I have categorical variables like "Household income", "Urban/rural", "Gender", "Age". I want to find out how many people are all of (for example): Low household income, urban, male, and in age category two.
That is, I don't want to calculate the frequencies of each of these variables separately, but rather, I want to see how many people lie at the intersections of them.
Basically: How do I use SPSS to find out how many people in my dataset are low income urban males between ages 25-33?
Aggregating by the categorical variables can give you all the possible intersections:
dataset declare agg.
aggregate /out = agg /break = Household income Urban_rural Gender AgeGroup /Nintersect = n .
dataset activate agg.
The new dataset now has the count of cases in each intersection of all the categorical variables used as break in the aggregate command.
You could use the crosstab command, from Analyze/Descriptive statistics menu. This wor works best when you want to intersect 2 variables. You may also use the Layer, in you have a 3rd variable
For more than 3 variables, use an if recode:
if age=2 and gender=1... Recodevar=1'.
Fre recodevar.
Mind the overlapping scenarios, so you don't overwrite your recodevar
