Discrepancy in dataset after download
Hi,
I want to conduct an analysis by using the Nigerian 2018 DHS data. For a specific variable concerning whether female respondents are circumcised, the official report states that 16,227 women were surveyed. I only have the STATA/BE version, which is why I could not include the whole DHS data in my STATA, but used this command to get the variable(s) (g102 is the circumcision var) needed:
use caseid v000 psu v002 v003 v012 weight v007 strata v024 v001 g100 g103 g104 g105 g106 g107 g108 g118 v106 v025 v105 v104 g102 v131 v130 sstate v190 v157 v158 v159 using "Desktop/Data DHS/Individual Nigeria 2018/NGIR7BFL.DTA", clear
But when I tab the variable, STATA only shows15,512 obs. As there are weights used in the official one, I tried to include them with this command:
svyset [pweight=weight], psu(psu) strata(strata)
svy: tab g102
But still, the var only shows 15,512 obs.
Would be very happy if someone could help!
I want to conduct an analysis by using the Nigerian 2018 DHS data. For a specific variable concerning whether female respondents are circumcised, the official report states that 16,227 women were surveyed. I only have the STATA/BE version, which is why I could not include the whole DHS data in my STATA, but used this command to get the variable(s) (g102 is the circumcision var) needed:
use caseid v000 psu v002 v003 v012 weight v007 strata v024 v001 g100 g103 g104 g105 g106 g107 g108 g118 v106 v025 v105 v104 g102 v131 v130 sstate v190 v157 v158 v159 using "Desktop/Data DHS/Individual Nigeria 2018/NGIR7BFL.DTA", clear
But when I tab the variable, STATA only shows15,512 obs. As there are weights used in the official one, I tried to include them with this command:
svyset [pweight=weight], psu(psu) strata(strata)
svy: tab g102
But still, the var only shows 15,512 obs.
Would be very happy if someone could help!
Comment