14 Nov
2004
14 Nov
'04
3:29 p.m.
No, this is a good question, because the Zelig help page is wrong. 80
So remember that the distributional assumption for the probit model are
\tilde{pi} = EV = Phi(mu) where mu = x %*% beta
mu is just the parameterization of the systematic component. It's not the
mean of the distribution. Phi is the standard normal CDF with mean 0 and
sigma2 = 1. So you want to find out what's the probability of observing x
%*% beta, given that you think the distribution is Normal(0, 1).
I'll fix that page shortly...
Olivia.
On Sun, 14 Nov 2004, Kate Emans wrote:
Hi Olivia,
I don't think this is a great question, but I'm stumped on this one.
For the log-likelihood of the probit, we know (e.g. from Zelig online help)
that pie = CDF(xi'B) where this is the CDF of a variable mu, distributed
normally.
I don't understand what mu is. If we set mu=xi'B, then CDF(mu)=.5 all the
time. . .
If we set mu= 0, then this is clearly wrong.
Help! Any hints on mu? Is it the mean of all the xi'B's? is it a
parameter to estimate?
Thank you!!!!
Kate
15 Nov
15 Nov
7:07 a.m.
New subject: [gov2001-l] about the interaction effect
Hi Olivia,
For the interaction effect between COOP and TARGET (call it COTAR), when we change the
value of COOP (say from 1 to 2), should we still hold the value of COTAR at its median or
change the value from 1X median(TARGET) to 2 X median(TARGET)? I guess the results could
differ, depending on the method one adopts. Thanks. Yanbo
-----Original Message-----
From: gov2001-l-bounces(a)lists.fas.harvard.edu
[mailto:gov2001-l-bounces@lists.fas.harvard.edu] On Behalf Of Olivia Lau
Sent: 2004?11?14? 20:29
To: gov2001-l(a)lists.fas.harvard.edu
Subject: [gov2001-l] Re: question on #2: what is the mean of the CDF inprobit?
No, this is a good question, because the Zelig help page is wrong. 80
So remember that the distributional assumption for the probit model are
\tilde{pi} = EV = Phi(mu) where mu = x %*% beta
mu is just the parameterization of the systematic component. It's not the
mean of the distribution. Phi is the standard normal CDF with mean 0 and
sigma2 = 1. So you want to find out what's the probability of observing x
%*% beta, given that you think the distribution is Normal(0, 1).
I'll fix that page shortly...
Olivia.
On Sun, 14 Nov 2004, Kate Emans wrote:
Hi Olivia,
I don't think this is a great question, but I'm stumped on this one.
For the log-likelihood of the probit, we know (e.g. from Zelig online help)
that pie = CDF(xi'B) where this is the CDF of a variable mu, distributed
normally.
I don't understand what mu is. If we set mu=xi'B, then CDF(mu)=.5 all the
time. . .
If we set mu= 0, then this is clearly wrong.
Help! Any hints on mu? Is it the mean of all the xi'B's? is it a
parameter to estimate?
Thank you!!!!
Kate
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
7:38 a.m.
New subject: [gov2001-l] about the interaction effect
You should change the value of the interaction term as you change the value
of the constituent terms.
----- Original Message -----
From: "Yanbo Wang" <yanbo(a)mit.edu>
To: <gov2001-l(a)lists.fas.harvard.edu>
Sent: Monday, November 15, 2004 12:07 PM
Subject: [gov2001-l] about the interaction effect
Hi Olivia,
For the interaction effect between COOP and TARGET (call it COTAR), when
we change the value of COOP (say from 1 to 2), should we still hold the
value of COTAR at its median or change the value from 1X median(TARGET) to
2 X median(TARGET)? I guess the results could differ, depending on the
method one adopts. Thanks. Yanbo
-----Original Message-----
From: gov2001-l-bounces(a)lists.fas.harvard.edu
[mailto:gov2001-l-bounces@lists.fas.harvard.edu] On Behalf Of Olivia Lau
Sent: 2004?11?14? 20:29
To: gov2001-l(a)lists.fas.harvard.edu
Subject: [gov2001-l] Re: question on #2: what is the mean of the CDF
inprobit?
No, this is a good question, because the Zelig help page is wrong. 80
So remember that the distributional assumption for the probit model are
\tilde{pi} = EV = Phi(mu) where mu = x %*% beta
mu is just the parameterization of the systematic component. It's not the
mean of the distribution. Phi is the standard normal CDF with mean 0 and
sigma2 = 1. So you want to find out what's the probability of observing x
%*% beta, given that you think the distribution is Normal(0, 1).
I'll fix that page shortly...
Olivia.
On Sun, 14 Nov 2004, Kate Emans wrote:
--------------------------------------------------------------------------------
Hi Olivia,
I don't think this is a great question, but I'm stumped on this one.
For the log-likelihood of the probit, we know (e.g. from Zelig online
help)
that pie = CDF(xi'B) where this is the CDF of a variable mu, distributed
normally.
I don't understand what mu is. If we set mu=xi'B, then CDF(mu)=.5 all
the
time. . .
If we set mu= 0, then this is clearly wrong.
Help! Any hints on mu? Is it the mean of all the xi'B's? is it a
parameter to estimate?
Thank you!!!!
Kate
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
7125
days inactive
7126
days old
gov2001@lists.gking.harvard.edu
2 comments
2 participants
participants (2)
-
olau＠fas.harvard.edu -
yanbo＠MIT.EDU