[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

From |
"Nick Cox" <n.j.cox@durham.ac.uk> |

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

Subject |
RE: st: RE: Re: Missing values test |

Date |
Sun, 2 Dec 2007 17:49:22 -0000 |

I am concerned with the structure of missingness, not how to fix it. -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Richard Williams Sent: 02 December 2007 17:41 To: statalist@hsphsun2.harvard.edu; statalist@hsphsun2.harvard.edu Subject: Re: st: RE: Re: Missing values test At 12:11 PM 12/2/2007, Nick Cox wrote: >I've not done it myself, and this may well be obvious to those who know >the literature, but surely more can be said. > >Missingness can always be represented by a dummy. So the structure of >missing data can always be explored by logit regression with >missingness on something as response w.r.t. various predictors, which >may well include missingness on some other things as dummy predictors. I believe Nick is talking about using the MD dummy as your dependent variable. In addition, there have been proposals about using MD dummies as independent vars, which I'll now comment on since i have given partially incorrect responses in the past! Cohen and Cohen proposed several years ago that you plug in the mean for missing data and then add a MD dummy variable indicator. Allison discusses this technique in his green Sage book, "Missing Data". When data exist in reality but their value is unknown (e.g. because of nonresponse), Allison calls this technique "remarkably simple and intuitively appealing." But unfortunately, "the method generally produces biased estimates of the coefficients." He says that listwise deletion is better. HOWEVER, as Richard Campbell recently pointed out to me, buried in the footnotes of Allison's book is the following: "While the dummy variable adjustment method is clearly unacceptable when data are truly missing, it may still be appropriate in cases where the unobserved value simply does not exist. For example, married respondents may be asked to rate the quality of their marriage, but that question has no meaning for unmarried respondents. Suppose we assume that there is one linear equation for married couples and another equation for unmarried couples. The married equation is identical to the unmarried equation except that it has (a) a term corresponding to the effect of marital quality on the dependent variable and b) a different intercept. It's easy to show that the dummy variable adjustment method produces optimal estimates in this situation." * * For searches and help try: * http://www.stata.com/support/faqs/res/findit.html * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

**References**:**st: Missing values test***From:*"Constantin Colonescu" <ccolonescu@gmail.com>

**st: Re: Missing values test***From:*"Rodrigo A. Alfaro" <raalfaroa@gmail.com>

**st: RE: Re: Missing values test***From:*"Nick Cox" <n.j.cox@durham.ac.uk>

**Re: st: RE: Re: Missing values test***From:*Richard Williams <Richard.A.Williams.5@ND.edu>

- Prev by Date:
**RE: st: RE: Re: Missing values test** - Next by Date:
**Re: st: RE: Re: Missing values test** - Previous by thread:
**Re: st: RE: Re: Missing values test** - Next by thread:
**Re: st: RE: Re: Missing values test** - Index(es):

© Copyright 1996–2022 StataCorp LLC | Terms of use | Privacy | Contact us | What's new | Site index |