[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: the impute command
At 10:56 AM 5/19/2004 -0400, Robert Bozick wrote:
It doesn't matter. It will basically drop a variable for you, even though
it does not say so.
I have a few questions concerning the impute command.
I am trying to impute values to a dichotomous variable coded 1 if
individuals were employed and 0 if they were not.
First, does the impute command treat all the predictor variables in the
same way that a regression command does? More specifically, if I am using
a set of dummy variables, do I omit one category? I ask this because I
was doing some test runs and I included ALL variables in the impute
command and it did not give me the message "variable was dropped due to
Second, is there a way to specify the impute command to round imputed
values either to 1 or 0 depending on the prediction (e.g. predicted values
0 - .49 become 0 and values .50-1 become 1) ?
You could just follow the impute command with a recode command. Keep in
mind that the imputed values could be less than 0 or greater than 1. So,
Recode y (min/.50 = 0)(.50/max = 1)
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
* For searches and help try: