Thanks, John.
Alan's suggestion seems to be a logical approach for handling regression
reference categories. More generally about missing/adding REGRESSION
subcommands, I'd need to think about that -- there are other features I
would prefer to see implemented in PSPP first.
Jack
On Thu, Sep 29, 2016 at 10:58:30AM -0400, Jack Drew wrote:
Thanks for the speedy response, Alan.
To be clear: if memory serves SPSS lets you specify the reference value for
a categorical variable. So for a variable with 0/1/2 values, you can
specify '0' as the reference c
Understood. Thank you again.
Jack
___
Pspp-users mailing list
Pspp-users@gnu.org
https://lists.gnu.org/mailman/listinfo/pspp-users
I've always used syntax to create dummy variables and it works the same
in PSPP and SPSS.
If you had a categorical variable X with *three* values 0/1/2 you would
create *two* dummy coded variables like this:
recode x (0=1) (1=0) (2=0) (ELSE=SYSMIS) into x_dum1.
recode x (0=0) (1=1) (2=0) (ELSE=S
Thanks for the speedy response, Alan.
To be clear: if memory serves SPSS lets you specify the reference value for
a categorical variable. So for a variable with 0/1/2 values, you can
specify '0' as the reference category.
However, if I understand you correctly, the method for PSPP is to create a
If I understand your question, you're asking which is is the category
against which each other dummy-coded category is compared?
You select it when you dummy code. When you have K categories, you
create K-1 dummy variables and one group has a zero on all K-1 dummy
variables. That group is the r
I use PSPP (current version 0.10.2) to generate linear regression models.
But, after checking the manual and help archive, I'm still having
difficulty understanding how PSPP treats the reference categories for dummy
variables, and if/how/what PSPP options let you set the reference.
Please could so
