Path: csiph.com!v102.xanadu-bbs.net!xanadu-bbs.net!eternal-september.org!feeder.eternal-september.org!feeds.phibee-telecom.net!newsfeed.xs4all.nl!newsfeed1a.news.xs4all.nl!xs4all!post.news.xs4all.nl!not-for-mail
MIME-Version: 1.0
Date: Fri, 8 May 2015 10:53:28 +0000
Subject: about orthogonal series
From: tahiri noria <tahiri.noria1@gmail.com>
To: perktold@email.unc.edu, python-list@python.org, josef.pktd@gmail.com
Content-Type: multipart/alternative; boundary=047d7bb03ed2a1867205158fd670
Precedence: list
Newsgroups: comp.lang.python
Message-ID: <mailman.233.1431082808.12865.python-list@python.org>
Lines: 56
NNTP-Posting-Host: 2001:888:2000:d::a6
Xref: csiph.com comp.lang.python:90265

--047d7bb03ed2a1867205158fd670
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

hello,

I read your article on the blog: http://jpktd.blogspot.com/ about
orthogonal series estimation , I would like to ask you if you allow .
First, I based on Article Sam Efromovich about "Orthogonal series density
estimates" .

he worked with the Fourier series with a compact support assumed [0,1],
whose aim is to estimate the probability density function. and it is said
in his Article that:


"The choice depends Primarily we of the carrier density. In general, When
the real line (-=E2=88=9E, =E2=88=9E) or the half line [0, =E2=88=9E) are t=
he support, Hermite and
Laguerre Then series are recommended; 3,17,23,24 see Refs. If f: has a
compact carrier, for instance [0, 1], Then trigonometric (or Fourier)
series are recommended. "

my question is that if I wanted to draw my probability density function on
a support [-2, -2] (because my data focus on -1 or 1) .What should I do?
is that these results are necessarily  just to support [0,1] for fourier
series ?

Cordially

TAHIRI Noria

--047d7bb03ed2a1867205158fd670
Content-Type: text/html; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr">hello,<div><br></div><div><div>I read your article on the =
blog: <a href=3D"http://jpktd.blogspot.com/">http://jpktd.blogspot.com/</a>=
 about orthogonal series estimation , I would like to ask you if you allow =
. First, I based on Article Sam Efromovich about &quot;Orthogonal series de=
nsity estimates&quot; .</div><div><div><br></div><div>he worked with the Fo=
urier series with a compact support assumed [0,1], whose aim is to estimate=
 the probability density function. and it is said in his Article that:</div=
></div><div><br></div><div><br></div><div>&quot;The choice depends Primaril=
y we of the carrier density. In general, When the real line (-=E2=88=9E, =
=E2=88=9E) or the half line [0, =E2=88=9E) are the support, Hermite and Lag=
uerre Then series are recommended; 3,17,23,24 see Refs. If f: has a compact=
 carrier, for instance [0, 1], Then trigonometric (or Fourier) series are r=
ecommended. &quot;</div><div><br></div><div>my question is that if I wanted=
 to draw my probability density function on a support [-2, -2] (because my =
data focus on -1 or 1) .What should I do?</div><div>is that these results a=
re necessarily =C2=A0just to support [0,1] for fourier series ?</div></div>=
<div><br></div><div>Cordially</div><div><br></div><div>TAHIRI Noria</div></=
div>

--047d7bb03ed2a1867205158fd670--