Trend of proportions of people on a medication over 10 years

[Lena Mathews]

I have 10 years worth of data (surveillance data so its weighted). I want to assess the trend of the proportion of people from each year who have a certain medication over the 10 year period. What is the best method to use? So far I used 1) Proportions for each year and used scatter plot to fit a line 2) linear regression svy: regress med_x year .3) I found a similar paper that used weighted poisson with age standardized estimates but couldn't figure out how to code this. Thank you for your help.

[Phil Bromiley]

You didn't get a quick answer. You'll increase your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output (fixed spacing fonts helps), and sample data using dataex.

This is really a matter of substance rather than Stata. There are many alternatives available to talk about trends in proportions, and what makes most sense depends on your context (on which we are not expert).