a bug with Student t-value??

[huaru wang]

Hello, every one,

Using the qt() function in R, I got a different Student t-value with the
Student t table.
e.g. the return value of function qt(0.95,9) is 1.833, while in table it is
2.262.

I do not know why the difference exists.   I guess it may be a bug in R.
--
Íõ»¯Èå ²©Ê¿Ñо¿Éú
±±¾©Ê¦·¶´óѧ¾°¹ÛÉú̬Óë¿É³ÖÐøÐÔ¿ÆѧÑо¿ÖÐÐÄ
±±¾©Êк£µíÇøнֿÚÍâ´ó½Ö19ºÅ±±¾©Ê¦·¶´óѧÉúÃü¿ÆѧѧԺ 100875
Huaru Wang
PhD Candidate, CLESS, College of Life Science, Beijing Normal University
Tel: 010 - 5880 5812
Cell phone:[phone]
No.19 Xinjiekouwai Street, Beijing 1000875

        [[alternative HTML version deleted]]


______________________________________________
R-help@... mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[Sunny Srivastava]

Hi Huaru,
Are you sure you are looking at 0.95 and NOT 0.975?

as qt(0.975,9) = 2.262

generally tables are given for alpha/2 (alpha=0.05 in your case)
significance.

Please check carefully.

Thx,
S.

On Sat, Nov 7, 2009 at 4:02 AM, huaru wang <huaru.wang@...> wrote:

> Hello, every one,
>
> Using the qt() function in R, I got a different Student t-value with the
> Student t table.
> e.g. the return value of function qt(0.95,9) is 1.833, while in table it is
> 2.262.
>
> I do not know why the difference exists.   I guess it may be a bug in R.
> --
> Íõ»¯Èå ²©Ê¿Ñо¿Éú
> ±±¾©Ê¦·¶´óѧ¾°¹ÛÉú̬Óë¿É³ÖÐøÐÔ¿ÆѧÑо¿ÖÐÐÄ
> ±±¾©Êк£µíÇøнֿÚÍâ´ó½Ö19ºÅ±±¾©Ê¦·¶´óѧÉúÃü¿ÆѧѧԺ 100875
> Huaru Wang
> PhD Candidate, CLESS, College of Life Science, Beijing Normal University
> Tel: 010 - 5880 5812
> Cell phone:[phone]
> No.19 Xinjiekouwai Street, Beijing 1000875
>
>        [[alternative HTML version deleted]]
>
>
> ______________________________________________
> R-help@... mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
>

        [[alternative HTML version deleted]]


______________________________________________
R-help@... mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[huaru wang]

Hi, Sunny,

   Sorry for my mistake. Thank you for your correction.

Thx,

Huaru

2009/11/7 Sunny Srivastava <research.baba@...>

> Hi Huaru,
> Are you sure you are looking at 0.95 and NOT 0.975?
>
> as qt(0.975,9) = 2.262
>
> generally tables are given for alpha/2 (alpha=0.05 in your case)
> significance.
>
>
> Please check carefully.
>
> Thx,
> S.
>
>  On Sat, Nov 7, 2009 at 4:02 AM, huaru wang <huaru.wang@...> wrote:
>
>>  Hello, every one,
>>
>> Using the qt() function in R, I got a different Student t-value with the
>> Student t table.
>> e.g. the return value of function qt(0.95,9) is 1.833, while in table it
>> is
>> 2.262.
>>
>> I do not know why the difference exists.   I guess it may be a bug in R.
>> --
>> Íõ»¯Èå ²©Ê¿Ñо¿Éú
>> ±±¾©Ê¦·¶´óѧ¾°¹ÛÉú̬Óë¿É³ÖÐøÐÔ¿ÆѧÑо¿ÖÐÐÄ
>> ±±¾©Êк£µíÇøнֿÚÍâ´ó½Ö19ºÅ±±¾©Ê¦·¶´óѧÉúÃü¿ÆѧѧԺ 100875
>> Huaru Wang
>> PhD Candidate, CLESS, College of Life Science, Beijing Normal University
>> Tel: 010 - 5880 5812
>> Cell phone:[phone]
>> No.19 Xinjiekouwai Street, Beijing 1000875
>>
>>        [[alternative HTML version deleted]]
>>
>>
>> ______________________________________________
>> R-help@... mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide
>> http://www.R-project.org/posting-guide.html<http://www.r-project.org/posting-guide.html>
>> and provide commented, minimal, self-contained, reproducible code.
>>
>>
>

--
Íõ»¯Èå ²©Ê¿Ñо¿Éú
±±¾©Ê¦·¶´óѧ¾°¹ÛÉú̬Óë¿É³ÖÐøÐÔ¿ÆѧÑо¿ÖÐÐÄ
±±¾©Êк£µíÇøнֿÚÍâ´ó½Ö19ºÅ±±¾©Ê¦·¶´óѧÉúÃü¿ÆѧѧԺ 100875
Huaru Wang
PhD Candidate, CLESS, College of Life Science, Beijing Normal University
Tel: 010 - 5880 5812
Cell phone:[phone]
No.19 Xinjiekouwai Street, Beijing 1000875

        [[alternative HTML version deleted]]


______________________________________________
R-help@... mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[Ted.Harding-2]

On 07-Nov-09 09:02:38, huaru wang wrote:

> Hello, every one,
>
> Using the qt() function in R, I got a different Student t-value
> with the Student t table.
> e.g. the return value of function qt(0.95,9) is 1.833, while in
> table it is 2.262.
>
> I do not know why the difference exists. I guess it may be a bug
> in R.
> --

Not at all. The reason is that your table gives the t-value for a
two-sided test (with equal tails), i.e. 0.025 in each tail.
The function qt() in R returns the t-value for a one-sided test,
i.e. 0.05 in the (by default) upper tail. Compare:

  qt(0.95,9)
# [1] 1.833113
  qt(0.975,9)
# [1] 2.262157

The second value agrees with your table. Many printed tables give
the two-sided values, rather than the one-sided.

Hoping this helps,
Ted.

--------------------------------------------------------------------
E-Mail: (Ted Harding) <Ted.Harding@...>
Fax-to-email: [phone]
Date: 07-Nov-09                                       Time: 09:55:50
------------------------------ XFMail ------------------------------

______________________________________________
R-help@... mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[Peter Dalgaard]

Sunny Srivastava wrote:
> Hi Huaru,
> Are you sure you are looking at 0.95 and NOT 0.975?
>
> as qt(0.975,9) = 2.262
>
> generally tables are given for alpha/2 (alpha=0.05 in your case)
> significance.
>
> Please check carefully.

Or, put differently, tables are often given for two-sided p-values
(especially in the back pages of textbooks), whereas qt() is for one-sided.

I.e. the t distribution with 9 DF has a probability of 0.95 of falling
BELOW 1.833 but also of falling BETWEEN -2.262 and +2.262.


--
    O__  ---- Peter Dalgaard             Øster Farimagsgade 5, Entr.B
   c/ /'_ --- Dept. of Biostatistics     PO Box 2099, 1014 Cph. K
  (*) \(*) -- University of Copenhagen   Denmark      Ph:  ([phone]
~~~~~~~~~~ - (p.dalgaard@...)              FAX: [phone]

______________________________________________
R-help@... mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.