I still don't think the exp(lp)/(1+exp(lp)) gonna work. Since this is conditional logit model, while this formula is only used in unconditional ones. By using this, one neglects the information based on stratum. Though I don't know how to solve it to. I am also working on a project on this and I do hope there's someone explaining this problem. Will that be a possibility that the phat can never be estimated as we never know the individual intercept? Disclaimer: This email (including any attachments) is for the use of the intended recipient only and may contain confidential information and/or copyright material. If you are not the intended recipient, please notify the sender immediately and delete this email and all copies from your system. Any unauthorized use, disclosure, reproduction, copying, distribution, or other form of unauthorized dissemination of the contents is expressly prohibited. [[alternative HTML version deleted]]
On Feb 28, 2013, at 5:26 AM, Miss SHENG Lisha wrote:> I still don't think the exp(lp)/(1+exp(lp)) gonna work. Since this is conditional logit model, while this formula is only used in unconditional ones. By using this, one neglects the information based on stratum. Though I don't know how to solve it to. I am also working on a project on this and I do hope there's someone explaining this problem. Will that be a possibility that the phat can never be estimated as we never know the individual intercept? >> [[alternative HTML version deleted]](You are requested to post in palin text.) This appears to be addressed to a thread that appeared almost three years ago. I suspect you have not read all the way to the end of the thread: https://stat.ethz.ch/pipermail/r-help/2010-April/235956.html -- David Winsemius Alameda, CA, USA
I do appreciate this answer. I heard that in SAS, conditional logistic model do predictions in the same way. However, this formula can only deal with in-sample predictions. How about the out-of-sample one? Is it like one of the former responses by Thomas, say, it's impossible to do the out-of-sample prediction??
I'm late to this discussion, but let me try to put it in another context.
Assume that I wanted to know whether kids who live west of their school or
east of
their shool are more likely to be early (some hypothesis about walking slower if
the sun
is in their eyes). So I create a 0/1 variable east/west and get samples of 10
student
arrival times at each of 100 different schools. Fit the model
lm(arrive ~ factor(school) + east.west)
where "arrive" is in some common scale like "minutes since
midnight". Since different
schools could have different starting times for their first class we need an
intercept per
school.
Two questions:
1. Incremental effect: the coefficient of east/west measures the
incredmental effect
across all schools. With n of 1000 it is likely estimated with high precision.
2. Absolute: predict the average arrival time (on the clock) for students.
Conditional logistic is very like this. We have a large number of strata
("schools") with
a small number of observations in each (often only 2 per strata). One can ask
incremental
questions about variables common to all strata, but absolute prediction is
pretty
worthless. a. You can only do it for schools (strata) that have already been
seen and b.
there are so few subjects in each of them that the estimates are very noisy.
The default prediction from clogit is focused on questions of type 1. The
documentation doesn't even bother to mention predictions of type 2, which
would be
probabilities of events. I can think of a way to extract such output from the
routine
(being the author gives some insight), but why would I want to?
Terry Therneau