The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Nutrition and Anthropometry » Sample size for Anthropometry in Malawi Demographic and Health Survey of 2010
Sample size for Anthropometry in Malawi Demographic and Health Survey of 2010 [message #9517] Thu, 07 April 2016 10:38 Go to next message
chikhungulana is currently offline  chikhungulana
Messages: 7
Registered: April 2016
Location: Southampton
Member
Hello

I am analysing the levels and trends of stunting and underweight in Malawi.I notice that for anthropometry estimates for MDHS 2010 (4,586), the sample size is less than half of what was used in 2000(11,926) and 2004 (10,914) MDHS data sets. I also find that the variables such as Region and Urban/rural residence that were significantly associated with stunting and underweight in 2000 and 2004 are no longer significant in 2010 and I was wondering if this could be due to the reduced sample size. Your advice will be greatly appreciated.

Thanks

Lana
Re: Sample size for Anthropometry in Malawi Demographic and Health Survey of 2010 [message #9590 is a reply to message #9517] Tue, 19 April 2016 12:26 Go to previous message
Liz-DHS
Messages: 1516
Registered: February 2013
Senior Member
Dear User,
A response from Dr. Ruilin Ren:
Quote:

Hi Liz
I had a quick look of the stunting indicator for the three Malawi DHS surveys, I think the change that the data user noticed was not due to the reduced sample size in the 2010 survey. If you look at the changes of the indictor by residence and by region, there is a clear trend, though the changes may not be statistically significant due to the small sample size, but the trend is clear: the situation in the urban areas was worsened, while the situation improved in the rural area; at the three regions level, Northern and Southern areas were worsened, but Central was improved. These changes clearly reduced the differences between the urban and rural areas, and between the Central and the other regions. To my opinion, the data user might have observed the correct change of the association of the indicator with type of residence and regions. Especially at the three regions level, the 2000 survey showed large differences by region, while the 2010 regional difference was much smaller. See the pooled indicators below.

DHS	Code	Region	Indicator	R
2000	1	Urban	Height-for-age (Below -2SD)	0.342
2004	1	Urban	Height-for-age (below -2SD)	0.378
2010	1	Urban	Height-for-age (below -2SD)	0.407

				
DHS	Code	Region	Indicator	R
2000	2	Rural	Height-for-age (Below -2SD)	0.512
2004	2	Rural	Height-for-age (below -2SD)	0.492
2010	2	Rural	Height-for-age (below -2SD)	0.482

				
DHS	Code	Region	Indicator	R
2000	3	Northern	Height-for-age (Below -2SD)	0.390
2004	3	Northern	Height-for-age (below -2SD)	0.424
2010	3	Northern	Height-for-age (below -2SD)	0.447

				
DHS	Code	Region	Indicator	R
2000	4	Central	Height-for-age (Below -2SD)	0.555
2004	4	Central	Height-for-age (below -2SD)	0.527
2010	4	Central	Height-for-age (below -2SD)	0.472


				
DHS	Code	Region	Indicator	R
2000	5	Southern	Height-for-age (Below -2SD)	0.453
2004	5	Southern	Height-for-age (below -2SD)	0.453
2010	5	Southern	Height-for-age (below -2SD)	0.476


[Updated on: Tue, 19 April 2016 17:23]

Report message to a moderator

Previous Topic: Children age Namibia DHS VI
Next Topic: Bangladesh and Nepal
Goto Forum:
  


Current Time: Thu Mar 28 09:44:04 Coordinated Universal Time 2024