Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Generating tables with predicted probabilities (asclogit)

From   Wameq Raza <>
Subject   st: Generating tables with predicted probabilities (asclogit)
Date   Fri, 28 Sep 2012 13:47:49 +0200

Hi everyone,
I've been using STATA 12 to run a conditional logit model with
alternative specific and case specific variables using the asclogit
command. I've been
able to run everything fine, but I'm trying to generate graphs of
probabilities for the alternative specific variables per the
categories in my dependent
Just to give you a background, I've been modeling the determinants of
health seeking behaviour and have 5 categories of providers (Public,
RMPs, Pharmacists and Others) as my dependent var and have avg cost,
distance and waiting time as alt specific vars along with a battery of
specific vars such as demographics, income and so forth.
At this point, what I want to do is graph the effect of say a change
in cost on probabilities of choosing each of the providers.
In a MNL model, one would predict probability of each of the equations
and then use:

predict p1, equation (#1)
graph twoway (qfit p1 income)

For the asclogit model, I've predicted the probability using
predict p1, pr

But I'm guessing this is predicting the probabilities for the entire
model as opposed to based on provider choices (ie, specific

Can anyone suggest anything I might be able to do?

W A M E Q   R A Z A
*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index