Nigeria - Demographic and Health Survey, 2003, Fourth Round
Reference ID | NGA-NPC-DHS-2003-v1.0 |
Year | 2003 |
Country | Nigeria |
Producer(s) | National Population Commission (NPC) - Federal Government of Nigeria (FGN) |
Sponsor(s) | President’s Emergency Plan for AIDS Relief - PEPFAR - funding United Nations Population Fund - UNFPA - funding MEASURE DHS Project - MEASURE - funding |
Metadata | Documentation in PDF Download DDI Download RDF |
Created on | Oct 18, 2010 |
Last modified | Dec 02, 2013 |
Page views | 1165566 |
Downloads | 22860 |
Sampling
Sampling Procedure
The primary sampling unit (PSU), or cluster, for the 2003 NDHS is defined as one or more EAs from the 1991 census frame. A minimum requirement of 50 households per cluster was imposed on the
design; in the case of less than 50 households, a contiguous EA was added. The number of clusters in each state was not allocated in proportion to the state's population because of the need to obtain estimates for each of the six zones. Since Nigeria is a country where the majority of the population resides in rural areas, the number of clusters allocated to the urban areas in five out of the six zones was increased in order to obtain reasonable urban estimates.
The target of the 2003 NDHS sample was to obtain completed interviews with about 8,250 women. Based on the level of nonresponse found in the 1999 Nigeria DHS survey, a target of 7,935
households was set. When the sample was implemented, three clusters could not be visited because of communal clashes, so 7,864 households were selected, in which all women age 15-49 were eligible to be interviewed. To obtain estimates of fertility and child mortality with a reasonable level of precision, a minimum of 1,200 completed interviews with women was desired in each zone. In each state, the number of households was not distributed proportionally between urban and rural areas. Also, in six designated states, a minimum of 350 completed interviews were targeted to provide selected indicators.
The 2003 NDHS sample was selected using a stratified, two-stage cluster design. A total of 365 clusters were selected, 165 in urban and 200 in rural areas. Table A.1 shows the distribution of clusters
selected for the 2003 NDHS. Once the number of households was allocated to each state by urban and rural areas, the numbers of clusters was calculated based on an average sample take of 20 completed women's interviews (in 19 selected households) in urban areas, and 25 completed interviews (in 24 selected households) in rural areas. In each urban or rural area in a given state, clusters were selected systematically with equal probability. The selection was done using the following formula:
In every third household selected, all men age 15-59 listed in the household were eligible to be interviewed. Based on data from the 1999 NDHS, this was expected to produce a total of about 2,800 successfully completed male interviews in the 2003 NDHS.
NOTE:
See the formula page 233 and more about the sampling procedure in table A1 page 232 in the report attached in external resources.
Deviations from Sample Design
No deviation was reported in the survey report use for the documentation.
Response Rate
The household and individual response rates for the 2003 NDHS. A total of 7,864 households were selected for the sample, of which 7,327 were found.
The shortfall is largely due to structures that were found to be vacant. Of the 7,327 existing households, 7,225 were successfully interviewed, yielding a household response rate of 99 percent. In these households, 7,985 women were identified as eligible for the individual interview. Interviews were completed with 95 percent of them. Of the 2,572 eligible men identified, 91 percent were successfully interviewed.
There is little difference between urban and rural response rates.
NOTE:
Results of the household and individual interviews response rates for the 2003 NDHS are shown in Table 1.2 in the report page 36 attached as external resources.