*********************************
*****Data analysis **************
*****Dien Hoa Anh Vu ************
*****10/07/2013 *****************
*********************************

*Open 'master file'
use "D:\Hoc Hanh\KKU\YEAR II\TAKASILA\Assignment\mothers.dta", clear

*Merge with 'using file'
joinby idmot using "D:\Hoc Hanh\KKU\YEAR II\TAKASILA\Assignment\fathers.dta"

*Drop variables not in interested, or keep only interested variables, e.g. id, idmot, b20a, b20b
keep id idmot b20a b20b

*Save this file, then continue to merge with other files
*Keep only variables that will be used to analize
*Save the last dataset

*Start to analize the data

*Demographic desrciption, using command TAB to see the frequency and percentage
tab b23

*Use command TAB X Y, ROW to get the percentage of Y among each subgroup of X
tab x y, row

*To see the OR of DTE among 5 sites
logistic DTE SITES

*Linear regression to predict the time of tooth eruption based on number of cigarettes
regress timeerupt cig

*Create variable SHS
gen SHS=
replace SHS=0 if 
replace SHS=1 if 

*To see the HR of DTE between 2 groups of SHS and non-SHS
stcox SHS DTE

*Draw survival curve
stcurve, hazard

*More commands will be added once the dataset is available.