You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@commons.apache.org by Phil Steitz <st...@yahoo.com> on 2003/06/04 22:31:37 UTC
Re: [math] [OT]UnivariateImpl - when sumsq ~ xbar*xbar*((double) n)
--- Al Chou <ho...@yahoo.com> wrote:
> --- Phil Steitz <ph...@steitz.com> wrote:
> > Al Chou wrote:
> > > --- Phil Steitz <ph...@steitz.com> wrote:
> > >
> > >>Al Chou wrote:
> > >>
> > >>>Uh, did we drop the idea of using the "corrected two-pass" algorithm for
> > >>
> > >>the
> > >>
> > >>>variance in the non-rolling case? I excerpted that thread below.
> > >>
> > >>I was going to mention that. The discussion above regards the
> > >>"non-stored vector" approach (UnivariateImpl). I submitted some patches
> > >>to the "stored" classes (StoredUnivariate,AbstractStoreUnivariate) last
> > >>weekend (adding percentiles --
> > >>http://issues.apache.org/bugzilla/show_bug.cgi?id=20377) and I was
> > >>waiting for them to get committed before suggesting this
> > >>change/submitting the patch.
> > >>
> > >>Given our recent NR entanglements, we need to make sure that if and when
> > >>we apply that patch we document using the original source of the formula.
> > >>
> > >>Thanks for the remider.
> > >
> > >
> > > Cool, thanks. We can reference the original journal article, though I
> > > personally would feel better if we had a copy of it so we could
> > specifically
> > > reference the equation number in it. Anybody have easy access to a
> library
> > > that carries "American Statistician"?
> > >
> > I am in the process of renewing my ASA membership and getting set up to
> > access JSTOR, where I can snag this. Will take a couple of days, but I
> > will chase this down.
>
>
> OK, I hope the article we want is available online, given that it's pretty
> old.
>
Strangely, it's actually the recent stuff that is not available. JSTOR has
American Statistician from 1947-1997. If you want a chuckle, have a look at
http://www.jstor.org/about/movingwall.html, which explains the rationale for
this.
Phil
>
> Al
>
> =====
> Albert Davidson Chou
>
> Get answers to Mac questions at http://www.Mac-Mgrs.org/ .
>
> __________________________________
> Do you Yahoo!?
> Yahoo! Calendar - Free online calendar with sync to Outlook(TM).
> http://calendar.yahoo.com
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: commons-dev-unsubscribe@jakarta.apache.org
> For additional commands, e-mail: commons-dev-help@jakarta.apache.org
>
__________________________________
Do you Yahoo!?
Yahoo! Calendar - Free online calendar with sync to Outlook(TM).
http://calendar.yahoo.com
---------------------------------------------------------------------
To unsubscribe, e-mail: commons-dev-unsubscribe@jakarta.apache.org
For additional commands, e-mail: commons-dev-help@jakarta.apache.org
Re: [math] [OT]UnivariateImpl - when sumsq ~ xbar*xbar*((double) n)
Posted by Phil Steitz <st...@yahoo.com>.
--- Al Chou <ho...@yahoo.com> wrote:
> --- "Mark R. Diggory" <md...@latte.harvard.edu> wrote:
> > Al Chou wrote:
> > >>>OK, I hope the article we want is available online, given that it's
> pretty
> > >>>old.
> > >>>
> > >>>
> > >>Strangely, it's actually the recent stuff that is not available. JSTOR
> has
> > >>American Statistician from 1947-1997. If you want a chuckle, have a look
> > at
> > >>http://www.jstor.org/about/movingwall.html, which explains the rationale
> > for
> > >>this.
> > >>
> > >
> > >It's all about money, eh? Well, as long as we have access to what we
> need,
> > >that's fine. Incidentally, I'm much more accustomed to seeing online
> > editions
> > >directly from the publisher, which explains why I expected only issues
> more
> > >recent than some date to be available.
> > >
> > >
> > >Al
> >
> >
> > Yes, the deal is that JStor would undercut the publishers profits from
> > printing if they exposed an article too soon. JStor isn't a "publisher",
> > just a "digital library". Its the publishers choice to provide access
> > online to the article, if they decide not to release it online, its to
> > promote subscriptions to the printed copies.
> >
> > IMHO, in cases where we can't find references to content that is
> > publicly available, we should feel ok about referencing a
> > "semi-protected" source like a journal article as long as its abstract
> > is public and its content is accessible at educational institutions.
> > -M.
>
> I agree that references to printed journal articles should be sufficient if
> there aren't online references. There are certainly scientific authors whose
> publications reference works that are hard to obtain, and that seems to be
> acceptable to the publishers even if it's frustrating to the readers. I hope
> we do at least somewhat better than that.
>
I agree. We should *always* favor references to freely available online
resources (i.e., no subscription required). In some cases, we will have to
refer to books or journals. What is most important is that we provide clear
definitions and stick to standard algorithms. Hopefully, the need for offline
resources will be mostly limited to references, as in the this case. What I
mean by "references" is attirbution and/or support for assertions that we make
in our documentation about algorithms or computations. In the present case,
the reference is necessary to attribute the source of the computational formula
and the derivation of its claimed properties (better accuracy and no bias).
> Al
>
> =====
> Albert Davidson Chou
>
> Get answers to Mac questions at http://www.Mac-Mgrs.org/ .
>
> __________________________________
> Do you Yahoo!?
> Yahoo! Calendar - Free online calendar with sync to Outlook(TM).
> http://calendar.yahoo.com
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: commons-dev-unsubscribe@jakarta.apache.org
> For additional commands, e-mail: commons-dev-help@jakarta.apache.org
>
__________________________________
Do you Yahoo!?
