[...]
>
> Hi Dave
>
> I'm forwarding your e-mail to the octave mailing list (this is the
> mailing list for octave forge packages, but ranks is part of octave
> core). Also, the best place to submit this would be the patch tracker
> on savannah http://savannah.gnu.org/patch/?group=octave
>
> One
2007, 2008, 2009 Kurt Hornik
+## 2007, 2008, 2009 Kurt Hornik
+## Copyright (C) 2012 Dave Goel
##
## This file is part of Octave.
##
## Octave is free software; you can redistribute it and/or modify it
-## under the terms of the GNU General Public License as published by
-## the Free Software Found
2000, 2002, 2004, 2005, 2006,
-## 2007, 2008, 2009 Kurt Hornik
+## 2007, 2008, 2009 Kurt Hornik
+## Copyright (C) 2012 Dave Goel
##
## This file is part of Octave.
##
## Octave is free software; you can redistribute it and/or modify it
-## under the terms of the GNU General P
>
> Søren writes:
>> There seems to be no easy way to achieve a cummax (a simple O(n)
>> operation) while avoiding loops. There are some ways to achieve
>> it[1], but they all end up being > O(n).
>
> It's been a while, but I thought I should write and say that the
> excellent Jaroslav Ha
> Looks like code and docs are not in sync.
I guess the only way to avoid touching the code in these examples is
to swap "x" and "y" in the docs - that will make the p value
consistent with the code, but then, of course, the meaning of the sign
of the corresponding statistic gets flipped around.
Dave Goel <[EMAIL PROTECTED]> writes:
> Consider a=[1 2 3 4], and b=[5 6 7 8].
>
> The null is a = b. The alt. is !=.
>
> We get
>
> octave:3> kolmogorov_smirnov_test_2 (a,b,"!=")
> pval: 0.0366311
>
>
>
> Now consider an even mo
"Jaroslav Hajek" <[EMAIL PROTECTED]> writes:
[...]
>
> Just out of curiosity, what use is "cumulative p-norm" for?
>
Oh, was that to me? As in, why do I want a cummax? There have been
several separate issues that all hinged on this recently. The most
recent is when I wanted to take a functio
Dave Goel <[EMAIL PROTECTED]> writes:
> Why re-implement the wheel? We should simply use the exact same
> logic and facilities used by tmpcumsum.
Sorry, I meant: cumsum.
>
> Nonetheless, here is a for loop that handles the n-dimensional case.
> I am attaching the 3 files a
>
> Yeah, I can't come up with anything of the top of my head. But I'll make
> you a deal. If you write an m-file version using for-loops, that handle
> the N-dimensional case, then I'll re-implement it in C++.
I am including here an m-version, tested, and also attaching it. But,
really, I sta
-Original Message-
Søren Hauberg <[EMAIL PROTECTED]> writes:
> tor, 30 10 2008 kl. 17:05 -0400, skrev Dave Goel:
>> There seems to be no easy way to achieve a cummax (a simple O(n)
>> operation) while avoiding loops. There are some ways to achieve
>>
There seems to be no easy way to achieve a cummax (a simple O(n)
operation) while avoiding loops. There are some ways to achieve
it[1], but they all end up being > O(n).
Thinking about cummax, that is about the only thing in this category
that one cannot achieve using cumsum (and/or cumprod).
I
I have looked up matlab (TM)'s answers at a friend's workstation:
>
>> betainc (.75, 2047, .5)
>
> 4.437e-258
matlab: 4.437e-258
>
>> betainc (.85, 2047, .5)
>
> 0
matlab: 1.0659e-146
> ^^ If it returned a zero for .85, it should either do likewise for
> .75, or it should return a better ans
>> [ tcdf bug reported]
>>
>>
>
> This is an octave core function and so issues should be reported to
> [EMAIL PROTECTED] That being said you should upgrade from 2.1.73 as that
> is a very old version of Octave. The latest stable release is 3.0.1.
> Also the t_cdf function had its name changed
3.0609e-14
octave:25> t_cdf (-31.1,4094)
ans = 1.2780e-14
-Original Message-
Dave Goel <[EMAIL PROTECTED]> writes:
> The 0, reported in line 10 below, is clearly not due to an "underflow"
> somewhere, because, as you see below, the values go as far down as
&g
The 0, reported in line 10 below, is clearly not due to an "underflow"
somewhere, because, as you see below, the values go as far down as
10^-247.
octave:9> t_cdf (-26.0,4094)
ans = 5.2275e-14
octave:10> t_cdf (-26.534,4094)
ans = 0
octave:11> t_cdf (-26.6,4094)
ans = 2.6505e-15
octave:16>
15 matches
Mail list logo
