Analyze some Data

Hello, I am preforming research on the impact of menu labeling laws on obesity. I have attached a document containing a list of counties that have enacted the laws anytime from 2008-2011. For this project, I am looking for a statistical analysis of a large data set in order to quantify the impact of menu labeling laws on obesity. The data sets comes from the SMART BRFSS Survey from CDC, is in SAS format, and contains 140 variables. It can be downloaded here: [login to view URL] I would like to preform a cross-sectional analysis by preforming the following: -2012 (latest) SMART BRFSS -Keep following variables: County code, county name, sex, race, age, BMI, normal/overweight/obese, education level completed, income, smoking status, drinks of alcohol per month, fair or poor general health, no leisure time physical activity, fruit and vegetable consumption, healthcare access, hypertension, cholesterol, diabetes, disability -delete other variables -add 6 new binary variables: “any menu law” “menu law 1+ year” “menu law 2+ years” “menu law 3+ years” “menu law 4+ years” “menu law 5 years” -each county will be assigned [0,1] based on how long they have had an implemented menu law as of 2012 (for example, because NYC has had a menu law for 5 years, counties in NYC will receive a 1 for each variable) -examine impact of menu law on ln(BMI) in 2012 -control for age, race, income, education -determine impact of income, education, race on obesity (possible interaction variable) -explain results and provide command sheet so results can be replicated. This can be preformed in R, SPSS, or STATA. The overall desire is to see how menu laws affect BMI. Have menu laws changed BMI rates in the counties that have adopted them early? If not, what other factors (age, income, education, race) do affect BMI? Please let me know if you have any questions or if any additional information is required. Thank you.