Internet and Computer Exercise 1 (From Marketing Research (6th Edition) ,Page 60
ID: 3042947 • Letter: I
Question
Internet and Computer Exercise 1 (From Marketing Research (6th Edition) ,Page 600: Chapter 18, Internet Exercise 1)- Conduct a two-group discriminant analysis on the data given in Tables 18.2 and 18.3 using SPSS (SAS and Minitab not needed). Compare the output and discuss similarities and differences. The comparison is about the similarities and differences in a) the significance values of the discriminant coefficients, b) percentage of original grouped cases correctly classified, and c) percentage of cross-validated grouped cases correctly classified across the three datasets.
no visit income travel vacation hhsize age amount 1 1 50.2 5 8 3 43 2 2 1 70.3 6 7 4 61 3 3 1 62.9 7 5 6 52 3 4 1 48.5 7 5 5 36 1 5 1 52.7 6 6 4 55 3 6 1 75 8 7 5 68 3 7 1 46.2 5 3 3 62 2 8 1 57 2 4 6 51 2 9 1 64.1 7 5 4 57 3 10 1 68.1 7 6 5 45 3 11 1 73.4 6 7 5 44 3 12 1 71.9 5 8 4 64 3 13 1 56.2 1 8 6 54 2 14 1 49.3 4 2 3 56 3 15 1 62 5 6 2 58 3 16 2 32.1 5 4 3 58 1 17 2 36.2 4 3 2 55 1 18 2 43.2 2 5 2 57 2 19 2 50.4 5 2 4 37 2 20 2 44.1 6 6 3 42 2 21 2 38.3 6 6 2 45 1 22 2 55 1 2 2 57 2 23 2 46.1 3 5 3 51 1 24 2 35 6 4 5 64 1 25 2 37.3 2 7 4 54 1 26 2 41.8 5 1 3 56 2 27 2 57 8 3 2 36 2 28 2 33.4 6 8 2 50 1 29 2 37.5 3 2 3 48 1 30 2 41.3 3 3 2 42 1 1 1 50.8 4 7 3 45 2 2 1 63.6 7 4 7 55 3 3 1 54 6 7 4 58 2 4 1 45 5 4 3 60 2 5 1 68 6 6 6 46 3 6 1 62.1 5 6 3 56 3 7 2 35 4 3 4 54 1 8 2 49.6 5 3 5 39 1 9 2 39.4 6 5 3 44 3 10 2 37 2 6 5 51 1 11 2 54.5 7 3 3 37 2 12 2 38.2 2 2 3 49 1Explanation / Answer
Eigenvalues
Function
Eigenvalue
% of Variance
Cumulative %
Canonical Correlation
dimension0
1
1.925a
100.0
100.0
.811
a. First 1 canonical discriminant functions were used in the analysis.
1. The larger the eigenvalue, the more of the variance in the dependent variable is explained by that function.
. The canonical correlation is the measure of association between the discriminant function and the dependent variable.
Classification Function Coefficients
visit
1.00
2.00
income
.900
.765
travel
1.738
1.755
vacation
1.438
.860
hhsize
2.267
1.474
age
1.105
1.007
amount
-2.494
-4.678
(Constant)
-67.684
-45.821
Fisher's linear discriminant functions
Classification Resultsa
visit
Predicted Group Membership
Total
1.00
2.00
Original
Count
1.00
18
3
21
2.00
0
21
21
%
1.00
85.7
14.3
100.0
2.00
.0
100.0
100.0
a. 92.9% of original grouped cases correctly classified.
Test Results
Wilks' Lambda
Test of Function(s)
Wilks' Lambda
Chi-square
df
Sig.
dimension0
1
.342
39.714
6
.000
Wilks' lambda is a measure of how well each function separates cases into groups. Smaller values of Wilks' lambda indicate greater discriminatory ability of the function.
These all are the result of Discriminant analysis in SPSS.
a)the discriminant functions for 1 and 2 is
visit 1 =.9 Income+1.738 travel+1.438 vacation+2.267 hhsize+1.105age+-2.494 amount-67.684
Visit 2 =.765 Income+1.755travel+.860vacation+1.474hhsize+1.007 age+-4.678 amount-45.821
b) Originally classified =39/42
=.9285
Therefore percentage of originally classified =92%
Eigenvalues
Function
Eigenvalue
% of Variance
Cumulative %
Canonical Correlation
dimension0
1
1.925a
100.0
100.0
.811
a. First 1 canonical discriminant functions were used in the analysis.
Related Questions
drjack9650@gmail.com
Navigate
Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.