The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Countries » Ethiopia » Computing Newborn Mortality rates (to compute time to death in days)
Computing Newborn Mortality rates [message #18911] Sat, 14 March 2020 23:57 Go to next message
getiye is currently offline  getiye
Messages: 2
Registered: March 2020
Member
Hello,
I am working on neonatal data. I want to generate the time to death in days. My research question is survival time and predictors among neonates using Ethiopian 2016 DHS. Age at death is recorded as 0 for death and else otherwise, B7(months, imputed). The current age of the child also recorded in months (B19. Please Can I get help on how to compute the time to death(time to event)as well as the censoring time? It can be in SPSS/ STATA or R.

Thanks!
Re: Computing Newborn Mortality rates [message #18950 is a reply to message #18911] Tue, 24 March 2020 14:27 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 1770
Registered: February 2013
Senior Member


Following is a response from DHS Research & Data Analysis Director, Tom Pullum:

We cannot help with the details. This a generic question about failure or survival models. You have b19, which is age in months, as you say. If b7=0, then the child died during the first month. If b7>0 the child died later. If b7=. (a dot, for Not Applicable), then the child was still living at the time of the survey (also indicated with b5=1). For early neonatal deaths, you use b6. For example, if b6<107, (the 1 indicates days) then the child died in the first week.
Re: Computing Newborn Mortality rates [message #18957 is a reply to message #18911] Tue, 24 March 2020 23:23 Go to previous message
getiye is currently offline  getiye
Messages: 2
Registered: March 2020
Member
Thank you so much dear Bridgette. I got it very helpful. I also wonder if I can get your help on how can I extract the data for newborns in the last five years from the BR dataset. It has a total of 41392 rows in SPSS(in its long-form, I guess). But I need to have the exact sample size of neonates in the five years including twins. When I try to extract it using the variable "Births in the last five years (0V208)", I got a very high sample size than my expectation. Thanks!

Getiye

[Updated on: Tue, 24 March 2020 23:27]

Report message to a moderator

Previous Topic: Calculating stillbirth using Ethiopia DHS 2000
Next Topic: Re-message18741
Goto Forum:
  


Current Time: Fri Apr 10 02:38:59 Eastern Daylight Time 2020