Re: bug in Shapiro Wilk Test

--===============1036614774818774820==
Content-Type: multipart/alternative; boundary="000000000000163f0506526966bb"

--000000000000163f0506526966bb
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

thank you for the heads up.  as you might have noticed on footer of the
reply to this email, while these mailing lists are still monitored most
discussion activity around Octave takes place on our discourse server at
octave.discourse.group.  I'd encourage you to make a post over there. it
sounds like this may be of interest to the maintainer of our statistics
package If you can point out which statistical functions are using that
test and may need to be examined it would help.

On Fri, May 22, 2026 at 8:58=E2=80=AFAM AK <[email protected]> wro=
te:

> Good afternoon,
>
> This concerns the Shapiro-Wilk test for normal distribution in the field
> of mathematical statistics.
> Did you take into account the latest research findings from the 2014
> publication by Hanusz & Tarasi=C5=84ska (1) when calculating the coeffici=
ents
> for the W-statistic? Both authors point out an error in the original work
> by Shapiro and Wilk.
>
> If you have not yet corrected the coefficient calculation, this could lea=
d
> to incorrect decisions in the case of the so-called H0 hypothesis.
>
> I hope you find this helpful.
>
> Best regards
> Alexander Kud
>
>
> (1) Zofia Hanusz & Joanna Tarasi=C5=83ska (2014) Simulation Study on Impr=
oved
> Shapiro=E2=80=93Wilk Tests for Normality, Communications in Statistics - =
Simulation
> and Computation, 43:9, 2093-2105, DOI: 10.1080/03610918.2013.844835
> Link to this article: http://dx.doi.org/10.1080/03610918.2013.844835
>
> Abstract
>
> The article concerns tests for normality based on the Shapiro=E2=80=93Wil=
k W
> statistic. The constants in the test statistic are recalculated as those
> given in Shapiro and Wilk are incorrect. The empirical significance level=
s
> and power of improved tests have been evaluated in simulation study and
> compared to original ones. The improved tests were also applied to the
> multivariate case. In this case, we consider two implementations of the W
> statistic, the first one proposed by Srivastava and Hui and the other by
> Hanusz and Tarasinska. Empirical size of tests and their power have been
> compared to the Henze=E2=80=93Zirkler test.
>
>
>
>
> ---------------------------------------------------
> Dr. Alexander Kud
> Scientist in Physical Chemistry
>
> [email protected]
> ---------------------------------------------------
>
>
> ----------
> We are transitioning to a web based forum
> for community help discussions at
> https://octave.discourse.group/c/help
>

--000000000000163f0506526966bb
Content-Type: text/html; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr">thank you for the heads up.=C2=A0 as you might have notice=
d on footer of the reply to this email, while these mailing lists are still=
 monitored most discussion activity around Octave takes place on our discou=
rse server at octave.discourse.group.=C2=A0 I&#39;d encourage you to make a=
 post over there. it sounds like this may be of interest to the maintainer =
of our statistics package If you can point out which statistical functions =
are using that test and may need to be examined it would help.=C2=A0</div><=
br><div class=3D"gmail_quote gmail_quote_container"><div dir=3D"ltr" class=
=3D"gmail_attr">On Fri, May 22, 2026 at 8:58=E2=80=AFAM AK &lt;<a href=3D"m=
ailto:[email protected]">[email protected]</a>&gt; wrote:=
<br></div><blockquote class=3D"gmail_quote" style=3D"margin:0px 0px 0px 0.8=
ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><u></u>

 =20

   =20
 =20
  <div bgcolor=3D"#ffffff">
    <p><font face=3D"Menlo">Good afternoon,<br>
        <br>
        This concerns the Shapiro-Wilk test for normal distribution in
        the field of mathematical statistics.<br>
        Did you take into account the latest research findings from the
        2014 publication by Hanusz &amp; Tarasi=C5=84ska (1) when calculati=
ng
        the coefficients for the W-statistic? Both authors point out an
        error in the original work by Shapiro and Wilk.<br>
        <br>
        If you have not yet corrected the coefficient calculation, this
        could lead to incorrect decisions in the case of the so-called
        H0 hypothesis.<br>
        <br>
        I hope you find this helpful.<br>
        <br>
        Best regards<br>
        Alexander Kud<br>
        <br>
        <br>
        (1) Zofia Hanusz &amp; Joanna Tarasi=C5=83ska (2014) Simulation Stu=
dy
        on Improved Shapiro=E2=80=93Wilk Tests for Normality, Communication=
s in
        Statistics - Simulation and Computation, 43:9, 2093-2105, DOI:
        10.1080/03610918.2013.844835<br>
        Link to this article:
        <a href=3D"http://dx.doi.org/10.1080/03610918.2013.844835" target=
=3D"_blank">http://dx.doi.org/10.1080/03610918.2013.844835</a><br>
        <br>
        Abstract<br>
        <br>
        The article concerns tests for normality based on the
        Shapiro=E2=80=93Wilk W statistic. The constants in the test statist=
ic
        are recalculated as those given in Shapiro and Wilk are
        incorrect. The empirical significance levels and power of
        improved tests have been evaluated in simulation study and
        compared to original ones. The improved tests were also applied
        to the multivariate case. In this case, we consider two
        implementations of the W statistic, the first one proposed by
        Srivastava and Hui and the other by Hanusz and Tarasinska.
        Empirical size of tests and their power have been compared to
        the Henze=E2=80=93Zirkler test.<br>
        <br>
        <br>
        <br>
        <br>
        ---------------------------------------------------<br>
        Dr. Alexander Kud<br>
        Scientist in Physical Chemistry<br>
        <br>
        <a href=3D"mailto:[email protected]" target=3D"_blank">ale=
[email protected]</a><br>
        ---------------------------------------------------=C2=A0<br>
      </font><br>
    </p>
  </div>

<br>
----------<br>
We are transitioning to a web based forum<br>
for community help discussions at<br>
<a href=3D"https://octave.discourse.group/c/help" rel=3D"noreferrer" target=
=3D"_blank">https://octave.discourse.group/c/help</a><br>
</blockquote></div>

--000000000000163f0506526966bb--


--===============1036614774818774820==
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: base64
Content-Disposition: inline

Ci0tLS0tLS0tLS0KV2UgYXJlIHRyYW5zaXRpb25pbmcgdG8gYSB3ZWIgYmFzZWQgZm9ydW0KZm9y
IGNvbW11bml0eSBoZWxwIGRpc2N1c3Npb25zIGF0Cmh0dHBzOi8vb2N0YXZlLmRpc2NvdXJzZS5n
cm91cC9jL2hlbHAK

--===============1036614774818774820==--