Re: [Boost-users] [math/distributions] Problem using inv-chi**2 and quantiles

Subject: Re: [Boost-users] [math/distributions] Problem using inv-chi**2 and quantiles
From: Paul Johnson (sa212+boost_at_[hidden])
Date: 2011-06-14 11:56:18

On 14/06/2011 14:51, Paul A. Bristow wrote:

>> Can anyone tell me what I'm doing wrong?
>
> Well, using EXCEL for a start ;-)

Well, that's why I'm here :)

> No - seriously, I can't see at a glance why they differ, and since this distribution has been added
> recently, a mistake as always possible.
>
> I'll look more closely as soon as I can, but it won't be today (but at least you know you are on my
> TODO list, and can mail me privately).

Excellent - thanks very much.

> PS As a very quick idea - Is the /2 in (1+$C$3)/2 the cause of the difference?

Excel can't calculate the lower limit if I take out the /2. However, if 
I take out the /2 in the upper limit ((1-$C$3)/2 => (1-$C$3)) then it 
produces an answer which is closer to the boost answer. For 17 events, 
Excel now produces 25.50, compared to boost's 25.98.

-Paul