I wondered if someone could offer some advice to a relative new user at
using Stata for indirect standardisation please?
I have a standard population dataset ("C:\Stata8\standard_pop.dta") that
contains the variables:
sex(2 levels) & age(9), pop_pop (population for sex-age level) and pop_dv
(outcome variable for sex-age level).
The working file also contains variables of quint(5 levels of disadvantage)
& sex(2) & age(9), sty_pop (population for each qunitile, sex & age) and
sty_dv (outcome variable for quintile, sex & age level).
I wish to compare the outcome variable across disadvantage quintiles after
adjusting for sex and age and used....
istdize sty_dv sty_pop sex age using "C:\Stata8\standard_pop.dta", by(quint)
pop(pop_dv pop_pop) print
The resultant output makes sense to me in that:
For the Standard Population it lists the relevant stratum specific rates by
sex and age;
For the Indirect Standardization output it shows appropriate figures in each
Quintile for the Standard Population Rate, the Observed Population and Cases
Expected.
What doesn't make sense to me is the Observed Case numbers. The total for
Observed cases at the end of output for each Quintile is different to the
total appearing in the Summary. Neither of the figures correspond to the
actual Quntile total either.
I've appended part of the relevant output below.....
-----------Standard Population-----------
Stratum Rate
----------------------------------------
1 1 0.03645
1 2 0.00445
1 3 0.02461
1 4 0.03507
1 5 0.04074
1 6 0.06241
1 7 0.12544
1 8 0.25994
1 9 0.46857
2 1 0.02632
2 2 0.00333
2 3 0.00871
2 4 0.01352
2 5 0.02323
2 6 0.04227
2 7 0.08375
2 8 0.16200
2 9 0.36878
----------------------------------------
Standard population's crude rate: 0.07397
-------------------------------------------------------------------
-> quint= 1
Indirect Standardization
Standard
Population Observed Cases
Stratum Rate Population Expected
-------------------------------------------------------------------
Male 0-4 0.0365 1115452544 40660135.98
Male 5-14 0.0044 2265765376 10072570.72
Male 15-24 0.0246 2039920384 50198037.35
Male 25-34 0.0351 2297000448 80553976.10
Male 35-44 0.0407 2285767936 93119707.91
Male 45-54 0.0624 1862058624 116201829.23
Male 55-64 0.1254 1328392704 166632918.91
Male 65-74 0.2599 1057590272 274912490.84
Male 75+ 0.4686 694986944 325651230.22
Female 0-4 0.0263 1062510656 27963572.39
Female 5-14 0.0033 2159252224 7186185.90
Female 15-24 0.0087 1934393216 16845861.98
Female 25-34 0.0135 2232171264 30178037.63
Female 35-44 0.0232 2228566016 51775768.18
Female 45-54 0.0423 1887901056 79809596.97
Female 55-64 0.0838 1323544832 110852900.03
Female 65-74 0.1620 1130700800 183175459.27
Female 75+ 0.3688 1057105536 389840996.20
-------------------------------------------------------------------
Totals: 299630808322055631275.83
Observed Cases:218401328
SMR (Obs/Exp): 0.11
SMR exact 95% Conf. Interval: [0.1062, 0.1063]
Crude Rate: 0.0073
Adjusted Rate: 0.0079
95% Conf. Interval: [0.0079, 0.0079]
Summary of Study Populations (Rates):
Cases
quint Observed Crude Adj_Rate Confidence Interval
--------------------------------------------------------------------------
1 102949656 0.007289 0.007859 [0.007858, 0.007860]
2 49972660 0.006685 0.006631 [0.006630, 0.006632]
3 96338672 0.002175 0.001966 [0.001966, 0.001967]
4 77413256 0.000559 0.000603 [0.000602, 0.000603]
5 29363224 0.003253 0.003167 [0.003166, 0.003168]
Summary of Study Populations (SMR):
Cases Cases Exact
quint Observed Expected SMR Confidence Interval
--------------------------------------------------------------------------
1 102949656 2.06e+09 0.106 [0.106231, 0.106259]
2 49972660 2.21e+09 0.090 [0.089636, 0.089661]
3 96338672 2.49e+09 0.027 [0.026575, 0.026587]
4 77413256 2.02e+09 0.008 [0.008145, 0.008152]
5 29363224 2.36e+09 0.043 [0.042807, 0.042823]
Any help on this is much appreciated.
Yours quizzically,
David Banham
Epidemiologist
Strategic Planning & Research Branch
Department of Human Services
PO Box 6 Rundle Mall
Adelaide SA 5000
Phone: 61 8 8226 0786
Fax: 61 6 8826 6700
E-mail: [email protected]
-----------------------------------------------------------------------
This e-mail may contain confidential information, which may be legally
privileged. Only the intended recipient(s) may access, use, distribute or
copy this e-mail. If this e-mail is received in error, please inform the
sender by return e-mail and delete the original. If there are doubts about
the validity of this message please contact the sender by telephone. It is
the recipient's responsibility to check the e-mail and any attached files
for viruses.
*
* 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/