Yahoo! Calendar - Free online calendar with sync to Outlook(TM).
http://calendar.yahoo.com
---------------------------------------------------------------------
To unsubscribe, e-mail: commons-dev-unsubscribe@jakarta.apache.org
For additional commands, e-mail: commons-dev-help@jakarta.apache.org
Re: [math] [OT]UnivariateImpl - when sumsq ~ xbar*xbar*((double) n)
Posted by Al Chou <ho...@yahoo.com>.
--- "Mark R. Diggory" <md...@latte.harvard.edu> wrote:
> Al Chou wrote:
> >>>OK, I hope the article we want is available online, given that it's pretty
> >>>old.
> >>>
> >>>
> >>Strangely, it's actually the recent stuff that is not available. JSTOR has
> >>American Statistician from 1947-1997. If you want a chuckle, have a look
> at
> >>http://www.jstor.org/about/movingwall.html, which explains the rationale
> for
> >>this.
> >>
> >
> >It's all about money, eh? Well, as long as we have access to what we need,
> >that's fine. Incidentally, I'm much more accustomed to seeing online
> editions
> >directly from the publisher, which explains why I expected only issues more
> >recent than some date to be available.
> >
> >
> >Al
>
>
> Yes, the deal is that JStor would undercut the publishers profits from
> printing if they exposed an article too soon. JStor isn't a "publisher",
> just a "digital library". Its the publishers choice to provide access
> online to the article, if they decide not to release it online, its to
> promote subscriptions to the printed copies.
>
> IMHO, in cases where we can't find references to content that is
> publicly available, we should feel ok about referencing a
> "semi-protected" source like a journal article as long as its abstract
> is public and its content is accessible at educational institutions.
> -M.
I agree that references to printed journal articles should be sufficient if
there aren't online references. There are certainly scientific authors whose
publications reference works that are hard to obtain, and that seems to be
acceptable to the publishers even if it's frustrating to the readers. I hope
we do at least somewhat better than that.
Al
=====
Albert Davidson Chou
Get answers to Mac questions at http://www.Mac-Mgrs.org/ .
__________________________________
Do you Yahoo!?
Yahoo! Calendar - Free online calendar with sync to Outlook(TM).
http://calendar.yahoo.com
---------------------------------------------------------------------
To unsubscribe, e-mail: commons-dev-unsubscribe@jakarta.apache.org
For additional commands, e-mail: commons-dev-help@jakarta.apache.org
Re: [math] [OT]UnivariateImpl - when sumsq ~ xbar*xbar*((double)
n)
Posted by "Mark R. Diggory" <md...@latte.harvard.edu>.
Al Chou wrote:
>>>OK, I hope the article we want is available online, given that it's pretty
>>>old.
>>>
>>>
>>Strangely, it's actually the recent stuff that is not available. JSTOR has
>>American Statistician from 1947-1997. If you want a chuckle, have a look at
>>http://www.jstor.org/about/movingwall.html, which explains the rationale for
>>this.
>>
>>
>
>It's all about money, eh? Well, as long as we have access to what we need,
>that's fine. Incidentally, I'm much more accustomed to seeing online editions
>directly from the publisher, which explains why I expected only issues more
>recent than some date to be available.
>
>
>Al
>
Yes, the deal is that JStor would undercut the publishers profits from
printing if they exposed an article too soon. JStor isn't a "publisher",
just a "digital library". Its the publishers choice to provide access
online to the article, if they decide not to release it online, its to
promote subscriptions to the printed copies.
IMHO, in cases where we can't find references to content that is
publicly available, we should feel ok about referencing a
"semi-protected" source like a journal article as long as its abstract
is public and its content is accessible at educational institutions.
-M.
---------------------------------------------------------------------
To unsubscribe, e-mail: commons-dev-unsubscribe@jakarta.apache.org
For additional commands, e-mail: commons-dev-help@jakarta.apache.org
Re: [math] [OT]UnivariateImpl - when sumsq ~ xbar*xbar*((double) n)
Posted by Al Chou <ho...@yahoo.com>.
--- Phil Steitz <st...@yahoo.com> wrote:
> --- Al Chou <ho...@yahoo.com> wrote:
> > --- Phil Steitz <ph...@steitz.com> wrote:
> > > Al Chou wrote:
> > > > --- Phil Steitz <ph...@steitz.com> wrote:
> > > > Cool, thanks. We can reference the original journal article, though I
> > > > personally would feel better if we had a copy of it so we could
> > > specifically
> > > > reference the equation number in it. Anybody have easy access to a
> > library
> > > > that carries "American Statistician"?
> > > >
> > > I am in the process of renewing my ASA membership and getting set up to
> > > access JSTOR, where I can snag this. Will take a couple of days, but I
> > > will chase this down.
> >
> >
> > OK, I hope the article we want is available online, given that it's pretty
> > old.
>
>
> Strangely, it's actually the recent stuff that is not available. JSTOR has
> American Statistician from 1947-1997. If you want a chuckle, have a look at
> http://www.jstor.org/about/movingwall.html, which explains the rationale for
> this.
It's all about money, eh? Well, as long as we have access to what we need,
that's fine. Incidentally, I'm much more accustomed to seeing online editions
directly from the publisher, which explains why I expected only issues more
recent than some date to be available.
Al
=====
Albert Davidson Chou
Get answers to Mac questions at http://www.Mac-Mgrs.org/ .
__________________________________
Do you Yahoo!?
Yahoo! Calendar - Free online calendar with sync to Outlook(TM).
http://calendar.yahoo.com
---------------------------------------------------------------------
To unsubscribe, e-mail: commons-dev-unsubscribe@jakarta.apache.org
For additional commands, e-mail: commons-dev-help@jakarta.apache.org