inverse quantile function

For making suggestions and/or requests for new features you'd like added to EViews.

Moderators: EViews Gareth, EViews Moderator

startz
Non-normality and collinearity are NOT problems!
Posts: 3775
Joined: Wed Sep 17, 2008 2:25 pm

inverse quantile function

Postby startz » Wed Jan 21, 2009 2:35 pm

How about an inverse quantile function, the inverse of @quantile?

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 13319
Joined: Tue Sep 16, 2008 5:38 pm

Re: inverse quantile function

Postby EViews Gareth » Wed Jan 21, 2009 2:42 pm

What would it do?

Am I missing something or isn't that just a rank function (i.e. the @ranks function)
Follow us on Twitter @IHSEViews

startz
Non-normality and collinearity are NOT problems!
Posts: 3775
Joined: Wed Sep 17, 2008 2:25 pm

Re: inverse quantile function

Postby startz » Wed Jan 21, 2009 3:00 pm

QMS Gareth wrote:What would it do?

Am I missing something or isn't that just a rank function (i.e. the @ranks function)


So that's what the @ranks function does!

Actually, I think the asnswer is "not quite." You would need @ranks()/@nobs.

More to the point, @quantile returns a single value, which is what I was looking for in an "inverse quantile" function. I wanted to know what quantile was associated with the number 72.6, which might not even be in the dataset.

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 13319
Joined: Tue Sep 16, 2008 5:38 pm

Re: inverse quantile function

Postby EViews Gareth » Wed Jan 21, 2009 3:18 pm

Something like:

Code: Select all

series dd=x>=72.6
scalar invquant = @sum(dd)/@nobs
Follow us on Twitter @IHSEViews

startz
Non-normality and collinearity are NOT problems!
Posts: 3775
Joined: Wed Sep 17, 2008 2:25 pm

Re: inverse quantile function

Postby startz » Wed Jan 21, 2009 3:29 pm

QMS Gareth wrote:Something like:

Code: Select all

series dd=x>=72.6
scalar invquant = @sum(dd)/@nobs


Well yes. Perhaps version 8 could have a function that did this so us slower types wouldn't need help figuring it out. Even better, a function where the cut point could be general, instead of being hard coded at 72.6 :wink:

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 13319
Joined: Tue Sep 16, 2008 5:38 pm

Re: inverse quantile function

Postby EViews Gareth » Wed Jan 21, 2009 4:12 pm

We're a little far off from thinking about version 8 at the moment...
Follow us on Twitter @IHSEViews


Return to “Suggestions and Requests”

Who is online

Users browsing this forum: No registered users and 26 guests