My study objective is to compare prevalence of Non Communicable Disease risk factors in two cross sectional surveys conducted in Year 2005 and Year 2022 in same population. Sampling strategy and data collection method were similar in both surveys. As time period between surveys is large,
please suggest me robust analytical measures to compare prevalence of risk factors for adjusting confounding variables in STATA.
Outcome variables - Hypertension , obesity (have both continuous and categorical variables)
exposure variables - Smoking / smokeless tobacco/ alcohol/ Low Physical activity / low vegetables and fruits consumption
socioeconomic - age / gender / education / occupation
I have a STATA merged dataset defined by variable Year (2005 and 2022)