Hello,
I have grouped 3 Tanzania DHS datasets from TDHS 2004/05, TDHS 2010 and TDHS 2015/16. I want to analyze the trends of unmet need for modern contraception among sexually active adolescents across the 3 survey periods and check for linearity of trends. At first I only did a cross tabulation and obtained the proportions of trends in each survey year and by different background characteristics, later computed their changes over time. But this method did not seem proper in terms of actually checking for the significance of the trends of unmet need for modern contraception (where there was a significant change).
Kindly advise how I can properly go about this using Stata.