[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: Sequential or hierarchical regression
At 09:17 PM 11/4/2004 -0800, Kang, Eugene wrote:
I just looked at -hireg-. Something to be careful of: It does not do a
listwise deletion of missing data for all variables in the final model,
e.g. I just did a test where the first regression had 500 cases and the
addition of more variables shrunk the N to 405 cases. I believe you should
be analyzing the same cases throughout it you are going to do incremental F
tests like this.
I am doing a sequential multiple regression where I start with the base
model: y = a + b1x1 + b2x2
followed by the full model: y = a = b1x1 + b2x2 + b3x3 + b4x4
Try findit hireg and install this program. It does what you want if I
understand you correctly.
A workaround is to select only cases with nonmissing values, e.g.
hireg y (x1 x2) (x3 x4) if !missing(y, x1, x2, x3, x4)
If I am reading sw.ado right (which I may not be), -sw- gets around this
problem by dropping missing data cases temporarily and then restoring the
original data set.
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: