Maarten
Det er jo glimrende o dejlig
Just to assure I have understood. In this model I keep age 10-19 and
non-perforated appendicitis (the largest groups) as reference level so
I do not bother with mean centering with age.
lnLOS exp(b) Std. Err. t P>t
[95% Conf. Interval]
lapscopy 1.015229 .0069404 2.21 0.027 1.001716 1.028924
_Iappdgn2_1 1.854565 .0133561 85.76 0.000 1.828571 1.880929
_Iappdgn2_3 1.172527 .0139403 13.39 0.000 1.14552 1.200171
_Ialderkat_0 1.113349 .0124712 9.59 0.000 1.089172 1.138063
_Ialderka~20 .9669727 .0081023 -4.01 0.000 .9512217 .9829846
_Ialderka~30 1.013716 .0091096 1.52 0.130 .9960177 1.03173
_Ialderka~40 1.074382 .0115025 6.70 0.000 1.052072 1.097165
_Ialderka~50 1.181179 .0134386 14.64 0.000 1.15513 1.207815
_Ialderka~60 1.309059 .0192205 18.34 0.000 1.271924 1.347279
_Ialderka~70 1.685401 .0312085 28.19 0.000 1.625328 1.747694
_Ialderka~80 2.303874 .0611701 31.43 0.000 2.187045 2.426943
prepermalign 1.190686 .027653 7.51 0.000 1.137701 1.24614
precardios~s 1.024731 .0266026 0.94 0.347 .9738935 1.078222
preperlung~d 1.076669 .0182661 4.35 0.000 1.041456 1.113073
preperhype~i 1.024272 .0208447 1.18 0.239 .9842196 1.065954
preperhjar~t 1.293909 .0480737 6.94 0.000 1.203033 1.391651
prepernjur~t 1.050412 .0516992 1.00 0.318 .953814 1.156792
preperdiab~s 1.168423 .0287019 6.34 0.000 1.113499 1.226055
cons 1.858693 .0106446 108.24 0.000 1.837946
1.879675
And here I calculate the effect of laparoscopy
. nlcom exp((_b[cons]+ _b[lapscopy]) - exp((_b[cons])))
_nl_1: exp((_b[cons]+ _b[lapscopy]) - exp((_b[cons])))
vtidln Coef. Std. Err. t P>t [95% Conf. Interval]
_nl_1 .2941382 .0027509 106.92 0.000 .2887463 .2995302
ie open appendectomy in nonperforated patients age 10-19 have a
geometric mean LOS of 1.86 (95% CI 1.83-1.88) days after adjustment
for comorbidity and lapscopy patients have 0.29 (95% CI 0.28-0.30)
days longer LOS.
Correct?
Greetings o stort tack
Roland Andersson
2008/11/5 Maarten buis <[email protected]>:
> --- roland andersson <[email protected]> wrote:
>> It is also difficult to imaging that there should be censoring
>> for conditions that normally need 1 to 7 days of hospital visit.
>
> Ok, sounds reasonable.
>
>> Following your example I have made this model
>>
>> xi:regress lnLOS lapscopic i.appdgn age agesq cons, eform("exp(b)")
>> nocons
>>
>> and get this result
>>
>> lnLOS exp(b) [95% Conf. Interval]
>> lapscopic 1.018056 1.004532 1.031762
>> _Iappdgn2_1 1.850726 1.824841 1.876978
>> _Iappdgn2_3 1.174283 1.147247 1.201956
>> age .9852508 .9841405 .9863623
>> agesq 1.000275 1.000261 1.000289
>> cons 2.208685 2.168225 2.2499
>>
>> I now understand that the exp(b) is a multiplicator, ie that open
>> appendectomy has a geometric mean LOS of 2.21 days whereas
>> laparoscopic patients have 1.02*2.21=2.25 days or 0.04 days longer
>> geometric mean LOS. Is it correct to recalculate the CI of this
>> difference as 2.21-1.0045*2.21=0.01 and 2.21-1.032*2.21=0.07?
>
> In that case I would use -adjust- and -nlcom- like in the example
> below:
>
> *--------------- begin example --------------------------
> sysuse cancer, clear
> gen ln_t = ln(studytime)
> gen cons = 1
> xi: reg ln_t i.drug age cons, nocons eform("exp(b)")
>
> adjust _Idrug_3=0 age, by(_Idrug_2) exp ci
> sum age if e(sample)
> nlcom exp((_b[cons] + _b[age]*`r(mean)')+ _b[_Idrug_2]) - ///
> exp((_b[cons] + _b[age]*`r(mean)'))
> *---------------- end example ---------------------------
>
> Notice that the difference in LOS now depends on the values of the
> other explanatory variables. These other variables define the baseline
> LOS (in your case the LOS for someone who received an open
> appendectomy). So if you haven't mean centered age, then the difference
> in geometric mean LOS you reported applies to newly born babies. You
> can report the difference in geometric mean LOS for someone of average
> age either by first mean centering age (subtract the mean age from the
> variable age as I did in the example in my previous post), or take mean
> age into account like in the example above.
>
> 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/
>
*
* 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/