Professional Documents
Culture Documents
Discriminant analysis
Discriminant analysis is used to estimate the relationship between a categorical dependent variable and a set of interval scaled, independent variables.
Naresh Malhotra and David Birks, Marketing Research, 3rd Edition, Pearson Education Limited 2007
Slide 21.2
Chapter outline
1.
2. 3. 4. 5.
Basic concept
Relation to regression and ANOVA Discriminant analysis model Statistics associated with Discriminant analysis Conducting Dscriminant analysis
6.
7.
Slide 21.3
Table 21.1 Similarities and differences among ANOVA, regression and discriminant analysis
Y = b0 + b1 X1 + b2 X2 + b3 X3
Slide 21.4
Discriminant analysis
Y = b0 + b1 X1 + b2 X2 + b3 X3
Discriminant analysis is a technique for analyzing data when the dependent variable is categorical and the independent variables are interval in nature. The objectives of discriminant analysis are as follows: Development of Discriminant functions, or linear combinations of independent variables, which will best discriminate between the categories of the dependent variable (groups). Examination of whether significant differences exist among the groups, in terms of the Independent variables. Determination of which predictor variables contribute to most of the intergroup differences. Classification of cases to one of the groups based on the values of the Independent variables. Evaluation of the accuracy of classification.
Slide 21.5
Slide 21.6
Geometric interpretation
Independent Variable
X2
G1
1 1 1 1 1 1 1 1 1
2 11 1 1 2 22 21
2 2 2 2 2 2 22 22
G2
G1 G2 X1 Variable D
Independent
Discriminant
Slide 21.7
Xs =
The coefficients or weights (b), are estimated so that the groups differ as much as possible on the values of the discriminant function. This occurs when the ratio of between-group sum of squares to within-group sum of squares for the discriminant scores is at a maximum.
Between group sum of squares Within group sum of squares
Slide 21.8
Classification matrix. Sometimes also called confusion or prediction matrix, the classification matrix contains the number of correctly classified and misclassified cases.
Slide 21.9
Slide 21.10
ANOVAGroup means and group standard deviations. These are computed for each predictor for each group. Pooled within-group correlation matrix. The pooled within-group correlation matrix is computed by averaging the separate covariance matrices for all the groups.
Slide 21.11
Slide 21.12
Slide 21.13
Slide 21.14
Example: We want to determine the salient characteristics of families that have visited a skiing resort during the last 2 years. The households that visited the resort during the last two years are coded as 1 and those that did not visit are coded as 2.
Table 21.2
Slide 21.15
Slide 21.16
Slide 21.17
Slide 21.18
Low correlation among indepenedent variables Small values of lambda means groups are different on these variables
Only income, holiday and house hold size significantly differentiate between those who visited a resort and those who did not.
Slide 21.19
The canonical correlation associated with this function is 0.8007. The square of this correlation is .64, which indicates that 64% of the variance in the dependent variable is explained by this model.
The sig indicates that the predictors significantly discriminate the groups.
The most important independent variable in discriminating between groups. Large standardised coefficients contribute more to the discriminating power of the function.
The signs of coefficients of all the independent variables are positive, which suggest that higher family income, household size, importance attached to family skiing holiday, attitude towards travel and age are more likely to result in the family visiting the resort.
Structure matrix: tells the relative importance of the predictors
Slide 21.20
Group centroids give the value of the discriminant function evaluated at the group means.
Slide 21.21
Slide 21.22
Slide 21.23
Slide 21.24
Slide 21.25
Slide 21.26
Slide 21.27
Slide 21.28
Slide 21.29
Slide 21.30
Slide 21.31
Slide 21.32
Slide 21.33
SPSS Windows
The DISCRIMINANT program performs both twogroup and multiple discriminant analysis. To select this procedure using SPSS for Windows click: Analyze>Classify>Discriminant Then run logit analysis or logistic regression using SPSS for Windows, click:
Slide 21.34
6. 7.
8.
9.
Slide 21.35
Slide 21.36
Slide 21.37
Assessing Group differences: In profiling the two groups, we can identify variables with larges differences in the group mean. (X6, X11, X12, X13 and X17) Repeat the same using step method. Carry out profiling of each group on these variables to understand the differences between them.
Slide 21.38
Management should use these results to develop strategies that accentuate these strengths and develop additional strengths to complement them.