Forecasting probability

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

Posts: 1
Joined: Thu Nov 01, 2018 7:51 am

Forecasting probability

Postby BTB » Thu Nov 01, 2018 10:44 am

Hi all, I am facing a problem with forecasting probability.

I need to forecast the probability of a crash within the next 24 months in the financial markets with regard to historical 24 months returns and its 95% confidence interval.

I have a database which looks like:

historical returns crash yes or no
from small to large 1 = crash, 0 = no crash
only positive returns
largest value ~ 130%

I estimate an equation which looks like "crash y 24mreturn" and use probit method.
When I click on forecasting then, the graph uses the number of observation on the x axis instead of the return and the values of the x axis don´t exceed the largest value (130% return => crash probability ~75%). However I would need values on the x axis going until 200%.

The next thing is that I can´t add a confidence interval as I can´t touch the field where I would need to type the numbers in.

Please find the graph which I will replicate with my data attached!

I would be very grateful for any support.

Thanks in advance.

Forecasting.JPG (17.89 KiB) Viewed 1757 times

Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 6 guests