[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: another svr problem
My data has replicate weights and so I am using the svr command with logit.
However, I find that the estimates are quite different from those obtained
from running the logit command without weights. I thought by correcting for
weighted data in the svr command we just adjust the standard error up, and
the point estimates should essentially remain the same. Am I missing
* For searches and help try: