The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Mortality » Enumeration Block
Enumeration Block [message #21793] Tue, 22 December 2020 01:19 Go to next message
shujaat.smc@gmail.com is currently offline  shujaat.smc@gmail.com
Messages: 75
Registered: July 2020
Senior Member
Dear DHS Representative,

How you define enumeration block for DHS survey conducted in Pakistan 2017-18.

The Definition shared on Pakistan Statistics website: http://www.pbs.gov.pk/content/methodology-1 (I am not sure that DHS use the same)

The PDHS report 2017-18 doesn't give the operational definition of Enumeration Block (EB).

Kindly share the definition of EB so that I can comprehend it in a true demographic way.

Best Regards

Dr. Hussain



Re: Enumeration Block [message #21844 is a reply to message #21793] Tue, 29 December 2020 19:37 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 2537
Registered: February 2013
Senior Member

Following is a response from DHS Senior Sampling Specialist, Mahmoud Elkasabi:

The DHS Program uses the census frame of enumeration areas provided by the national statistical office in the survey country. We do not redefine or reconstruct the enumeration areas; we use them as they are and as officially defined. This applies for all countries including Pakistan. So the definition provided by Pakistan Bureau of Statistics should be the correct definition.
Re: Enumeration Block [message #21903 is a reply to message #21844] Thu, 07 January 2021 03:42 Go to previous messageGo to next message
shujaat.smc@gmail.com is currently offline  shujaat.smc@gmail.com
Messages: 75
Registered: July 2020
Senior Member
Dear Mahmoud,

Thanks a lot for your reply.

Happy New Year!

Best Regards

Dr. Hussain
Re: Enumeration Block [message #21942 is a reply to message #21844] Sun, 10 January 2021 05:15 Go to previous messageGo to next message
shujaat.smc@gmail.com is currently offline  shujaat.smc@gmail.com
Messages: 75
Registered: July 2020
Senior Member
Dear DHS Representative,

I have copied the following text from https://microdata.worldbank.org/index.php/catalog/3411

"The first stage involved selecting sample points (clusters) consisting of EBs. EBs were drawn with a probability proportional to their size, which is the number of households residing in the EB at the time of the census. A total of 580 clusters were selected."

Quest1: In my understanding, the enumeration block in urban strata is a city or a county/town of the city and for rural strata, it is a village or group of villages. However, looking at the text from the above site its seems that there is no difference in cluster & EB?

Quest2: In my understanding, the clusters are selected from EB in the first stage by performing the systematic random sampling on the sorted list of households with probability proportionate to size (That is how many houses (buildings in urban & huts in rural strata) are listed (Not the number of household members residing in the EB from which we have to select the clusters). But reading the text from the world Bank website gives the impression that size means the number of peoples residing in EB not the number of houses/huts.

Quest3: EBs were not drawn by Probability Proportionate to size instead clusters were drawn by Probablity Proportionate to the size of that particular EB. (Do I have the correct concept)?

Kindly Clarify this confusion.


Best Regards

Dr. Hussain
Re: Enumeration Block [message #21963 is a reply to message #21942] Mon, 11 January 2021 17:46 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 2537
Registered: February 2013
Senior Member
Following is a response from DHS Research & Data Analysis Director, Tom Pullum:


More generically we usually refer to Enumeration Areas (EAs) rather than Enumeration Blocks (EBs). But yes, these are the Primary Sampling Units (PSUs) or clusters. They do mean the same thing. Clusters and clustering are terms used in sampling theory.

A generic sampling frame includes a measure of size for each EA or EB. In different settings it may be the number of housing units or the number of households or the number of individuals enumerated at the last census. The EAs or EBs are selected with probability proportional to this measure of size, whatever it may be. For example, a unit in the sampling frame that is twice as large as another unit is twice as likely to be selected for the sample.

The term "systematic" must be used carefully. It applies to a different sampling strategy (https://en.wikipedia.org/wiki/Systematic_sampling).

Re: Enumeration Block [message #21970 is a reply to message #21963] Tue, 12 January 2021 04:07 Go to previous message
shujaat.smc@gmail.com is currently offline  shujaat.smc@gmail.com
Messages: 75
Registered: July 2020
Senior Member
Dear Tom Pullum, Happy New Year!

Thanks a lot for clearing the concept.

Best Regards

Dr. Hussain
Previous Topic: Mother mortality rate
Next Topic: Neonatal death highest Proportion in U5CM. However, a Rare Statistical Event
Goto Forum:
  


Current Time: Tue Jun 28 05:34:59 Coordinated Universal Time 2022