Nigeria - Multiple Indicator Cluster Survey/National Immunization Coverage Survey 2016-17, Fifth round (MICS) and NICS (third Round)
Reference ID | NGA-NBS-MICS5-NICS-2016-17-v1.1 |
Year | 2016 - 2017 |
Country | Nigeria |
Producer(s) | National Bureau of Statistics (NBS) - Federal Government of Nigeria |
Sponsor(s) | Bill and Melinda Gates Foundation - Bill Gates - Funding partner United Nations Children's Fund - UNICEF - Sponsor Save One Million Lives - SOML - Funding partner United Nations Population Fund - UNFPA - Funding partner World Bank - W |
Metadata | Documentation in PDF Download DDI Download RDF |
Study website |
Created on | Feb 20, 2019 |
Last modified | Feb 20, 2019 |
Page views | 598129 |
Downloads | 45340 |
Sampling
Sampling Procedure
The sample for the Nigeria MICS 2016-17 was designed to provide estimates for a large number of indicators on the situation of children and women at the national, rural/urban, states as well as the 6 geopolitical
zones of Nigeria. The states within each zone were identified as the main sampling Strata while the Enumeration Areas (EAs) within each state were identified as the Primary Sampling Units (PSUs). The EAs were selected from the National Integrated Survey of Households round 2 (NISH2) master sample, based on a list of EAs prepared for the 2006 Population Census. Two stage sampling was conducted with the first stage being the selection of EAs within the strata while the second stage was the selection of households within each EAs.
Within each state, 60 EAs were selected systematically from the NISH2 master sample, apart from Lagos and Kano states where 120 EAs (respectively) were sampled. The larger sample size for Lagos and Kano states was based on requests by the respective State governments to have sufficient sample to enable disaggregation of indicators at senatorial district level. After a household listing was carried out within the selected EAs, a systematic sample of sixteen (16) households was drawn in each sample EA. The sample was stratified by state and is not self-weighting. For reporting of results, sample weights were applied. Out of 2340 EAs selected for coverage, 2,239 were listed and covered during the fieldwork period. A total of 101 EAs could not be enumerated because they were inaccessible due to insecurity especially in Borno, Yobe and Adamawa states. A more detailed description of the sample design can be found in Appendix A
The Nigeria MICS 2016-17 was implemented jointly with the National Immunisation Coverage Survey (NICS) which was designed to provide estimates of vaccine coverage for the country. However, the sample size for MICS 2016-17 was not sufficient to estimate state level vaccination coverage for children aged 12 to 23 months in twenty states, namely: Abia, Akwa ibom, Anambra, Bayelsa, Benue, Cross River, Delta, Edo, Ekiti, Enugu, Imo, Kogi, Kwara, Ogun, Ondo, Osun, Oyo, Plateau, Rivers and FCT (Abuja). Consequently, supplemental sampling was conducted to meet the requirements for vaccine coverage estimation, in these
twenty states.
NICS (National Immunisation Coverage Survey) Sample design
The Nigeria NICS 2016-17 sample design based on precise estimation of pentavalent 3 vaccination coverage within ±10% in each state (reporting domain). When the proposed MICS samples were evaluated, it was realised that the “MICS sample” would not have been sufficient to estimate state vaccination coverage for children aged 12 to 23 months in 20 out of the 37 states based on the desired precision parameters. These states were Abia, Akwa Ibom, Anambra, Bayelsa, Benue, Cross River, Delta, Edo, Ekiti, Enugu, Imo, Kogi, Kwara, Ogun, Ondo, Osun, Oyo, Plateau, Rivers and FCT (Abuja). Consequently, to enable precise estimation of vaccination indicators in each state, supplemental sampling was conducted to meet the requirements for vaccine coverage estimation, in the 20 whose MICS 2016-17 was deficient. Immunisation indicators in these 20 states were estimated from analysis of the combined sample (supplemental sample + original MICS sample), while estimation of other MICS indicators these 20 states were done exclusively using the MICS sample.
Deviations from Sample Design
No deviation from the Sample Design.
Response Rate
Out of 37,440 households sampled, 35,747 households were visited, 34,289 were found to be occupied and 33,901 were successfully interviewed, representing a household response rate of 98.9 percent.
In the interviewed households, 36,176 women (age 15-49 years) were identified. Of these, 34,376 were successfully interviewed, yielding a response rate of 95.0 percent within the interviewed households.
The survey also sampled men (age 15-49), but required only a subsample. All men (age 15-49) were identified in 17,868 households selected for the men questionnaire; 16,514 men (age 15-49 years) were
listed in the household questionnaires. Questionnaires were completed for 15,183 eligible men, which corresponds to a response rate of 91.9 percent within eligible interviewed households.
There were 28,578 children under age five listed in the household questionnaires. Questionnaires were completed for 28,085 of these children, which corresponds to a response rate of 98.3 percent within
interviewed households.
Overall response rates of 93.9, 90.9 and 97.2 are calculated for the individual interviews of women, men, and under-5s, respectively
Table HH.1: Results of household, women's, men's and under-5 interviews
Number of households, women, men, and children under 5 by interview results, and household, women's, men's and under-5's response rates, Nigeria, 2016-17
Area Geopolitical zone
Total Urban Rural North central North east North west South east South south South west
Households
Expected sample 37,440 12,240 25,200 6,720 5,760 7,680 4,800 5,760 6,720
Actual sample 35,747 11,991 23,756 6,552 4,620 7,586 4,752 5,626 6,611
Occupied 34,289 11,311 22,978 6,318 4,447 7,424 4,593 5,387 6,120
Interviewed 33,901 11,104 22,797 6,244 4,396 7,395 4,524 5,354 5,988
HH response rate 98.9 98.2 99.2 98.8 98.9 99.6 98.5 99.4 97.8
Women
Eligible 36,176 11,689 24,487 7,462 5,469 9,765 3,753 4,918 4,809
Interviewed 34,376 10,965 23,411 7,013 5,223 9,376 3,645 4,728 4,391
Women's response rate 95.0 93.8 95.6 94.0 95.5 96.0 97.1 96.1 91.3
Women's overall response rate 93.9 92.1 94.9 92.9 94.4 95.6 95.7 95.5 89.3
Men
Eligible 16,514 5,450 11,064 3,468 2,559 4,356 1,568 2,253 2,310
Interviewed 15,183 4,890 10,293 3,184 2,452 3,935 1,481 2,173 1,958
Men's response rate 91.9 89.7 93.0 91.8 95.8 90.3 94.5 96.4 84.8
Men's overall response rate 90.9 88.1 92.3 90.7 94.7 90.0 93.0 95.9 82.9
Children under 5
Eligible 28,578 7,612 20,966 5,474 4,855 9,662 2,399 3,187 3,001
Mothers/caretakers intervd. 28,085 7,471 20,614 5,347 4,733 9,519 2,383 3,172 2,931
Under-5's response rate 98.3 98.1 98.3 97.7 97.5 98.5 99.3 99.5 97.7
Under-5's overall response rate 97.2 96.4 97.5 96.5 96.4 98.1 97.8 98.9 95.6
For the National Immunization Coverage Survey (NICS) 2016/17, from the 40,518 interviewed households, 6,360 mothers/caretakers of children age 12 to 23 months were identified. Of these, 6,268 were successfully interviewed, yielding a response rate of 98.3 percent within interviewed households.
Also, Out of a total of 44,960 households planned for selected for coverage, 42,981 were canvassed but only 41,059 were found to be occupied. Of these, 40, 518 were successfully interviewed for a household response rate of 98.7 percent.
Weighting
Sample weights were calculated for each of the data files.
Sample weights for the household data for 34 states (excluding Kano and Lagos) and Abuja FCT were computed as the inverse of its probability of selection (calculated by multiplying the probabilities at each sampling stage); In the case of the states of Kano and Lagos, the NISH2 master sample EAs were stratified by senatorial district and the EAs were selected
separately within each senatorial district. The basic weight for the MICS 2016 sample households is the inverse of the overall probability of selection.
Following the adjustment of the raw household weights for non-response, these weights are generally normalized (standardized) so that relative weights are used for the analysis of the survey data. In this way the sum of the relative weights is equal to the number of sample households at the national level. The household weights were normalized by dividing each weight by the average weight at the national level (that is, the sum of the weights for all sample households divided by the number of sample households).
The non-response adjustment factors for the individual women, men, and under-5 questionnaires were applied to the adjusted household weights. Numbers of eligible women, men, and under-5 children were obtained from the roster of household members in the Household Questionnaire for households where interviews were completed.
The women, men and child weights are normalized in the same way as the household weights. In this case the full (raw) weights were divided by the average women, men or child weight, respectively. Sample weights were appended to all data sets and analyses were performed by weighting households, women, men, or under-5s with these sample weights.
MICS sample was not self-weighting, sampling weights were computed for use in subsequent analysis. Cluster-based (EA) weights were computed by normalising the product of the reciprocal of the sampling probability and the response rate. The main component of the sampling weights is the reciprocal of the sampling fraction employed while selecting the number of households in a sampling stratum (state) and PSU (enumeration area).
The sampling fractions correspond to the probability of sampling enumeration areas in a state and the probability of sampling households within an enumeration area respectively. Enumeration area (EA) sampling probability was computed at state level as the proportion of enumeration areas selected for each state and the number of enumeration areas in the state as per the 2006 National Population Census master sampling frame while the household sampling probability was computed as the fraction of number of households selected per enumeration area (16) divided by the number of households in the enumeration area updated during household listing exercise. As there was a difference in the number of EAs selected in the MICS and MICS/NICS sample in states where supplemental sampling was conducted, naturally, the sampling probability within the MICS dataset would differ from the sampling probability in the MICS/NICS. Sampling weights in the states with no supplemental sampling, on the other hand, were similar in both the MICS and MICS/NICS dataset.