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

From |
"Mona Mowafi" <mmowafi@hsph.harvard.edu> |

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

Subject |
Re: st: predicted probabilities |

Date |
Mon, 17 Nov 2008 14:17:30 -0500 |

Dear Joao, Maarten, all, Thank you for your help. It seems I am getting the same values regardless of whether I set the other variables constant or not, and this seems odd. Here's what I did: *//GETTING PREDICTED PROBABILITIES OF BMICAT FROM THE FULL MODEL*// do "C:\DOCUME~1\MONAMO~1\LOCALS~1\Temp\STD06000000.tmp" do "C:\DOCUME~1\MONAMO~1\LOCALS~1\Temp\STD06000000.tmp" (these are do files for my multionomial model) predict pbmi2 pbmi3 pbmi4, pr sum pbmi2 sum pbmi3 sum pbmi4 table ED2, c(m pbmi2 m pbmi3 m pbmi4) table WB_pov, c(m pbmi2 m pbmi3 m pbmi4) table ASSET_INDEX, c(m pbmi2 m pbmi3 m pbmi4) table PCAwealthindex, c(m pbmi2 m pbmi3 m pbmi4) describe pbmi2 describe pbmi3 describe pbmi4 *//GETTING PREDICTED PROBABILITIES OF BMICAT KEEPING OTHER VARIABLES CONSTANT (SET AT LOWEST RISK GROUP FOR ALL)*// preserve replace WB_pov=4 replace ASSET_INDEX=1 replace PCAwealthindex=1 replace AGECAT4=1 replace FATHERED=1 replace GENHEALTH_PAST=1 predict pbmiset2 pbmiset3 pbmiset4, p table ED2, c(m pbmiset2 m pbmiset3 m pbmiset4) table WB_pov, c(m pbmi2 m pbmi3 m pbmi4) table ASSET_INDEX, c(m pbmi2 m pbmi3 m pbmi4) table PCAwealthindex, c(m pbmi2 m pbmi3 m pbmi4) restore I have 2 follow-up questions: 1) Does it make sense that I would get the same predicted probabilities whether or not I fixed the other variables in the model? 2) Do you know how I can get 95% CI's for these means? (did not see that in the options with stata help) A millions thanks, Mona >>> "Joao Ricardo F. Lima" <jricardofl@gmail.com> 11/17/2008 6:14 AM >>> Dear Mona, Maarten and Statalisters, reading Maarten's answer, I would like to ask if this procedure is correct: ****** " // creating predictions while keeping other variables constant // predicted probabilities of urban women of average age preserve sum age if e(sample), meanonly replace age = r(mean) replace female = 1 replace rural = 0 predict pra*, pr table race , c(m pra1 m pra2 m pra3 m pra4 m pra5) restore" *************** because the value of r(mean) (sample) is different of svy: mean (population): webuse nhanes2f, clear svyset psuid [pweight=finalwgt], strata(stratid) . svy: mean age (running mean on estimation sample) Survey: Mean estimation Number of strata = 31 Number of obs = 10337 Number of PSUs = 62 Population size = 117023659 Design df = 31 -------------------------------------------------------------- | Linearized | Mean Std. Err. [95% Conf. Interval] -------------+------------------------------------------------ age | 42.23732 .3034412 41.61844 42.85619 -------------------------------------------------------------- . sum age if e(sample) Variable | Obs Mean Std. Dev. Min Max -------------+-------------------------------------------------------- age | 10337 47.5637 17.21678 20 74 If I am using svy: mlogit, the mean to be used isńt the populational? Thanks a lot, Best Regards, Joao Lima 2008/11/16 Maarten buis <maartenbuis@yahoo.co.uk>: > --- Mona Mowafi <mmowafi@hsph.harvard.edu> wrote: >> I am seeking to attain predicted probabilities of my outcome (BMI >> cats - normal, overweight, obese) for four main independent >> variables. I am not sure how to do it, but here is what I have >> tried: >> >> svyset [pweight=femaleweight], strata(order) psu(place) >> >> xi: svymlogit BMICAT i.AGECAT4 i.ED2 i.WB_pov i.ASSET_INDEX >> i.PCAwealthindex i.FATHERED i.GENHEALTH_PAST, basecategory(2) nolog >> svymlogit, rrr >> >> predict p1 p2 p3 >> sort ED2 >> by ED2: sum p1 >> by ED2: sum p2 >> by ED2: sum p3 >> >> Here are my main