stop | subject voted to Stop)
Of all those who voted to stop the research, for
how many did we correctly predict that.

140
140

75%
140 47 187

False Positive Rate


P (incorrect prediction | predicted occurrence)
P (subject voted to Stop | we predicted Continue)
Of all those for whom we predicted a vote to Continue
the research, how often were we wrong.

47
47

41%
47 68 115

False Negative Rate


P (incorrect prediction | predicted nonoccurrence)
P (subject voted to Continue | we predicted Stop)
Of all those for whom we predicted a vote to Stop the
research, how often were we wrong.

60
60

30%
140 60 200

Pearson

Analyze, Descriptive Statistics, Crosstabs


Gender Rows; Decision Columns

Crosstabs Statistics
Statistics, Chi-Square, Continue

Crosstabs Cells
Cells, Observed Counts, Row
Percentages

Crosstabs Output
Continue, OK
59% & 30% match logistics predictions.
gender * decision Crosstabulation

gender

Female
Male

Total

Count
% within gender
Count
% within gender
Count
% within gender

decision
stop
continue
140
60
70.0%
30.0%
47
68
40.9%
59.1%
187
128
59.4%
40.6%

Total
200
100.0%
115
100.0%
315
100.0%

Crosstabs Output
Likelihood Ratio 2 = 25.653, as with
logistic.
Chi-Square Tests

Pearson Chi-Square
Likelihood Ratio
N of Valid Cases

Value
25.685b
25.653
315

df
1
1

Asymp. Sig.
(2-sided)
.000
.000

a. Computed only for a 2x2 table


b. 0 cells (.0%) have expected count less than 5. The
minimum expected count is 46.73.

Model 2: Decision =
Idealism, Relativism, Gender
Analyze, Regression, Binary Logistic
Decision Dependent
Gender, Idealism, Relatvsm
Covariate(s)

Click Options and check HosmerLemeshow goodness of fit and CI for


exp(B) 95%.

Continue, OK.

Comparing Nested Models


With only intercept and gender,
-2LL = 399.913.
Adding idealism and relativism dropped
-2LL to 346.503, a drop of 53.41.
2(2) = 399.913 346.503 = 53.41, p = ?
Model Summary
Step
1

-2 Log
Cox & Snell
likelihood
R Square
346.503a
.222

Nagelkerke
R Square
.300

a. Estimation terminated at iteration number 4 because


parameter estimates changed by less than .001.

Obtain p
Transform, Compute
Target Variable = p
Numeric Expression =
1 - CDF.CHISQ(53.41,2)

p=?
OK
Data Editor, Variable View
Set Decimal Points to 5 for p

p < .0001
Data Editor, Data View
p = .00000
Adding the ethical ideology variables
significantly improved the model.

Hosmer-Lemeshow
H: predictions made by the model fit
perfectly with observed group
memberships
Cases are arranged in order by their
predicted probability on the criterion.
Then divided into ten bins with
approximately equal n.
This gives ten rows in the table.

For each bin and each event, we have


number of observed cases and expected
number predicted from the model.
Contingency Table for Hosmer and Lemeshow Test

Step
1

1
2
3
4
5
6
7
8
9
10

decision = stop
Observed Expected
29
29.331
30
27.673
28
25.669
20
23.265
22
20.693
15
18.058
15
15.830
10
12.920
12
9.319
6
4.241

decision = continue
Observed Expected
3
2.669
2
4.327
4
6.331
12
8.735
10
11.307
17
13.942
17
16.170
22
19.080
20
22.681
21
22.759

Total
32
32
32
32
32
32
32
32
32
27

Note expected freqs decline in first


column, rise in second.
The nonsignificant chi-square is indicative
of good fit of data with linear model.

Hosmer and Lemeshow Test


Step
1

Chi-square
8.810

df
8

Sig.
.359

Hosmer-Lemeshow
There are problems with this procedure.
Not even Hosmer and Lemeshow
recommend it these days.
Even with good fit the test may be
significant if sample sizes are large
Even with poor fit the test may not be
significant if sample sizes are small.

Linearity of the Logit


We have assumed that the log odds are
related to the predictors in a linear fashion.
Use the Box-Tidwell test to evaluate this
assumption.
For each continuous predictor, compute
the natural log.
Include in the model interactions between
each predictor and its natural log.

