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 |
László Sándor <sandorl@gmail.com> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: is something wrong with fvvarlist "i(3 4).role"? |

Date |
Wed, 14 Jul 2010 12:02:53 +0200 |

Thanks, Jeff, this is really helpful. I still must note that this behavior is not exactly what -help fvvarlist- seems to imply (e.g. i(3 4). is said to include two dummies...), nor what many (most?) users would use i#. operators for. If I want to include two dummies, why would I lose one of them? Of course, if the sample would be limited to include only these two groups, and then use one as the base level, that would make sense. But that is not what this operator does anyway. Many thanks, still, and it is still quite easy to do what I needed, once I know how to! Laszlo On Tue, Jul 13, 2010 at 5:09 PM, Jeff Pitblado, StataCorp LP <jpitblado@stata.com> wrote: > > Laszlo Sandor <sandorl@gmail.com> is using the new factor variables notation, > specifically the 'i.' operator with a numlist: > > > I think I have a straightforward question in the subject line. > > > > I use the up-to-date Stata on a mac. The factor variable handling does > > not work as promised in the manual (cf. -h fvvarlist-). See the most > > striking, simple example below. Or am I missing the obvious? > > > > Laszlo > > > > > > > > . sum i(3 4).role > > > > Variable | Obs Mean Std. Dev. Min Max > > -------------+-------------------------------------------------------- > > 4.role | 747 .2503347 .433496 0 1 > > > > . sum i(3/4).role > > > > Variable | Obs Mean Std. Dev. Min Max > > -------------+-------------------------------------------------------- > > 4.role | 747 .2503347 .433496 0 1 > > Michael Mitchell <Michael.Normal.Mitchell@gmail.com> replied explaining that > level 3 of the 'role' variable is being treated as a reference level. > > By default, Stata suppresses the reference level from the output. Here are a > couple ways that Laszlo can change this behavior. > > 1. Use the -baselevels- option to get -summarize- to report the reference > level. > > . sum i(3 4).role, baselevels > > Since the reference level pseudo variable '3b.role' will only take on the > values 0 or missing, the only useful information for -summarize- to report > is the number of non-missing values in the 'role' variable. > > 2. Use the 'b.' operator to turn off the reference level logic: > > . sum i(3 4)bn.role > > This will summarize the indicators for both levels of 'role'. > > --Jeff > jpitblado@stata.com > * > * 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/ * * 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/

**References**:**Re: st: is something wrong with fvvarlist "i(3 4).role"?***From:*jpitblado@stata.com (Jeff Pitblado, StataCorp LP)

- Prev by Date:
**Re: st: Multicollinearity in fixed effects regressions** - Next by Date:
**st: RE: Multicollinearity in fixed effects regressions** - Previous by thread:
**Re: st: is something wrong with fvvarlist "i(3 4).role"?** - Next by thread:
**st: xtivreg2 weak-instrument-robust inference** - Index(es):