Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: CDF plot with normal probability axis
From
Nick Cox <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: CDF plot with normal probability axis
Date
Thu, 14 Nov 2013 13:19:51 +0000
Your statement about -qnorm- and -quantile- is not one I endorse. The
positive is that -qplot- does more than either.
Nick
[email protected]
On 14 November 2013 13:18, Nick Cox <[email protected]> wrote:
> My point is just that I underline that there is a choice and refer to
> literature that explains the choices. As a hydrologist, or rather as
> someone who publishes in hydrological journals, I am drawn to (i -
> 0.5)/n which is what the engineering hydrologist Allen Hazen used in
> 1914, as something easy to teach and which works fine for me. As a
> Stata user-programmer, I let people choose.
> Nick
> [email protected]
>
>
> On 14 November 2013 13:10, David Hoaglin <[email protected]> wrote:
>> Thanks, Nick.
>>
>> I didn't see a = 1/3 in the FAQ or the SJ articles, and the derivation
>> of it is interesting.
>>
>> I agree that small differences in plotting position are unlikely to
>> make much difference.
>>
>> You make a good argument for avoiding -qnorm- and -quantile-.
>>
>> David Hoaglin
>>
>> On Thu, Nov 14, 2013 at 7:54 AM, Nick Cox <[email protected]> wrote:
>>> Quite so. Choice of plotting position is discussed at some length in
>>> the FAQ I mentioned, which links to the literature, and in
>>> publications on my -qplot- and its predecessor -quantil2- in the SJ
>>> and STB respectively.
>>>
>>> Naturally I am all in favour of using a better method rather than a
>>> weaker one, but I remain unconvinced that minute differences in
>>> plotting position either are discernible on a graph or have impact on
>>> decisions about data, so long as you are not working with very small
>>> samples. If you are, nothing much helps.
>>>
>>> Your bigger argument is with StataCorp, who wire i / (n + 1) into
>>> -qnorm- and (i - 0.5) / _N into -quantile- and don't allow variations.
>>> My quantile plotting programs have always allowed user choice of a in
>>> (i - a) / (n - 2a + 1).
>>>
>>> Nick
>>> [email protected]
>> *
>> * For searches and help try:
>> * http://www.stata.com/help.cgi?search
>> * http://www.stata.com/support/faqs/resources/statalist-faq/
>> * http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/