Nigeria - Nigeria Child Labour Survey 2022, First round
Reference ID | NGA-NBS-NCLS-2022-v01 |
Year | 2022 |
Country | Nigeria |
Producer(s) | National Bureau of Statistics (NBS) - Federal Government of Nigeria (FGN) |
Sponsor(s) | International Labour Organization - ILO - Funding |
Metadata | Documentation in PDF Download DDI Download RDF |
Created on | May 23, 2024 |
Last modified | May 23, 2024 |
Page views | 18398 |
Downloads | 566 |
Sampling
Sampling Procedure
The sample design for the survey was based on the National Integrated Survey of Households (NISH) master sample design developed by the NBS. This was developed from the frame of EAs demarcated by the National Population Commission for the 2006 housing and population census. The NISH design employed a replicated sampling design, a technique by which many samples (replicates) were selected independently
from a population such that each replicate sample represents the population.
Basically, the NISH sample design is a two-stage, replicated and rotated cluster sample design with EAs as the primary sampling units, and households as the secondary sampling units. Generally, for each Nigerian state and the FCT, the NISH master sample is made up of 200 EAs drawn into 20 replicates. A replicate consists of ten EAs.
The calculation of the sample size used the design effect of 1.2. Other parameters for the sample size calculation included the predicted value of the prevalence rate (40 per cent); the relative margin of error at 95 per cent confidence (5 per cent); the proportion of the target population in the base population (36.07 per cent); the average household size (5.06); and the expected response rate of households (95 per cent). The sample size of the survey was designed to provide state estimates of the prevalence of child labour with standard errors of about 1 per cent [r*RME/2 = 40%*5%/2 = 1%] under simple random sampling (RME = relative margin of error).
The sample design of the survey was based on a stratified two-stage sampling technique. In the first stage of sampling, 30 EAs were selected as part of a master sample in each of the 36 states and the FCT. In total, 1,110 EAs formed the primary sampling units of the survey. In the second stage, 15 households were systematically selected in each of the EAs. The target sample size was 16,650 households. All children 5 to 17 years
old living in the households were interviewed.
Deviations from Sample Design
The sample of the 2022 NCLS was targeted at 16,650 households but the number of households interviewed was slightly lower than anticipated (16,418) due to relocation and unavailability of some households.
Response Rate
NCLS 2022 was targeted at 16,650 households but in total 16,418 households were visited and interviewed, which represents a response rate of 98.6 per cent.
Weighting
The probability weight of the household was produced by taking the inverse of the probability to select the household (probability products obtained at each sampling stage). Weights were calculated by multiplying the probability of selection of EAs by the probability of selecting the households within the EAs and then taking the inverse of the product. An adjustment was made for non-responses before the final weight was applied to the dataset. Final weight values were further calibrated to follow the national population distribution by state.