Nigeria - Harmonised Nigeria Living Standards Survey 2009, First Round

The sample design employed for HNLSS Survey 2008/09 is a 2-stage cluster sample design in which Enumeration Areas (EAs) or Primary Sampling Units (PSUs) constitutes the 1st stage sample while the Housing units (HUs) from the EAs make up the 2nd stage sample or the Ultimate Sampling Units (USUs)

Sampling Frame
The enumeration areas (EAs) as demarcated by the National Population Commission (NPopC) for the 2006 population census served as the sampling frame for the HNLSS 2008/09.

Sample Size
Sample sizes must meet some minimal requirement in order to obtain reliable estimate. Hence, for HNLSS Survey 2008/09, the sample size varies from state to state depending on the number of Local Government Areas (LGAs) in each state. Ten (10) EAs were selected in each LGA making a total of 7,774 EAs to be canvassed for throughout the federation from the 774 LGAs including the Federal Capital Territory (FCT) Abuja.

Selection Procedure
The 7,740 EAs were selected directly from the population of the EAs in the NPopC with equal probability of selection. Prior to selection, all the contiguous EAs were arranged in serpentine order in each LGA of the state. This arrangement ensured that there was no overlapping


A total of 77,390 households were covered from a sample of 77,400 households giving the survey coverage rate of 99.9 percent. Of all the six zones, it was only SW zone that had the least response rate of 99.9 percent. The response rate in the remaining 5 zone was 100.0 percent each. Table 1.2 Status of Retrieval of Records by Zone and State attached to the report in External Resources


AS PER DATA SET
At households level, out of the 77,390 retrieved, only 73,329 were scanable.


Estimation Procedure
Let
E be the number of EAs in the state
e be the number of selected in the state
For a given stratum or domain, the estimate of the variance of a rate, r is given by

Var(r) = (se)2 = 1 ?(ri - r)2
K(k -1)i=1
Where
K is the number of clusters in the stratum or estimation domain
r is the weighted estimate calculated from the entire sample of clusters in the stratum
ri is equal to Kr - (K-1) r(i), where
r(i) is re-weighted estimate calculated from the reduced sample of K-1 clusters

To obtain an estimate of the variance at a higher level, say, at the national level, the process is repeated over all strata, with K redefined to refer to the total number of clusters (as opposed to the number in the stratum)

Estimation of Mean
Let
N be the total number of Housing Units listed for the selected EA
n be the number of selected Housing Units in the selected EA
Yij be the value of element from selected HUs of the selected EA
Y be the estimate of sample total

Therefore, for a proportion estimate, we have
. yij
.xi


No deviation


Total of 77,390 households were covered from a sample of 77,400 households giving the survey coverage rate of 99.9 percent

As per data set at households level, out of the 77,390 retrieved, only 73,329 were analysable giving 94.7 percent.

At sector level (Urban/Rural), 25.2% were recorded for Urban while Rural recorded 74.8%.


The NLSS, like most household surveys, is based on NISH frame. The NISH design is a two-stage design with EA's as first stage units and households as second stage units. Ten enumeration areas (EAs) were randomly selected each month and five household were systematically selected from the household listing of each selected EAs. Population level estimates are made by multiplying the data for each household by two factors, one equal to the inverse of the probability of selecting that household from the total list of households in its EA, and one equal to the inverse of the probability of selecting that EA from the list of EAs in its state. The selections can be done by treating every unit as the same and using simple random selection or, if the data is available, a more efficient sample can be selected using some size variable known for every unit of the population thought to be correlated with the variables of interest for measurement. So the weighting factor is at the EA level in each state:


where
Nh = the total number of EAs in state h.
nh = the number of sampled EAs in state h.
Mhi = the number of listed households in ith EA of state h.
nhi = the number of sampled households in ith EA of state h.
Xhij = the number of persons in the jth household in ith EA of state h.
Phij = the poverty score for the jth household in ith EA of state h.

So the above will apply to all the individual members in order to give the population. However, the above weighting factor will be multiplied by average household size, when there is need to take the household aggregates to the population.

The variable Household weight was used in the data set for the weight.