Box-Tidwell
If an interaction is significant, there is a
problem.
For the troublesome predictor, try
including the square of that predictor.
That is, add a polynomial component to
the model.
See
T-Test versus Binary Logistic Regression

Variables in the Equation


B

S.E.

gender

1.147

idealism

1.130 1.921

Wald

.269 18.129
.346

df

Sig.
1

.000 3.148

.556 3.097

relatvsm
1.656 2.637
.394
1
idealism by
Step 1a
-.652
.690
.893
1
idealism_LN
relatvsm by
-.479
.949
.254
1
relatvsm_LN
Constant
-5.015 5.877
.728
1
a. Variable(s) entered on step 1: gender, idealism, relatvsm, idealism *
idealism_LN , relatvsm * relatvsm_LN .

No Problem Here.

Exp(B)

.530 5.240
.345

.521

.614

.620

.393

.007

Model 3: Decision =
Idealism, Relativism, Gender, Purpose
Need 4 dummy variables to code the five
purposes.
Consider the Medical group a reference
group.
Dummy variables are: Cosmetic, Theory,
Meat, Veterin.
0 = not in this group, 1 = in this group.

Add the Dummy Variables


Analyze, Regression, Binary Logistic
Add to the Covariates: Cosmetic, Theory,
Meat, Veterin.
OK

Block 0
Look at Variables not in the Equation.
Score is how much -2LL would drop if a
single variable were added to the model
with intercept only.
Variables not in the Equation
Step
0

Variables

Overall Statistics

gender
idealism
relatvsm
cosmetic
theory
meat
veterin

Score
25.685
47.679
7.239
.003
2.933
.556
.013
77.665

df
1
1
1
1
1
1
1
7

Sig.
.000
.000
.007
.955
.087
.456
.909
.000

Effect of Adding Purpose


Our previous model had -2LL = 346.503.
Adding Purpose dropped -2LL to 338.060.
Model Summary
Step
1

-2 Log
Cox & Snell
likelihood
R Square
a
338.060
.243

Nagelkerke
R Square
.327

a. Estimation terminated at iteration number 5 because


parameter estimates changed by less than .001.

2(4) = 8.443, p = .0766.


But I make planned comparisons (with medical
reference group) anyhow!

Classification Table
YOU calculate the sensitivity, specificity,
false positive rate, and false negative rate.
Classification Tablea
Predicted

Step 1

Observed
decision
Overall Percentage

a. The cut value is .500

stop
continue

decision
stop
continue
152
35
54
74

Percentage
Correct
81.3
57.8
71.7

Answer Key

Sensitivity = 74/128 = 58%


Specificity = 152/187 = 81%
False Positive Rate = 35/109 = 32%
False Negative Rate = 54/206 = 26%

Wald Chi-Square
A conservative test of the unique
contribution of each predictor.
Presented in Variables in the Equation.
Alternative: drop one predictor from the
model, observe the increase in -2LL, test
via 2.

Variables in the Equation

Step
a
1

gender
idealism
relatvsm
cosmetic
theory
meat
veterin
Constant

B
1.255
-.701
.326
-.709
-1.160
-.866
-.542
2.279

Wald
20.586
37.891
6.634
2.850
7.346
4.164
1.751
4.867

df
1
1
1
1
1
1
1
1

Sig.
.000
.000
.010
.091
.007
.041
.186
.027

Exp(B)
3.508
.496
1.386
.492
.314
.421
.581
9.766

95.0% C.I.for EXP(B)


Lower
Upper
2.040
6.033
.397
.620
1.081
1.777
.216
1.121
.136
.725
.183
.966
.260
1.298

a. Variable(s) entered on step 1: gender, idealism, relatvsm, cosmetic, theory, meat, veterin.

Odds Ratios Exp(B)


Odds of approval more than cut in half (.496) for
each one point increase in Idealism.
Odds of approval multiplied by 1.39 for each one
point increase in Relativism.
Odds of approval if purpose is Theory Testing
are only .314 what they are for Medical
Research.
Odds of approval if purpose is Agricultural
Research are only .421 what they are for
Medical research

Inverted Odds Ratios


Some folks have problems with odds
ratios less than 1.
Just invert the odds ratio.
For example, 1/.421 = 2.38.
That is, respondents were more than two
times more likely to approve the medical
research than the research designed to
feed to poor in the third world.

Classification Decision Rule


Consider a screening test for Cancer.
Which is the more serious error
False Positive test says you have cancer,
but you do not
False Negative test says you do not have
cancer but you do

Want to reduce the False Negative rate?

