The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Countries » Bangladesh » Calculation of sample size in BDHS 2014
Calculation of sample size in BDHS 2014 [message #13721] Wed, 13 December 2017 00:07 Go to next message
mdhasan4 is currently offline  mdhasan4
Messages: 4
Registered: September 2015
Location: Bangladesh
Dear Experts,

I would like to know the justification of sample size calculation. In every report, we get sampling technique what they used it but didn't mention anything about why 600 EA and selected 30 household per cluster? Is there any formula or way that can help us to convinced the people.

I am cordially requesting the experts who are involved with this program, please give your value able opinion. Sometimes we fall in big trouble, we can't give satisfactory answer to our supervisor.

[Updated on: Wed, 13 December 2017 00:07]

Report message to a moderator

Re: Calculation of sample size in BDHS 2014 [message #13731 is a reply to message #13721] Thu, 14 December 2017 08:39 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 2280
Registered: February 2013
Senior Member
Following is a response from Senior DHS Stata Specialist, Tom Pullum:

Under the "Publications" tab at you can find core documentation, including a description of the sampling procedures: al_Sept2012_DHSM4.pdf .

The number of EAs in each stratum, and the number of households in the EAs, are based on a compromise between (a) the funds and staff available for data collection and (b) the desired power of the survey to detect real differences in the population. The survey design is approved by in-country experts as well as DHS staff. You, as a researcher, should not be held accountable for the survey design.

Re: Calculation of sample size in BDHS 2014 [message #15762 is a reply to message #13731] Tue, 11 September 2018 10:54 Go to previous message
tasnuva is currently offline  tasnuva
Messages: 6
Registered: July 2018

Thank you for this information. One reviewer of a journal asked me same questions on a manuscript. Your response is very helpful.

Dr. Tasnuva Wahed
Previous Topic: To perform anova for count data in stata with survey weight
Next Topic: Infant and Child Mortality data set
Goto Forum:

Current Time: Mon May 17 22:34:46 Coordinated Universal Time 2021