Home » Data » Dataset use in SPSS » Antenatal care vs infant mortality -Kenya
| Re: Antenatal care vs infant mortality -Kenya [message #1590 is a reply to message #1589] |
Fri, 14 March 2014 19:46   |
 |
user-rhs
Messages: 132
Registered: December 2013
|
Senior Member |
|
|
If you restrict to BIDX==1 (i.e., delete observation if BIDX>1), then your dataset includes only the most recent born children. From then on, any of your tabulations re: mother's antenatal care, for example, the number of ANC visits, whether she received injections, iron, etc., will be tabulated only on those children.
Using 2008-9 child recode data, I see that 1,997 children in that dataset were NOT the most recent, so when I drop those observations, I am down to 4,082 most recent births. Again, you can confirm that the ANC variables are collected only for the most recent birth, by asking the software to tabulate BIDX where ANC variable (ex: m13) is missing.
Note that the age range for BIDX==1 is 0-59 months, not 12-59 months. You will need to do some data management to create categories of child's age if you are interested only in the 12-59 subset.
Similarly, you will need to create a variable on whether the mother attended ANC or not in order to get the cross-tabulation between ANCxdeath. Note, because the number of children who died are quite small (165), you may have difficulties finding statistical significance.
My examples are in Stata but they are directly translatable to SPSS.
hth,
RHS
|
|
|
|
Current Time: Wed Dec 18 12:14:15 Coordinated Universal Time 2024
|
The DHS Program User Forum
Members
Search
Help
Register
Login
Home
