27.03.2013 Views

SPSS® 12.0 Command Syntax Reference

SPSS® 12.0 Command Syntax Reference

SPSS® 12.0 Command Syntax Reference

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

476 DISCRIMINANT<br />

• When multiple FUNCTIONS subcommands are specified, the program uses the last;<br />

however, if n 2 or n 3 are omitted on the last FUNCTIONS subcommand, the corresponding<br />

specifications on the previous FUNCTIONS subcommands will remain in effect.<br />

Example<br />

DISCRIMINANT GROUPS=CLASS(1,5)<br />

/VARIABLES = SCORE1 TO SCORE20<br />

/FUNCTIONS=4,100,.80.<br />

• The first two parameters on the FUNCTIONS subcommand are defaults: the default for n1 is 4 (the number of groups minus 1), and the default for n2 is 100.<br />

• The third parameter tells DISCRIMINANT to use fewer than four discriminant functions if<br />

the significance level of a function is greater than 0.80.<br />

PRIORS Subcommand<br />

By default, DISCRIMINANT assumes equal prior probabilities for groups when classifying<br />

cases. You can provide different prior probabilities with the PRIORS subcommand.<br />

• Prior probabilities are used only during classification.<br />

• If you provide unequal prior probabilities, DISCRIMINANT adjusts the classification<br />

coefficients to reflect this.<br />

• If adjacent groups have the same prior probability, you can use the notation n*c on the<br />

value list to indicate that n adjacent groups have the same prior probability c.<br />

• You can specify a prior probability of 0. No cases are classified into such a group.<br />

• If the sum of the prior probabilities is not 1, the program rescales the probabilities to sum<br />

to 1 and issues a warning.<br />

EQUAL Equal prior probabilities. This is the default.<br />

SIZE Proportion of the cases analyzed that fall into each group. If 50% of the<br />

cases included in the analysis fall into the first group, 25% in the second, and<br />

25% in the third, the prior probabilities are 0.5, 0.25, and 0.25, respectively.<br />

Group size is determined after cases with missing values for the predictor variables<br />

are deleted.<br />

Value list User-specified prior probabilities. The list of probabilities must sum to 1.0.<br />

The number of prior probabilities named or implied must equal the number<br />

of groups.<br />

Example<br />

DISCRIMINANT GROUPS=TYPE(1,5)<br />

/VARIABLES=A TO H<br />

/PRIORS = 4*.15,.4.<br />

• The PRIORS subcommand establishes prior probabilities of 0.15 for the first four groups<br />

and 0.4 for the fifth group.

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!