Dear list
I am having some trouble with dstdize and hope that someone can help.
My dataset consists of a grouping variable "elderly" on 3 levels, "female" on 2 levels and a binary outcome variable (outc30). I wish to calculate standardized mortality-rates using the first group in "elderly" as reference.
I can almost accomplish this using dstdize, but I have trouble using the population variable. I set this to 1 just to get started and called the command as below (with output).
However, my wish is to use weights relating to the first group "elderly=60", that is 81/171 and 70/151 for male and female, respectively. These weights should be used in the other two groups and in the calculation of adjusted rates. How do I tell Stata to do this?
gen all=1
. dstdize outc30 all female, by(elderly)
----------------------------------------------------------
-> elderly= 60
-----Unadjusted----- Std.
Pop. Stratum Pop.
Stratum Pop. Cases Dist. Rate[s] Dst[P] s*P
----------------------------------------------------------
0 81 22 0.536 0.2716 0.550 0.1495
1 70 12 0.464 0.1714 0.450 0.0771
----------------------------------------------------------
Totals: 151 34 Adjusted Cases: 34.2
Crude Rate: 0.2252
Adjusted Rate: 0.2266
95% Conf. Interval: [0.1601, 0.2930]
----------------------------------------------------------
-> elderly= 80
-----Unadjusted----- Std.
Pop. Stratum Pop.
Stratum Pop. Cases Dist. Rate[s] Dst[P] s*P
----------------------------------------------------------
0 96 35 0.565 0.3646 0.550 0.2006
1 74 25 0.435 0.3378 0.450 0.1519
----------------------------------------------------------
Totals: 170 60 Adjusted Cases: 59.9
Crude Rate: 0.3529
Adjusted Rate: 0.3526
95% Conf. Interval: [0.2808, 0.4244]
----------------------------------------------------------
-> elderly= 110
-----Unadjusted----- Std.
Pop. Stratum Pop.
Stratum Pop. Cases Dist. Rate[s] Dst[P] s*P
----------------------------------------------------------
0 20 13 0.541 0.6500 0.550 0.3577
1 17 7 0.459 0.4118 0.450 0.1852
----------------------------------------------------------
Totals: 37 20 Adjusted Cases: 20.1
Crude Rate: 0.5405
Adjusted Rate: 0.5429
95% Conf. Interval: [0.3870, 0.6987]
Summary of Study Populations:
elderly N Crude Adj_Rate Confidence Interval
--------------------------------------------------------------------------
60 151 0.225166 0.226554 [ 0.160089, 0.293018]
80 170 0.352941 0.352555 [ 0.280752, 0.424359]
110 37 0.540541 0.542861 [ 0.386972, 0.698749]
_______________________________
Claus Dethlefsen, Msc, PhD
Statistiker ved Kardiovaskul�rt Forskningscenter
Klinisk Epidemiologisk Afdeling
Aalborg Sygehus Nord
Stengade 10, 2. sal
9000 Aalborg
Tlf: 9932 1086
9932 1094 (direkte)
Fax: 9932 1088
email: [email protected]
*
* 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/
