Notice: On March 31, it was **announced** that Statalist is moving from an email list to a **forum**. The old list will shut down on April 23, and its replacement, **statalist.org** is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

From |
"Allan Reese (Cefas)" <allan.reese@cefas.co.uk> |

To |
"statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |

Subject |
Re: st: Scatterplot jitters - bug? (v12/Win used) |

Date |
Wed, 26 Jun 2013 14:30:55 +0000 |

In the example below, the points at (5 35.2) are jittered, and only (5 50.2) are plotted coincident. You raise a good philosophical question: when jitter is requested, should the program extract the plotting ranges from the jittered data or the "true" values? Also puzzling, I thought jitter added a random amount to each value, but repeated calls appear to give the same graph for this example, and -set seed- is also not changing the jittered plot. Allan PS: I assume you mean the Stata multiverse. Date: Mon, 24 Jun 2013 15:10:10 +0100 From: Nick Cox <njcoxstata@gmail.com> Fair point, but somewhere in the Stata universe there is also an anti-Allan who would regard it as a bug if data points were jittered to outside the plot region. On 24 June 2013 14:03, Allan Reese (Cefas) <allan.reese@cefas.co.uk> wrote: > Here's an irritating "feature" that I would term a bug, in that the results are not as per documentation and are counter-intuitive. It seems that coincident points at the top-right limit of the plotted area are not jittered. Here's a little, real, dataset and two examples to compare. Point at (5 50.2) are not jittered in the first plot. > > . list y x, sep(0) > > +----------+ > | y x | > |----------| > 1. | 0 44.7 | > 2. | 0 44.7 | > 3. | 0 44.7 | > 4. | 0 39.9 | > 5. | 1 39.9 | > 6. | 0 39.9 | > 7. | 3 35.2 | > 8. | 5 35.2 | > 9. | 5 35.2 | > 10. | 5 50.2 | > 11. | 5 50.2 | > 12. | 3 50.2 | > +----------+ > > . scatter y x, jitter(5) > > . scatter y x, jitter(5) yscale( range(0 5.2)) > > Allan > > > > * > * 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/ * * 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/

- Prev by Date:
**re: st: Using AIPW for missing data purposes in RCTs?** - Next by Date:
**re: st: factor variables and pweights not accepted in qreg Stata v13** - Previous by thread:
**st: Test for heteroscedasticity in panel data in STATA** - Next by thread:
**st: How to -estadd- specific F statistics after -ivreg2- ?** - Index(es):