Classification Decision Rule


Analyze, Regression, Binary Logistic
Options
Classification Cutoff = .4, Continue, OK

Effect of Lowering Cutoff


YOU calculate the Sensitivity, Specificity,
False Positive Rate, and False Negative
Rate for the model with the cutoff at .4.
Fill in the table on page 15 of the handout.

Answer Key

SAS Rules
See, on page 16 of the handout, how easy
SAS makes it to see the effect of changing
the cutoff.
SAS classification tables remove bias
(using a jackknifed classification
procedure), SPSS does not have this
feature.

Presenting the Results


See the handout.

Interaction Terms
May want to standardize continuous
predictor variables.
Compute the interaction terms or
Let Logistic compute them.

Deliberation and Physical


Attractiveness in a Mock Trial
Subjects are mock jurors in a criminal trial.
For half the defendant is plain, for the
other half physically attractive.
Half recommend a verdict with no
deliberation, half deliberate first.

Get the Data


Bring Logistic2x2x2.sav into SPSS.
Each row is one cell in 2x2x2 contingency
table.
Could do a logit analysis, but will do
logistic regression instead.

Tell SPSS to weight cases by Freq. Data,


Weight Cases:

Dependent = Guilty.
Covariates = Delib, Plain.
In left pane highlight Delib and Plain.

Then click >a*b> to create the interaction


term.

Under Options, ask for the HosmerLemeshow test and confidence intervals
on the odds ratios.

Significant Interaction
The interaction is large and significant
(odds ratio of .030), so we shall ignore the
main effects.
Variables in the Equation

Step
a
1

Delib
Plain
Delib by Plain
Constant

Wald
3.697
4.204
8.075
.037

df
1
1
1
1

Sig.
.054
.040
.004
.847

a. Variable(s) entered on step 1: Delib, Plain, Delib * Plain .

Exp(B)
.338
3.134
.030
1.077

95.0% C.I.for EXP(B)


Lower
Upper
.112
1.021
1.052
9.339
.003
.338

Use Crosstabs to test the conditional


effects of Plain at each level of Delib.
Split file by Delib.

Analyze, Crosstabs.
Rows = Plain, Columns = Guilty.
Statistics, Chi-square, Continue.
Cells, Observed Counts and Column
Percentages.
Continue, OK.

Rows = Plain, Columns = Guilty

For those who did deliberate, the odds of


a guilty verdict are 1/29 when the
defendant was plain and 8/22 when she
was attractive, yielding a conditional odds
ratio of 0.09483 .
a
Plain * Guilty Crosstabulation

Guilty
Plain

Total

Attrractive Count
% within Plain
Plain
Count
% within Plain
Count
% within Plain

a. Delib = Yes

No

Yes

Total

22
73.3%
29
96.7%
51
85.0%

8
26.7%
1
3.3%
9
15.0%

30
100.0%
30
100.0%
60
100.0%

For those who did not deliberate, the odds


of a guilty verdict are 27/8 when the
defendant was plain and 14/13 when she
was attractive, yielding a conditional odds
ratio of 3.1339.
a
Plain * Guilty Crosstabulation

Guilty
Plain

Total

Attrractive Count
% within Plain
Plain
Count
% within Plain
Count
% within Plain

a. Delib = No

No

Yes

Total

13
48.1%
8
22.9%
21
33.9%

14
51.9%
27
77.1%
41
66.1%

27
100.0%
35
100.0%
62
100.0%

Interaction Odds Ratio


The interaction odds ratio is simply the ratio of
these conditional odds ratios that is, .
09483/3.1339 = 0.030.
Among those who did not deliberate, the plain
defendant was found guilty significantly more
often than the attractive defendant, 2(1, N = 62)
= 4.353, p = .037.
Among those who did deliberate, the attractive
defendant was found guilty significantly more
often than the plain defendant, 2(1, N = 60) =
6.405, p = .011.

Interaction Between Continuous


and Dichotomous Predictor

Interaction Falls Short of


Significance

Standardizing Predictors
Most helpful with continuous predictors.
Especially when want to compare the
relative contributions of predictors in the
model.
Also useful when the predictor is
measured in units that are not intrinsically
meaningful.

Predicting Retention in ECUs


Engineering Program

Practice Your New Skills


Try the exercises in the handout.

You might also like