RE: st: RE: CDF plot with normal probability axis

["Barclay Matthew (PUBLIC HEALTH ENGLAND)" <matthewbarclay@nhs.net>]

Good point - thanks. I didn't think it through fully, and the issue did not become obvious as I tested on a convenient dataset where the highest point was less than 100%.

Matt



-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Nick Cox
Sent: 14 November 2013 09:25
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: RE: CDF plot with normal probability axis

Warning this message contains links that it has not been possible to verify as safe.  You should only click on the links if you are sure they are from a trusted source.
If you do it that way, the -midpoint- option should really be used.
Otherwise, the highest point is unplottable.

-distplot- is from SJ.

Nick
njcoxstata@gmail.com


On 14 November 2013 08:57, Barclay Matthew (PUBLIC HEALTH ENGLAND)
<matthewbarclay@nhs.net> wrote:
> Hi Michael,
>
> I think -distplot- with the -trscale(invnorm(@))- option may do what you want.
>
> Alternatively, say we have logged values in variable log_val and cumulative probability in variable c_prob, then
>
> gen normal_c_prob = invnorm(c_prob)
> twoway line normal log_val
>
> will produce the graph you want, although the y-axis labelling will need to be modified to match the graph in your link.
>
> Cheers,
> Matt
>
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Livingston, Michael (TP)
> Sent: 14 November 2013 02:10
> To: statalist@hsphsun2.harvard.edu
> Subject: st: CDF plot with normal probability axis
>
> Warning this message contains links that it has not been possible to verify as safe.  You should only click on the links if you are sure they are from a trusted source.
> Hi there,
>
> I'm trying to create  simple plot to compare two distributions - I want the logged values across the x-axis and then the cumulative probability on the y-axis, but with a normal probability y-axis (like the one here: http://lowrank.net/gnuplot/plot7-e.html).
>
> It seems like it should be really simple, but I haven't come with any solutions using distplot or cdfplot. Is there something obvious I'm missing?
>

*
*   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/


********************************************************************************************************************

This message may contain confidential information. If you are not the intended recipient please inform the
sender that you have received the message in error before deleting it.
Please do not disclose, copy or distribute information in this e-mail or take any action in reliance on its contents:
to do so is strictly prohibited and may be unlawful.

Thank you for your co-operation.

NHSmail is the secure email and directory service available for all NHS staff in England and Scotland
NHSmail is approved for exchanging patient data and other sensitive information with NHSmail and GSi recipients
NHSmail provides an email address for your career in the NHS and can be accessed anywhere

********************************************************************************************************************

*
*   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/