URGENT: How to estimate Predicted Probabilities in Logit Regression?

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

student95
Posts: 2
Joined: Mon Apr 20, 2020 6:12 am

URGENT: How to estimate Predicted Probabilities in Logit Regression?

Postby student95 » Tue May 19, 2020 11:04 am

Hi,

I have estimated marginal effects at means with the code:

q01.forecast(i) xbf
scalar meanxb = @mean(xbf)
scalar meffectw = @dlogistic(-meanxb)
scalar meffectw = @dlogistic(-@mean(xbf))
vector meffects = meffectw*eq01.@coefs

... But how do I estimate predicted probabilities? Can someone help me with a code like the above-mentioned (or directions) in order to get predicted probabilities (most likely in a vector also)

Thanks!!

EViews Glenn
EViews Developer
Posts: 2642
Joined: Wed Oct 15, 2008 9:17 am

Re: URGENT: How to estimate Predicted Probabilities in Logit Regression?

Postby EViews Glenn » Fri Jun 05, 2020 10:44 am

If you forecast without the "i" option, you'll get the predicted probabilities.


Return to “Estimation”

Who is online

Users browsing this forum: mickeykozzi and 8 guests