Dropping outliers

For econometric discussions not necessarily related to EViews.

Moderators: EViews Gareth, EViews Moderator

Steffie Kremer
Posts: 2
Joined: Wed Aug 01, 2012 5:36 am

Dropping outliers

Postby Steffie Kremer » Wed Aug 01, 2012 5:42 am

Hello,

I have an equation including the change in the futures rate and a dummy variable on days when there was an FOMC announcement (then the dummy is 1). Could somebody please tell me how I can drop outliers on the change in the futures rate (for example, changes in futures rates over 0.05), but that it drops it only when my dummy variable is equal to zero? (So there is no FOMC announcement?)

Thanks!

EViews Glenn
EViews Developer
Posts: 2682
Joined: Wed Oct 15, 2008 9:17 am

Re: Dropping outliers

Postby EViews Glenn » Wed Aug 01, 2012 9:56 am

Use the smpl command. Something like

Code: Select all

smpl if @abs(futures)>.05 and dummy=0

Steffie Kremer
Posts: 2
Joined: Wed Aug 01, 2012 5:36 am

Re: Dropping outliers

Postby Steffie Kremer » Wed Aug 01, 2012 10:57 am

Thank you for the tip!
The only thing is that if I use this equation, the large changes that are related to an FOMC announcement are also dropped, while these should not be dropped.
So I would like to drop all variables that satisfy the equation:futures >0.05 AND dummy=0. (so not futures>0.05 and dummy =1)

Thank you very much.


Return to “Econometric Discussions”

Who is online

Users browsing this forum: No registered users and 1 guest