User Guide

514
Chapter 35
For multiple dichotomy sets, category names shown in the output come from
variable labels defined for elementary variables in the group. If the variable labels are
not defined
, variable names are used as labels. For multiple category sets, category
labels come from the value labels of the first variable in the group. If categories
missing for the first variable are present for other variables in the group, define a
value labe
l for the missing categories.
Missing Va
lues.
Cases with missing values are excluded on a table-by-table basis.
Alternatively, you can choose one or both of the following:
 Exclude cases listwise within dichotomies. Excludes cases with missing values
for any var
iable from the tabulation of the multiple dichotomy set. This applies
only to multiple response sets defined as dichotomy sets. By default, a case
is considered missing for a multiple dichotomy set if none of its component
variable
s contains the counted value. Cases with missing values for some (but
not all variables) are included in the tabulations of the group if at least one
variable contains the counted value.
 Exclude cases listwise within categories. Excludes cases with missing values for
any varia
ble from tabulation of the multiple category set. This applies only to
multiple response sets defined as category sets. By default, a case is considered
missing for a multiple category set only if none of its components has valid
values w
ithin the defined range.
Example. Each variable created from a survey question is an elementary variable. To
analyze a multiple response item, you must combine the variables into one of two
types o
f multiple response sets: a multiple dichotomy set or a multiple category set.
For example, if an airline survey asked which of three airlines (American, United,
TWA) you have flown in the last six months and you used dichotomous variables and
define
damultiple dichotomy set, each of the three variables in the set would become
a category of the group variable. The counts and percentages for the three airlines
are displayed in one frequency table. If you discover that no respondent mentioned
more t
han two airlines, you could create two variables, each having three codes, one
for each airline. If you define a multiple category set, the values are tabulated by
addingthesamecodesintheelementaryvariables together. The resulting set of
valu
es is the same as those for each of the elementary variables. For example, 30
responses for United are the sum of the 5 United responses for airline 1 and the 25
United responses for airline 2. The counts and percentages for the three airlines
are d
isplayed in one frequency table.