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

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

From |
"Airey, David C" <david.airey@vanderbilt.edu> |

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

Subject |
Re: st: error bars in marginsplot |

Date |
Sun, 16 Sep 2012 08:22:13 -0500 |

. Very nice trick. Thanks for that one. -Dave On Sat, Sep 15, 2012 at 6:34 PM, Jordan Silberman wrote: > Is it possible to have the marginsplot command display error bars that > are 1 standard error wide, rather than displaying error bars that are > the full 95% CI? We can use the -level()- option for that. The trick is to find the level that corresponds with 1 standard error. This is normal(1)-normal(-1). Since the -level()- option works in percentages, we need to multiply that by 100, and since it only takes two decimal places after the decimal point, we need to use the -round()- option. Putting all this together: *------------------ begin example ------------------ sysuse auto, clear reg price i.rep78 margins, over(rep78) marginsplot , /// level(`=round((normal(1)-normal(-1))*100,.01)') *------------------- end example ------------------- (For more on examples I sent to the Statalist see: http://www.maartenbuis.nl/example_faq ) * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

- Prev by Date:
**Re: R: st: Fixed Effects GLS regression** - Next by Date:
**st: indicator for "if cell contains the word or phrase"** - Previous by thread:
**Re: st: error bars in marginsplot** - Next by thread:
**R: st: Fixed Effects GLS regression** - Index(es):