Age standardization

[Ahmed A Arif]

I am calculating age-adjusted prevalence of certain diseases using direct method. I have a variable agestd that contains frequency of age groups

. tab agestd

        Age |
Groups-Stan |
dardization |      Freq.     Percent        Cum.
------------+-----------------------------------
  18-24 yrs |     85,585       11.98       11.98
  25-44 yrs |    252,055       35.29       47.28
  45-64 yrs |    246,928       34.57       81.85
    65+ yrs |    129,619       18.15      100.00
------------+-----------------------------------
      Total |    714,187      100.00

The second variable contains standard weights based on 2000 US population

. tab std_wt

   Standard |
     weight |      Freq.     Percent        Cum.
------------+-----------------------------------
     .12881 |     85,585       11.98       11.98
    .170271 |    129,619       18.15       30.13
    .299194 |    246,928       34.57       64.71
    .401725 |    252,055       35.29      100.00
------------+-----------------------------------
      Total |    714,187      100.00

The survey command I'm using to calculate age standardized prevalence is

svy,subpop (if occp==1 &  working==1): prop copd, stdize(agestd) stdweight(std_wt)
svy,subpop (if occp==1 &  working==0): prop copd, stdize(agestd) stdweight(std_wt)

The command runs fine but I would like to ask if the syntax is correct.

Is there a way to compare the two which standardized prevalence get a P value? The only way I can compare the two prevalences is by looking at their 95% confidence intervals.

Thanks

[Ruth-Alma Turkson-Ocran]

Yes, I do believe you are running the right syntax. To compare the two prevalence, I have done the following:

svy, subpop (if occp==1) : prop copd, stdize(agestd) stdweight(std_wt), over(working) 
 nlcom _b[_subpop_2]/_b[_subpop_1] // Prevalence Ratio

[Mohammed Essa]

Are the standard weights here direct variable name from the standard population file?