questions: >> >> 1) Does this syntax, does p1 refer to my reference outcome = normal >> weight; p2= overweight, p3 = obese? I want to make sure that I am >> interpreting what p1, p2, and p3 is properly. > > You can see what category the variables refer to by looking at the > labels that -predict- has attached to them. You can see those by typing > -desc p*- (which will describe all variables whose name start with p, > if there are too many of those type -desc p1 p2 p3-). > >> 2) If I sort and sum by p1, p2, and p3 - is this giving me the mean >> predicted probability of each of my three outcomes for all >> individuals in each of those three sub-categories (of education, for >> example, as seen above)? That is what I'm trying to do. > > Yes, but there is a subtle issue here: the differences between the > educational categories may be due to the effect of education but can > also be due to differences between the educational categories in the > distribution of the other explanatory variables. For instance the lower > educational categories will consist of individuals from a lower social > background and these tend to have , and these tend a higher BMI. You > can keep the other variables constant by first replacing the other > variables by some number, e.g. the mean, and than predict, and than > make the tables. > > Both methods are illustrated below (I used -table- in this examples as > it creates more compact tables, but -by ...: sum...- will work too, > another alternative would be -tabstat-). > > *---------------------- begin example --------------------- > webuse nhanes2f, clear > svyset psuid [pweight=finalwgt], strata(stratid) > tab health > svy: mlogit health rural black orace sex age > > // create predictions without keeping other variables constant > predict pr*, pr > > // the labels show which variable belongs to which category > desc pr* > > // comparing the average predicted probabilities with the observed > percentages > sum pr* > tab health > > table race , c(m pr1 m pr2 m pr3 m pr4 m pr5) > > > // creating predictions while keeping other variables constant > // predicted probabilities of urban women of average age > preserve > sum age if e(sample), meanonly > replace age = r(mean) > replace female = 1 > replace rural = 0 > > predict pra*, pr > table race , c(m pra1 m pra2 m pra3 m pra4 m pra5) > > restore > *--------------------- end example ------------------- > (For more on how to use examples I sent to the Statalist, see > http://home.fsw.vu.nl/m.buis/stata/exampleFAQ.html ) > > Hope this helps, > Maarten > > ----------------------------------------- > Maarten L. Buis > Department of Social Research Methodology > Vrije Universiteit Amsterdam > Boelelaan 1081 > 1081 HV Amsterdam > The Netherlands > > visiting address: > Buitenveldertselaan 3 (Metropolitan), room N515 > > +31 20 5986715 > > http://home.fsw.vu.nl/m.buis/ > ----------------------------------------- > > > > * > * 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/ > -- ------------------------------- Joao Ricardo Lima Professor UFPB-CCA-DCFS +553138923914 ------------------------------- * * 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**:**st: predicted probabilities***From:*"Mona Mowafi" <mmowafi@hsph.harvard.edu>

**Re: st: predicted probabilities***From:*Maarten buis <maartenbuis@yahoo.co.uk>

**Re: st: predicted probabilities***From:*"Joao Ricardo F. Lima" <jricardofl@gmail.com>

- Prev by Date:
**st: RE: Dropping subset of observations** - Next by Date:
**st: SV: RE: file write + if condition?** - Previous by thread:
**Re: st: predicted probabilities** - Next by thread:
**st: Getting Negative Alphas** - Index(es):

© Copyright 1996–2014 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |