Abstract

The programme for the World Census of Agriculture 2000 is the eighth in the series for promoting a global approach to agricultural census taking. The first and second programmes were sponsored by the International Institute for Agriculture (IITA) in 1930 and 1940. Subsequent ones up to 1990 were promoted by the Food and Agriculture Organization of the United Nations(FAO). FAO recommends that each country should conduct at least one agricultural census in each census programme decade and its programme for the World Census of Agriculture 2000 for instance corresponds to agricultural census to be undertaken during the decade 1996 to 2005. Many countries do not have sufficient resources for conducting an agricultural census. It therefore became an acceptable practice since 1960 to conduct agricultural census on sample basis for those countries lacking the resources required for a complete enumeration.

In Nigeria's case, a combination of complete enumeration and sample enumeration is adopted whereby the rural (peasant) holdings are covered on sample basis while the modern holdings are covered on complete enumeration. The project named “National Agricultural Sample Census” derives from this practice. Nigeria through the National Agricultural Sample Census (NASC) participated in the 1970's, 1980's, 1990's programmes of the World Census of Agriculture. Nigeria failed to conduct the Agricultural Census in 2003/2004 because of lack of funding. The NBS regular annual agriculture surveys since 1996 had been epileptic and many years of backlog of data set are still unprocessed. The baseline agricultural data is yet to be updated while the annual regular surveys suffered set back. There is an urgent need by the governments (Federal, State, LGA), sector agencies, FAO and other International Organizations to come together to undertake the agricultural census exercise which is long overdue. The conduct of 2006/2008 National Agricultural Sample Census Survey is now on course with the pilot exercise carried out in the third quarter of 2007.

The National Agricultural Sample Census (NASC) 2006/08 is imperative to the strengthening of the weak agricultural data in Nigeria. The project is phased into three sub-projects for ease of implementation; the Pilot Survey, Modern Agricultural Holding and the Main Census. It commenced in the third quarter of 2006 and to terminate in the first quarter of 2008. The pilot survey was implemented collaboratively by National Bureau of Statistics.

The main objective of the pilot survey was to test the adequacy of the survey instruments, equipments and administration of questionnaires, data processing arrangement and report writing. The pilot survey conducted in July 2007 covered the two NBS survey system-the National Integrated Survey of Households (NISH) and National Integrated Survey of Establishment (NISE). The survey instruments were designed to be applied using the two survey systems while the use of Geographic Positioning System (GPS) was introduced as additional new tool for implementing the project.

The Stakeholders workshop held at Kaduna on 21st-23rd May 2007 was one of the initial bench marks for the take off of the pilot survey. The pilot survey implementation started with the first level training (training of trainers) at the NBS headquarters between 13th - 15th June 2007. The second level training for all levels of field personnels was implemented at headquarters of the twelve (12) concerned states between 2nd - 6th July 2007. The field work of the pilot survey commenced on the 9th July and ended on the 13th of July 07. The IMPS and SPSS were the statistical packages used to develop the data entry programme.

Geographic coverage

State

Analysis unit

Household crop farmers

Universe

Crop farming household

Kind of data

Census/enumeration data [cen]

Sampling procedure

The survey was carried out in 12 states falling under 6 geo-political zones. 2 states were covered in each geo-political zone. 2 local government areas per selected state were studied. 2 Rural enumeration areas per local government area were covered and
4 Crop farming housing units were systematically selected and canvassed .

Sampling deviation

No deviation

Mode of data collection

Face-to-face [f2f]

Research instrument

The NASC crop questionnaire was divided into the following sections: - Holding identification - Holding characteristics - Access to land - Access to credit and funds used - Production input utilization, quantity and cost - Sources of inputs/equipment - Area harvested - Agric machinery - Production - Farm expenditure - Processing facilities - Storage facilities - Employment in agric. - Farm expenditure - Sales - Consumption - Market channels - Livestock farming - Fish farming

Cleaning operations

The data processing and analysis plan involved five main stages: training of data processing staff; manual editing and coding; development of data entry programme; data entry and editing and tabulation. Census and Surveys Processing System (CSPro) software were used for data entry, Statistical Package for Social Sciences (SPSS) and CSPro for editing and a combination of SPSS, Statistical Analysis Software (SAS) and EXCEL for table generation. The subject-matter specialists and computer personnel from the NBS and CBN implemented the data processing work. Tabulation Plans were equally developed by these officers for their areas and topics covered in the three-survey system used for the exercise. The data editing is in 2 phases namely manual editing before the data entry were done. This involved using editors at the various zones to manually edit and ensure consistency in the information on the questionnaire. The second editing is the computer editing, this is the cleaning of the already entered data. The completed questionnaires were collected and edited manually (a) Office editing and coding were done by the editor using visual control of the questionnaire before data entry (b) Cspro was used to design the data entry template provided as external resource (c) Ten operator plus two suppervissor and two progammer were used (d) Ten machines were used for data entry (e) After data entry data entry supervisor runs fequency on each section to see that all the questionnaire were enterd

Response rate

The response rate at EA level was 100 percent, while 98.44 percent was achieved at crop farming housing units level

Sampling error estimates

No computation of sampling error

Data appraisal

The Quality Control measures were carried out during the survey, essentially to ensure quality of data. There were two levels of supervision involving the supervisors at the first level, NBS State Officers and Zonal Controllers at second level and finally the NBS Headquarters staff constituting the second level supervision.

BackgroundThe conduction and report of network meta-analysis (NMA), including the presentation of the network-plot, should be transparent. We aimed to propose metrics adapted from graph theory and social network-analysis literature to numerically describe NMA geometry.MethodsA previous systematic review of NMAs of pharmacological interventions was performed. Data on the graph’s presentation were collected. Network-plots were reproduced using Gephi 0.9.1. Eleven geometric metrics were tested. The Spearman test for non-parametric correlation analyses and the Bland-Altman and Lin’s Concordance tests were performed (IBM SPSS Statistics 24.0).ResultsFrom the 477 identified NMAs only 167 graphs could be reproduced because they provided enough information on the plot characteristics. The median nodes and edges were 8 (IQR 6–11) and 10 (IQR 6–16), respectively, with 22 included studies (IQR 13–35). Metrics such as density (median 0.39, ranged 0.07–1.00), median thickness (2.0, IQR 1.0–3.0), percentages of common comparators (median 68%), and strong edges (median 53%) were found to contribute to the description of NMA geometry. Mean thickness, average weighted degree and average path length produced similar results than other metrics, but they can lead to misleading conclusions.ConclusionsWe suggest the incorporation of seven simple metrics to report NMA geometry. Editors and peer-reviews should ensure that guidelines for NMA report are strictly followed before publication.

Abstract

The main objective of the Pilot Survey was to test the adequacy of the survey instruments, equipments and administration of questionnaires, data processing arrangement and report writing. The Pilot survey conducted in July 2007 covered the two NBS survey system-the National Integrated Survey of Households (NISH) and National Integrated Survey of Establishment (NISE). The survey instruments were designed to be applied using the two survey systems while the use of Geographic Positioning System (GPS) was introduced as additional new tool for implementing the project.

The programme for the World Census of Agriculture 2000 is the eighth in the series for promoting a global approach to agricultural census taking. The first and second programmes were sponsored by the International Institute for Agriculture (IITA) in 1930 and 1940. Subsequent ones up to 1990 were promoted by (FAO). Food and Agriculture Organization of the United Nations recommends that each country should conduct at least one agricultural census in each census programme decade and its programme for the World Census of Agriculture 2000 for instance corresponds to Agricultural Census to be undertaken during the decade 1996 to 2005. Many countries do not have sufficient resources for conducting an agricultural census. It therefore became an acceptable practice since 1960 to conduct agricultural census on sample basis for those countries lacking the resources required for a complete enumeration.

In Nigeria's case, a combination of complete enumeration and sample enumeration is adopted whereby the rural (peasant) holdings are covered on sample basis while the modern holdings are covered on complete enumeration. The project named "National Agricultural Sample Census" derives from this practice. Nigeria through the National Agricultural Sample Census (NASC) participated in the 1970's, 1980's, 1990's programmes of the World Census of Agriculture. Nigeria failed to conduct the Agricultural Census in 2003/2004 because of lack of funding.

The NBS regular annual agriculture surveys since 1996 had been epileptic and many years of backlog of data set are still unprocessed. The baseline agricultural data is yet to be updated while the annual regular surveys suffered set back. There is an urgent need by the Governments (Federal, State, LGA), sector agencies, FAO and other International Organizations to come together to undertake the agricultural census exercise which is long overdue. The conduct of 2006/2008 National Agricultural Sample Census Survey is now on course with the pilot exercise carried out in the third quarter of 2007.

The National Agricultural Sample Census (NASC) 2006/08 is imperative to the strengthening of the weak agricultural data in Nigeria. The project is phased into three sub-projects for ease of implementation; the Pilot Survey, Modern Agricultural Holding and the Main Census. It commenced in the third quarter of 2006 and to terminate in the first quarter of 2008. The pilot survey was implemented collaboratively by National Bureau of Statistics.

The Stakeholders workshop held at Kaduna on 21st-23rd May 2007 was one of the initial bench marks for the take off of the Pilot Survey. The Pilot Survey implementation started with the first level training (Training of Trainers) at the NBS Headquarters between 13th - 15th June 2007. The second level training for all levels of field personnels was implemented at Headquarters of the twelve (12) concerned states between 2nd - 6th July 2007. The field work of the Pilot Survey commenced on the 9th July and ended on the 13th of July 07. The CSpro and SPSS were the statistical packages used to develop the data entry programme. The results of the survey are presented in chapter three of this report.

The owner-like possession was the most common system nationwide with a figure of 2,083,503 (holding) followed by family land 962,233 (holding) while squatter was the least system used 40,473 (holding). Distribution of holding by type of land showed that three types of land-upland, lowland and irrigated were mostly used with irrigated land being the highest 5,825,531 holding followed by lowland 5,320,782 holding and upland 3,070,911 holdings with the highest holding within the age group of 25-44 years. In all states, 2,392,725 males were involved in crop farming while 540,070 females were also paticipating. Out of the 11 major crops reported, cassava recorded the highest number of farms 2,649,098 farms, next was maize 2,199,352 and yam 2,042,440 farms while the least was cotton 46,287 farms. Other crops were Beans, Cocoyam, Groundnut, Guinea corn, melon, Millet and Rice.

Geographic coverage

State

Analysis unit

Household based

Universe

Household

Kind of data

Sample survey data [ssd]

Sampling procedure

12 states were purposely selected in the country. 2 states from each of the 6 geo-political zones. 2 LGAs per selected state were studied. 2 Rural EAs per LGA were covered and 5 Housing Units were systematically selected and canvassed for GHS data.

Sampling deviation

No Deviation

Mode of data collection

Face-to-face [f2f]

Research instrument

The questionnaire for the Private Farmers (Holding) is a structured questionnaire based on household characteristics with some modifications and additions. The questionnaire contains the following sections. Holding identification Holding Characteristics Access to Land Access to Credit and Funds Used Production input utilization; quantity and cost Sources of inputs/equipment Area Harvested. Agric Machinery. Production. Farm Expenditure. Processing Facilities. Storage Facilities. Employment in Agric. Farm Expenditure. Sales. Consumption. Market Channels. Livestock Farming. Fish Farming.

Cleaning operations

The data editing is in 2 phases namely manual editing before the questionnaires were scanned. This involved using editors at the various zones to manually edit and ensure consistency in the information on the questionnaire. The second editing is the computer editing, this is the cleaning of the already scanned data. The subject-matter specialists and computer personnel from the NBS and CBN implemented the data processing work. Tabulation Plans were equally developed by these officers for their areas and topics covered in the three-survey system used for the exercise.

The data editing is in 2 phases namely manual editing before the data entry were done. This involved using editors at the various zones to manually edit and ensure consistency in the information on the questionnaire. The second editing is the computer editing, this is the cleaning of the already enterd data. The completed questionnaires were collated and edited manually

(a) Office editing and coding were done by the editor using visul contro of the questionnaire before data entry (b) Cspro was used to design the data entry template provided as external resource (c) Ten operator plus two suppervissor and two progammer were used (d) Ten machines were used for data entry (e) After data entry data entry supervisor runs fequency on each section to see that all the questionnaire were enterd

Response rate

On state basis, 100 percent response rate was acheived at EA level .

While 99.6 percent was recorded at housing units level.

Sampling error estimates

No computation of sampling error

Data appraisal

The Quality Control measures were carried out during the survey, essentially to ensure quality of data. There were two levels of supervision involving the supervisors at the first level, NBS State Officers and Zonal Controllers at second level and finally the NBS Headquarters staff constituting the second level supervision.

Abstract

The Socio Economic Private Farmer Survey (CROP) is part of the brainchild of the National Bureau of Statistics (NBS) and is often referred to as a regular survey carried out on annual basis by the NBS over the years. In recent times, starting from 2004, there has been a collaborative effort between the NBS and the CBN in 2004 and 2005 till now the collaboration incorporated Nigerian Communications commission (NCC). The main reason of for conducting the survey was to enable the collaborating agencies fulfill their mandate in the production of current and credible statistics, to monitor and evaluate the status of the economy and the various government programmes such as the National Economic Empowerment and Development Strategy (NEEDS) and the Millennium Development Goals (MDGs).

The collaborative survey also assured the elimination of conflicts in data generated by the different agencies and ensured a reliable, authentic national statistics for the country.

Geographic coverage

National

Analysis unit

Household who engage in crop farming

Universe

The survey covered all the household members who were into crop production.

Kind of data

Sample survey data [ssd]

Sampling procedure

National Agricultural Sample Survey (Private Farmers Questionnaire Survey) samples were derived from the National Bureau of Statistics 2000/05 NISH sample design. The NISH employed a 2-stage, replicated and rotated cluster sample design with enumeration areas (EAs) as first stage sampling units [Primary Sampling Units (PSU)], while the housing units constituted the second stage sampling units [Secondary Sampling Units]. The housing units were the ultimate sampling units for the multi-subject survey.

The Private Farmers' Survey total sample size was 10,950 Farming Housing Units. In each State, the housing units were stratified into Farming and Non-Farming. Five housing units were systematically selected in each Enumeration Area. A sample size of 300 farming housing units was drawn from each State and 150 from FCT, Abuja. The total sample size of 10,950 could provide estimates at national and State levels.

For the NASS (Private Farmers), 5 farming housing Unit (FHUs) were selected systematically after stratifying the housing units into farming and non-farming housing units where all the holders within the selected farming housing units were interviewed using the private farmers questionnaires.

Mode of data collection

Face-to-face [f2f]

Research instrument

The questionnaire for the Socio Economic Private Farmers Survey (CROP) is a structured questionnaire based on household characteristics with some modifications and additions.

Cleaning operations

The data processing and analysis plan involved five main stages: training of data processing staff; manual editing and coding; development of data entry programme; data entry and editing and tabulation. Integrated Micro Prossor System (IMPS) and ACCESS software were used for data entry, Statistical Package for Social Sciences (SPSS) and Censuses and Surveys Processing System (CSPro) for editing and a combination of SPSS, Statistical Analysis Software (SAS) and EXCEL for table generation. The subject-matter specialists and computer personnel from the NBS and CBN implemented the data processing work. Tabulation Plans were equally developed by these officers for their areas and topics covered in the three-survey system used for the exercise.

The data editing is in 2 phases namely manual editing before the data entry were done. This involved using editors at the various zones to manually edit and ensure consistency in the information on the questionnaire. The second editing is the computer editing, this is the cleaning of the already enterd data.

The completed questionnaires were collated and edited manually using the following process: (a) Office editing and coding were done by the editor using visual control of the questionnaire before data entry (b) IMPS was used to design the data entry template provided as external resource (c) Ten operator plus two suppervissor and two progammer were used (d) Ten machines were used for data entry (e) After data entry data entry supervisor runs fequency on each section to see that all the questionnaire were enterd (f) Conversion progarm was written to convert the data to spss also provided

This download goves updated with RecID Adjustment Weights for the 1891-1911 England and Wales censuses and corresponds to Supplementary material for the paper "The Population of Non-corporate Business Proprietors in England and Wales 1891-1911", by Bennett, Robert J., Montebruno, Piero, Smith, Harry J. as an outcome of the ESRC project ES/M010953: Drivers of Entrepreneurship and Small Businesses PI Prof. Robert J. Bennett. The material consists of three raw text files 1. 1891 Employment status & Weights 2. 1901 Employment status & Weights 3. 1911 Employment status & Weights Each file has the three following variables: 1. RecID: the ID for I-CEM2 as in Higgs, Edward and Schürer, Kevin (University of Essex) (2014) The Integrated Census Microdata (I-CeM) UKDA, SN-7481; K. Schürer, E. Higgs, A.M. Reid, E.M Garrett, Integrated Census Microdata, 1851-1911, version V. 2 (I-CeM.2), (2016) [data collection] UK Data Service SN: 7481 2. Employment status: 1 Worker 2 Employer 3 Own-account 3. Weights: the inverse of the probability of giving an answer to the Employment Status question of the censuses by Sex and Relationship to the head of the family. A detailed explanation of how these weights were calculated and how to use them in the context of data analysis of this censuses can be found in the accompanying working paper, Montebruno, Piero (2018) ‘Adjustment Weights 1891-1911: Weights to adjust entrepreneurs taking account of non-response and misallocation bias in Censuses 1891-1911’, Working Paper 11: ESRC project ES/M010953: ‘Drivers of Entrepreneurship and Small Businesses’, University of Cambridge, Department of Geography and Cambridge Group for the History of Population and Social Structure. The files can be opened by any text editor, database management system (Access) or statistical package (Stata, SPSS) This dataset should be cited as Adjustment Weights 1891-1911, "The Population of Non-corporate Business Proprietors in England and Wales 1891-1911", by Bennett, Robert J., Montebruno, Piero, Smith, Harry J. Please cite using its DOI.

Abstract

The Multiple Indicator Cluster Survey (MICS) is a household survey programme developed by UNICEF to assist countries in filling data gaps for monitoring human development in general and the situation of children and women in particular. MICS is capable of producing statistically sound, internationally comparable estimates of social indicators. The Gambia Multiple Indicator Cluster Survey provides valuable information on the situation of children and women in The Gambia and was based, in large part, on the needs to monitor progress towards goals and targets emanating from recent international agreements: the Millennium Declaration, adopted by all 191 United Nations Member States in September 2000, and the Plan of Action of A World Fit For Children, adopted by 189 Member States at the United Nations Special Session on Children in May 2002. Both of these commitments build upon promises made by the international community at the 1990 World Summit for Children.

Survey Objectives: The 2006 Gambia Multiple Indicator Cluster Survey has as its primary objectives: - To provide up-to-date information for assessing the situation of children and women in the Gambia; - To furnish data needed for monitoring progress toward goals established in the Millennium Declaration, the goals of A World Fit For Children (WFFC), and other internationally agreed upon goals, as a basis for future action; - To contribute to the improvement of data and monitoring systems in the Gambia and to strengthen technical expertise in the design, implementation, and analysis of such systems.

Survey Content Following the MICS global questionnaire templates, the questionnaires were designed in a modular fashion customized to the needs of The Gambia. The questionnaires consist of a household questionnaire, a questionnaire for women aged 15-49 and a questionnaire for children under the age of five (to be administered to the mother or caretaker).

Survey Implementation The Gambia Multiple Indicator Cluster Survey (MICS) was carried by The Gambia Bureau of Statistics. Financial and technical support was provided by the United Nations Children's Fund (UNICEF). Technical assistance and training for the survey was provided through a series of regional workshops organised by UNICEF covering questionnaire content, sampling and survey implementation; data processing; data quality and data analysis; report writing and dissemination.

Geographic coverage

National

Analysis unit

Households (defined as a group of persons who usually live and eat together)

Household members (defined as members of the household who usually live in the household, which may include people who did not sleep in the household the previous night, but does not include visitors who slept in the household the previous night but do not usually live in the household)

Women aged 15-49

Children aged 0-4

Universe

The survey covered all de jure household members (usual residents), all women aged 15-49 years resident in the household, and all children aged 0-4 years (under age 5) resident in the household.

Kind of data

Sample survey data [ssd]

Sampling procedure

The sample for the Gambia's Multiple Indicator Cluster Survey (MICS) was designed to provide estimates on a large number of indicators on the situation of children and women at the national level, for urban and rural areas, and for 8 Local Government Areas (LGA): Banjul, Kanifing, Brikama, Mansakonko, Kerewan, Kuntaur, Janjanbureh and Basse. The LGAs were identified as the main sampling domains and the sample was selected in two stages. Within each LGA, at least 14 and at most 99 census enumeration areas were selected with probability proportional to size. After a household listing was carried out within the selected enumeration areas, a systematic sample of 6,175 households was drawn. The sample was stratified by LGA and urban and rural areas, it is not self-weighting. For reporting national level results, sample weights are used. A more detailed description of the sample design can be found in Appendix A of the final report and among the technical documents in the archive.

Sampling deviation

No major deviations from the original sample design were made. All sample enumeration areas were accessed and successfully interviewed with good response rates.

Mode of data collection

Face-to-face [f2f]

Research instrument

The questionnaires are based on the MICS III model questionnaire. Although translated versions of the questionnaires could not be produced for the survey, an attempt was made during the training of data collection personnel to translate all the questions into Mandinka, Fula and Wollof to ensure that there was a common approach to administering the questions to respondents in the local languages. All the questionnaires were pre-tested. Based on the results of the pre-test, modifications were made to the wording of some questions and translation problems identified and suitable alternatives discussed.

Cleaning operations

The Census and Survey program (CSpro3.1) was used for the data entry application. Eighteen main data entry clerks and 18 verifiers were appointed, and they completed the entry and verification in about 2 and a half months. The coders appointed were 20 in number and they completed coding in about one and a half month. Before the analysis started the datasets were free from all structural and inconsistency errors.

Data editing took place at a number of stages throughout the processing including: a) Office editing and coding b) During data entry c) Structure checking and completeness d) Secondary editing e) Structural checking of SPSS data files

Detailed documentation of the editing of data can be found in the data processing guidelines in the MICS manual http://www.childinfo.org/mics/mics3/manual.php.

Data processing and coding manuals were prepared . The data processing manual has detailed editing instructions in addition to instructions on how to use the data entry applications. Intensive trainings were given to the data entry clerks, coders and editors.

Response rate

Of the 6,175 households selected for the sample, 6,171 were found to be occupied. Of these, 6,071were successfully interviewed for a household response rate of 98.4 per cent. In the interviewed households, 10,252 women aged 15-49 were identified. Of these, 9,982 were successfully interviewed, yielding a response rate of 97.4 per cent. In addition, 6,641 under -5 children were listed in the household questionnaire. Copies of the questionnaires were completed for 6,543 of these children. This corresponds to a response rate of 98.5 per cent. Overall response rates of 95.8 per cent and 96.9 per cent are calculated for the women's and under-5's interviews respectively.

Sampling error estimates

Estimates from a sample survey are affected by two types of errors: 1) non-sampling errors and 2) sampling errors. Non-sampling errors are the results of mistakes made in the implementation of data collection and data processing. Numerous efforts were made during implementation of the MICS - 3 to minimize this type of error, however, non-sampling errors are impossible to avoid and difficult to evaluate statistically.

Sampling errors can be evaluated statistically. The sample of respondents to the MICS - 3 is only one of many possible samples that could have been selected from the same population, using the same design and expected size. Each of these samples would yield results that different somewhat from the results of the actual sample selected. Sampling errors are a measure of the variability in the results of the survey between all possible samples, and, although, the degree of variability is not known exactly, it can be estimated from the survey results. The sampling errors are measured in terms of the standard error for a particular statistic (mean or percentage), which is the square root of the variance. Confidence intervals are calculated for each statistic within which the true value for the population can be assumed to fall. Plus or minus two standard errors of the statistic is used for key statistics presented in MICS, equivalent to a 95 percent confidence interval.

If the sample of respondents had been a simple random sample, it would have been possible to use straightforward formulae for calculating sampling errors. However, the MICS - 3 sample is the result of a two-stage stratified design, and consequently needs to use more complex formulae. The SPSS complex samples module has been used to calculate sampling errors for the MICS - 3. This module uses the Taylor linearization method of variance estimation for survey estimates that are means or proportions. This method is documented in the SPSS file CSDescriptives.pdf found under the Help, Algorithms options in SPSS.

Sampling errors have been calculated for a select set of statistics (all of which are proportions due to the limitations of the Taylor linearization method) for the national sample, urban and rural areas, and for each of the five regions. For each statistic, the estimate, its standard error, the coefficient of variation (or relative error -- the ratio between the standard error and the estimate), the design effect, and the square root design effect (DEFT -- the ratio between the standard error using the given sample design and the standard error that would result if a simple random sample had been used), as well as the 95 percent confidence intervals (+/-2 standard errors).

Data appraisal

A series of data quality

Abstract

The primary purpose of the survey is to facilitate the estimation of poverty prevalence, and a study of the nature of poverty, in Southern Sudan. Briefly, analysis of the survey results should be able to tell us the proportion of Southern Sudan's population that lives below the poverty line, the spatial pattern of distribution of poverty across states and regions, and the manner in which poverty affects different aspects of the lives of poor people.

An additional purpose of the survey is to enable analysts to compute weights for the basket of commodities for each state so that a Consumer Price Index may be calculated for each state in the future. Thus far, CPI has only been calculated for five cities - Juba, Wau, Rumbek, Torit and Malakal. The CPI helps track price movements month-to-month and is useful for inflation targeting.

In addition to the above purposes, an important aspect for the use of the data is to enable other stake-holders in Southern Sudan including GoSS ministries, UN agencies, NGOs and researchers to carry out in-depth analysis of particular aspects of the data which are of interest to them. For example, we expect the survey to yield high-quality baseline information on labour force and agriculture to fill in these crucial data-gaps till full-fledged surveys can be held on these subjects.

Geographic coverage

The National Baseline Household Survey (NBHS) 2009 is a National Coverage, the sample covers the Ten States of Southern Sudan. The Data allowed comparison across Regions, States and a Urban / Rural split. In all the Ten States, all Counties were covered in the sample which gives a complete representation of the population of Southern Sudan. Replacements were done for those EAs that were under insecurity like the case in Jonglei and Western Equatoria State. One EA was replaced in Central Equatoria State was replace due demolition.

Analysis unit

Households and individuals

Kind of data

Sample survey data [ssd]

Sampling procedure

The Sample selected for the 2009 National baseline Household Survey (NBHS) was based on a stratified two stage Sampled Design. The Sampling frame was based on 2008 Sudan Census preliminary count of Household by Enumeration Areas (EAs) and the Census Cartography. The Primary Sample Units (PSUs) was EAs which were Census operational segments indentified on maps, with an average of 184 households in Urban and 136 Household in Rural areas.

For the NBHS, the Census EAs were stratified by State, Urban and Rural Areas. At the second sampling stage, households were selected from the listing in each sampled EA. The Sample Size was determined for obtaining reliable estimates for key survey indicators at State level, and for Urban and Rural domains at the National level.

A sample of 44 EAs was selected at the first sampling stage for each of the Ten States of Southern Sudan, and at the second stage, 12 households were selected from the listing of each sampled EA. Therefore 528 households per State were selected which total to a sample size of 5280 households for Southern Sudan.

Given the above, only 15.2% of the households in Southern Sudan were classified as Urban, a higher first stage sampling rates was used for the Urban Stratum of each State in order to improve the precision of Unban estimates at the National level.

Sampling deviation

During the survey, derivation from sample design occurred in Western Equatoria and Jonglei State. These were caused by insecurity in these States. In Central Equatoria, one EA was demolished which force the survey team to replace that EA.

Mode of data collection

Face-to-face [f2f]

Research instrument

The questionnaire for the survey was designed in consultation with data users to ensure their requirements could be incorporated. A technical Working Group and a user Needs Group were set up to decide on user requirement and priorities for the survey; these group included representatives from various ministries, UN agencies and NGOs.

The questionnaire contains several modules on different themes including health, education, labor, housing, asset ownership, access to credit, economic shocks, and transfers to the household, consumption and agriculture.

A pilot questionnaire was approved by the User Needs Group on 24th November 2008. The pilot survey was carried out in December 2008, following which some changes were made to the questionnaire. Finally, after several rounds of discussion between Central Bureau of Statistics (GoNU) and SSCCSE in January and February 2009, the final questionnaire was approved in February 2009.

The questionnaire is identical in both the South and the North with the exception of two modules which were only included selectively - child malnutrition (anthropometry) in the South and income in the North.

Cleaning operations

Data editing was first done manually in the field using Verification check list. Other edits were done in the office using the tif files. Edit rules were later apply using the SPSS.

Data receiving/scanner feeding responsible at data processing centre: Check 1: Number of forms total per EA counted and protocolled Check 2: Staples removed before scanning Check 3: Scan 1 EA per “batch” Check 4: Re-staple, mark as scanned and store

Scanning verification on screen: Check 1: (must-be-filled-in-check) If no codes for a1_state to a1_house, check TIFF file for text or writings outside box and put code based on text if possible - if not type 9, 99 or 999 (MISSING) to get past the check Check 2: (only-one-mark-allowed-check for all single response questions) If more than one mark, check TIFF file and correct if possible - if not possible to decide on correction, type 9 or 99 (to signal to SPSS professional editor) Check 3: (valid-range-checks) If outside range, verify TIFF on screen and be sure that what is written on the form is correctly interpreted (special focus on decimal errors and possible extra zeros given when writing SDGs). If errors identified then correct on screen, if not force the initial written value through without any changes. This will be dealt with in SPSS edits.

Other detailed documentation of the editing of the data can be found in the "Data processing guidelines" the document is provided in an external resource.

Response rate

The response rate for this study 100 percent.

Sampling error estimates

To estimate the standard errors for NBHS indicators estimation of variance for the proportion given in the formula was used: Vp'= Def*p (1-p)/(n-1), where: p - Proportion for the variance estimate, n - Sample size, and Def - effect of sample planning for the observed group of indicators. The standard error is the square root of Var xd'.

To calculate the variance for the whole population, the estimations of variance for the separate domains were summed. The approximate design effect was derived from the estimation of the variance of the simple random sample, and from the estimation of the variance proposed in the ultimate cluster method. The design effect was calculated for all groups of variance and separately for all observed domains. All differences denoted as significant in the text are significant at the 95 percent confidence level, unless otherwise indicated.

Data appraisal

Due to lack of standardize unit of measurement, price correction factors were used to adjust the prices. key corrections were done for abnormal quantities reported to have been consumed by Sampled Households

Abstract

Because of the importance of the household sector and due to it's large contribution to energy consumption in the Palestinian Territory, PCBS decided to conduct a special household energy survey to cover energy indicators in the household sector. To achieve this, a questionnaire was attached to the Labor Force Survey.

This survey aimed to provide data on energy consumption in the household sector and to provide data on energy consumption behavior in the society by type of energy.

This report presents data on various energy households indicators in the Palestinian Territory, and presents statistical data on electricity and other fuel consumption for the household sector, using type of fuel by different activities (cooking, Baking, conditioning, lighting, and water Heating).

Geographic coverage

The Palestinian Territory.

Analysis unit

Households

Universe

The target population was all Palestinian households living in the Palestinian Territory.

Kind of data

Sample survey data [ssd]

Sampling procedure

Sampling frame is a master sample from the Population, Housing and Establishment Census 1997. It consists of a list of enumeration areas, which were used as PSU's in the first stage of selection.

Sampling Design The sample of this survey is a sub-sample of Labour Force Survey (LFS) sample, that is conducted every 13 weeks. The total sample of LFS is about 7,559 households distributed over 13 weeks. The sample of the Household Energy Survey occupies six weeks of the third quarter 2006 of LFS.

Stratification: In designing the sample of LFS, three levels of stratification were made:

Stratification by governorate. Stratification by place of residence which comprises: (a) Urban (b) Rural (c) Refugee camps Stratification by locality size.

Sample Unit: In the first stage, the sampling units are the enumerator areas (clusters) in the master sample. In the second stage, the sampling units are households.

Analysis Unit: Analysis units are composed of households.

Sample Size: The sample size is of (3,115) Palestinian households in West Bank and Gaza Strip, where this sample has been distributed according to the locality in urban areas, in rural areas and in refugee camps.

Mode of data collection

Face-to-face [f2f]

Research instrument

The design of the questionnaire for the Household Energy Survey was based on the experiences of similar countries as well as on international standards and recommendations for the most important indicators, taking into account the special situation of the Palestinian Territory.

Cleaning operations

The data processing stage consisted of the following operations: Editing and coding before data entry: All questionnaires were edited and coded in the office using the same instructions adopted for editing in the field.

Data entry: At this stage, data was entered into the computer using a data entry template developed in Access. The data entry program was prepared to satisfy a number of requirements such as: · To prevent the duplication of the questionnaires during data entry. · To apply integrity and consistency checks of entered data. · To handle errors in user friendly manner. · The ability to transfer captured data to another format for data analysis using statistical analysis software such as SPSS.

Response rate

During fieldwork 3,115 Households were visited in the Palestinian Territory, the end results for the interview become as following: (2,695) complete questioner (33) traveling households (34) housing unit not existed (102) cases no body in the house (35) objection cases (158) housing unit abandoned (20) household can't give data (38) other cases

The responce rate was about 92.2%

Sampling error estimates

Sampling Errors: These types of errors evolved as a result of studying a part of the society and not all of it. For this survey, variance calculations were made for average household consumption and total consumption for the different types of energy in the Palestinian Territory.

Non Sampling Errors: These errors are due to non-response cases as well as the implementation of surveys. In this survey, these errors emerged because of (a) the special situation of the questionnaire itself which depends on type of estimation (b) diversity of sources (e.g. the interviewers, respondent, editors, coders, data entry operator …etc).

The sources of these errors can be summarized in: Some of the households were not in their houses and the interviewers couldn't meet them. Some of the households didn't show attention toward the questionnaire.
Some errors occurred due to the way the questions were asked by interviewers. Misunderstood of the questions by the respondents. Answering the questions related to consumption by making estimations.

Data appraisal

The data of the survey is comparable geographically and over time by comparing the data between different geographical areas to data of previous surveys.

Geographic coverage

Palestinian Territory

Analysis unit

Household

Universe

The target population consisted of all Palestinian households that usually reside in the Palestinian Territory

Kind of data

Sample survey data [ssd]

Sampling procedure

The sampling frame consisted of a master sample of enumeration areas (EAs) selected from the Population Housing and Establishment Census 2007 The master sample consists of area units of relatively equal size (number of households, about 150 housing units), and these units has been used as primary sampling units (PSUs).

Sample Size The sample size 7,500 households located in 300 enumeration areas in the Palestinian Territory, distributed by 5000 households in West Bank and 2500 in Gaza Strip. The design considered dissemination on governorate level and the localities affected by the annexation wall.

Sample design

The sample is two stage stratified cluster sample with two stages: First stage: selection a stratified systematic random sample of 300 Enumeration Areas (200 in west Bank, 100 in Gaza strip). Second stage: selection a systematic random sample of 25 households from each enumeration area selected in the first stage. And then to choose a legible person aged 18 years and above to be the respondent of the questionnaire questions.

Note: in Jerusalem Governorate (J1), 20 enumeration areas were selected; then in the second phase, a group of 25 households from each enumeration area were chosen using census-2007 method of delineation and enumeration. This method was adopted to ensure household response is to the maximum to comply with the percentage of non-response as set in the sample design.

Mode of data collection

Face-to-face [f2f]

Research instrument

A special questionnaire was designed in accordance with UN standards and recommendations, the questionnaire include the identification data in addition to the quality control measures, it covers the following fields: Part one: Social data which include name, relation with head of household, sex, age, refugee status, place of residence, reasons of changing place of residence if happened, health insurance, difficulties, education, labor and marital status. Part two: that covers the housing unit data. Part three: that covers the agricultural data. Part four: that covers the data on assistants. Part five: that covers the data on coping strategies> Part six: that covers the income data. Part seven: that covers the data on expenditure and consumption. Part eight: that covers the nutrition and lack of food. Part nine: that covers the data on freedom of movement.

Cleaning operations

Both data entry and tabulation were completed by using the ACCESS and SPSS software programs. Data entry was organized into two files, corresponding to the main parts of the questionnaire. Data entry template was designed to reflect an exact image of the questionnaire, and included various electronic checks: logical check, range checks, consistency checks and cross-validation.

Response rate

Response rate was 92%

Sampling error estimates

Statistical Errors: Sampling rather than comprehensive enumeration has been used to collect data in this survey. Therefore it is liable to two types of errors affecting the quality of survey data, sampling (statistical errors) and non-sampling errors (non-statistical errors). Statistical errors mean the errors resulting from sample designing and this is computed simply. Variance and effect of sample design has been computed for the Palestinian Territory, the West Bank and Gaza Strip.

Non-Statistical Errors: Non-statistical errors, on the other hand, could not be determined easily, due to the diversity of sources from which they may arise, e.g., the interviewer, respondent, editor, coder, and data entry operator.

Abstract

Though the National Bureau of Statistics generates youth and adult literacy data regularly on annual basis, the survey was conducted with a wider scope to complement the existing data on literacy in Nigeria. The main purpose of the survey was to determine the magnitude, levels and distribution of adult literacy and obtain comprehensive data and information with a view identifying issues of concern, which need to be addressed in the promotion of adult literacy in Nigeria. Underlying this is the fact that literacy is fundamental to information dissemination, socio-economic development and poverty alleviation among others. It was the first attempt to carry out a stand alone survey on Literacy Survey Nigeria.

The objectives of the 2009 National Literacy Survey were to: - Determine the magnitude, level and distribution of mass literacy (persons aged 15 year and above) - Obtain comprehensive data and information on mass literacy from literacy providers and stakeholders in both private and public sectors - Identify issues of concern which need to be addressed in the promotion of mass literacy in the country - Determine the number of persons aged 6 – 14 that are out of school - Ascertain number of persons mainstreaming from non-formal to formal education or vice versa

Geographic coverage

The survey will cover all the 36 states and Federal Capital Territory (FCT). Both urban and rural areas will be canvassed

Analysis unit

Household level

Kind of data

Sample survey data [ssd]

Sampling procedure

2.1 Sample Design 2.1.1 Introduction of NISH Design 1993/99

The Multiple Indicator Cluster Survey (MICS) 1999 was run as a module of the National Integrated Survey of Households (NISH) design. NISH is the Nigerian version of the United Nations National Household Survey Capability Programme and is a multi-subject household based survey system. It is an ongoing programme of household based surveys enquiring into various aspects of households, including housing, health, education and employment. The programme started in 1981 after a pilot study in 1980. The design utilizes a probability sample drawn using a random sampling method at the national and sub-national levels.

The main features of the NISH design are:

Multi-Phase Sampling: In each state 800 EAs were selected with equal probability as first phase samples. A second phase sample of 200 EAs was selected with probability proportional to size.

Multi-Stage Sampling Design: A two-stage design was used. Enumeration Areas were used as the first stage sampling units and Housing Units (HUs) as the second stage sampling units.

Replicated Rotatable Design: Two hundred EAs were selected in each state in 10 independent replicates of 20 EAs per replicate. A rotation was imposed which ensured 6 replicates to be studied each survey year but in subsequent year a replicate is dropped for a new one, that is, a rotation of 1/6 was applied. This means in a survey year, 120 EAs will be covered in each state. In the Federal Capital Territory (Abuja), 60 EAs are covered.

Master Sample: The EAs and HUs selected constitute the Master Sample and subsets were taken for various surveys depending on the nature of the survey and the sample size desired. In any one-year, the 120 EAs are randomly allocated to the 12 months of the year for the survey. The General Household Survey (GHS) is the core module of NISH. Thus, every month 10 EAs are covered for the GHS. For other supplemental modules of NISH, subsets of the master sample are used. The MICS 1999 was run as a module of NISH.

2.1.2 Sample Size

The global MICS design anticipated a sample of 300-500 households per district (domain). This was based on the assumption of a cluster design with design effect of about 2, an average household size of 6, children below the age of 5 years constituting 15 percent of the population and a diarrhoea prevalence of 25 percent. Such a sample would give estimates with an error margin of about 0.1 at the district level. Such a sample would usually come from about 10 clusters of 40 to 50 households per cluster.

In Nigeria, the parameters are similar to the scenario described above. Average household size varied from 3.0 to 5.6 among the states, with a national average of about 5.5. Similarly, children below 5 years constituted between 15-16 percent of total population. Diarrhoea prevalence had been estimated at about 15 percent. These figures have led to sample sizes of between 450 and 660 for each state.

It was decided that a uniform sample of 600 households per state be chosen for the survey. Although non-response, estimated at about 5 percent from previous surveys reduced the sample further, most states had 550 or more households. The MICS sample was drawn from the National Master Sample for the 1998/99 NISH programme implemented by the Federal Office of Statistics (FOS).

The sample was drawn from 30 EAs in each state with a sub-sample of 20 households selected per EA. The design was more efficient than the global MICS design which anticipated a cluster sub-sample size of 40-50 households per cluster. Usually, when the sub-sample size was reduced by half and the number of clusters doubled, a reduction of at least 20 percent in the design effect was achieved. This was derived from DEFF = 1 + (m-1) rho where m is sub-sample size and rho is intra-class correlation. Therefore, the design effect for the Nigerian MICS was about 1.6 instead of 2. This means that for the same size of 600 households, the error margin was reduced by about 10 percent, but where the sample was less than 600 the expected error margin would be achieved.

It should be noted that sampling was based on the former 30 states plus a Federal Capital Territory administrative structure [there are now 36 states and a Federal Capital Territory].

2.1.3 Selection of Households

The global design anticipated either the segmenting of clusters into small areas of approximate 40-45 households and randomly selecting one so that all households within such area was covered or using the random walk procedure in the cluster to select the 40-45 households. Neither of the two procedures was employed. For the segmentation method, it was not difficult to see that the clustering effect could be increased, since, in general, the smaller the cluster the greater the design effect. With such a system, DEFF would be higher than 2, even if minimally. The random walk method, on the other hand, could be affected by enumerator bias, which would be difficult to control and not easily measurable.

For NISH surveys, the listing of all housing units in the selected EAs was first carried out to provide a frame for the sub-sampling. Systematic random sampling was thereafter used to select the sample of housing units. The GHS used a sub-sample of 10 housing units but since the MICS required 20 households, another supplementary sample of 10 housing units was selected and added to the GHS sample. All households in the sample housing units were interviewed, as previous surveys have shown that a housing unit generally contained one household.

Sampling deviation

There were no deviation from sample design

Mode of data collection

Face-to-face [f2f]

Research instrument

The study used various instruments to collect the data. Apart from the main questionnaire that was developed for the survey and targeted the households and individuals, there were other instruments for the conduct of the assessment tests. The main questionnaire was structured in English Language but the interviewers were trained to translate and conduct the interview in local languages.

The questionnaire contains nine parts (A - I). Part A: Identification information Part B: Socio demographic background (all members) Part C: Educational attainment
Part D: Educational attainment
Part E: Literacy in english
Part F: Literacy in any other language Part G: Literacy in english Part H: Literacy in any other language Part I: Knowledge and accessibility of literacy programme

Cleaning operations

The 2009 National Literacy Survey data was processed in 4 stages namely, manual editing and coding, data entry, data cleaning and tabulation.

• Manual Processing - Completed questionnaires started arriving at the NBS headquarters two weeks after training from the states. Manual processing started with the development of editing/coding guidelines which were used to train the officers on manual editing. Development of data entry programme; data entry and editing and tabulation. Census and Surveys Processing System (CSPro) software were used for data entry, Statistical Package for Social Sciences (SPSS) and Census and Surveys Processing System (CSPro) for editing and a combination of SPSS, Statistical Analysis Software (SAS) and EXCEL for table generation.

The guidelines include errors that could be found in the completed questionnaires and how they could be corrected. These likely errors include omissions, inconsistencies, unreasonable entries, impossible entries, double entries, transcription errors and others found in the questionnaires. 10 officers were selected as editors, while 20 data entry staff were used in addition to 3 programers.

• Data Entry - The data entry was done manually, using the following steps: 1) Questionnaire reception 2) Office editing and coding 3) Data entry 4) Structure and completeness checking 5) Verification entry 6) Comparison of verification data 7) Back up of raw data 8) Secondary editing 9) Edited data back up After all clusters are processed, all data is concatenated together and then the following steps are completed for all data

Abstract

This report presents results of the 2010 the Kingdom of Eswatini MICS, carried out by CSO in collaboration with UNICEF and other partners. Since its launch in the mid-1990s, MICS has become one of the largest sources of information on a range of indicators including child health, nutrition, water and sanitation, reproductive health, education, child protection and HIV/AIDS. The 2010 Kingdom of Eswatini MICS was implemented to assess the current situation of the Swazi population, particularly children and women, as well as to measure progress towards goals and targets emanating from international agreements: the Millennium Declaration, adopted by all 191 United Nations Member States in September 2000, and the WFFC Plan of Action, adopted by 189 Member States at the United Nations (UN) Special Session on Children in May 2002. Both of these commitments build upon promises made by the international community at the 1990 World Summit for Children.

The 2010 Kingdom of Eswatini MICS is based on a nationally representative sample of 5,475 households selected from 365 enumeration areas distributed in the four regions of the country. It is an important source of information for measuring progress towards targets set by these various strategic plans, as well international declarations including the MDGs, the United Nations General Assembly Special Session Declaration of Commitment on HIV/AIDS (UNGASS) and others commitments.

Geographic coverage

National

Analysis unit

• individuals
• households

Universe

The survey covered all de jure household members (usual residents), all women aged between 15-49 years, all children under 5 living in the household, and all men aged 15-59 years.

Kind of data

Sample survey data [ssd]

Sampling procedure

The primary objective of the sample design for the 2010 Kingdom of Eswatini MICS was to produce statistically reliable estimates of most indicators, at the national level, for urban and rural areas, and for the four regions of the country (Hhohho, Manzini, Shiselweni and Lubombo).

A multi-stage, stratified cluster sampling approach was used for the selection of the survey sample. The 2006/07 Swaziland Demographic Health Survey (SDHS) collected many of the indicators in the MICS. Therefore, the results of the 2006/07 SDHS and the sample design were used as a reference in finalizing the sample design for the 2010 Swaziland MICS. In the survey, most of the indicators will be tabulated at the national level, urban and rural domains, and for the four regions as in the case of the 2006/07 SDHS.

The sampling frame for MICS comes from the recent Kingdom of Eswatini Census of Population and Housing data collected in 2007. The primary sampling units (PSUs) are the census enumeration areas (EAs). The EAs were created for the 2007 Census operations with well-defined boundaries identified on sketch maps. The number of households in an EA is based on the expected workload for one enumerator. According to the 2007 Census, the average number of households per EA is 103 (274 for rural EAs and 34 for urban EAs).

The sample size for a good household survey, such as the 2010 Kingdom of Eswatini MICS, is determined by the accuracy required for the estimates for each domain, as well as by the resource and operational constraints. The allocation of the sample EAs in each region to the rural and urban strata will be proportional to the number of households. Based on these criteria, the proposed allocation of sample EAs and households by region and rural and urban stratum results in a total sample of 365 EAs and 5,475 households.

The sampling procedures are more fully described in "Swaziland Multiple Indicator Cluster Survey 2010 - Final Report" pp.A1-A6.

Mode of data collection

Face-to-face [f2f]

Research instrument

The 2010 Kingdom of Eswatini MICS consists of four main questionnaires including a household questionnaire, women’s and men’s questionnaires and a questionnaire for children under age five. The survey includes information on key indicators on the following topics:

Household questionnaire: age, sex, urban vs. rural residency, household composition, education of household members, household assets, water and sanitation, use of iodized salt, use of insecticidetreated nets (ITNs), orphanhood and vulnerability of children, child labor and child discipline.

Questionnaire for children under five: birth registration, early childhood development, infant and young child feeding, care of illness (including diarrhoea and pneumonia), malaria, immunization and anthropometry.

Women’s questionnaire: child mortality, birth history, desire for last birth, maternal an newborn health, illness symptoms, contraception, unmet need, marriage/union, sexual behaviour, HIV/AIDS, sexually transmitted infections (STIs), and attitudes towards domestic violence.

Men’s questionnaire: marriage/union, attitudes towards contraception, sexual behaviour, HIV/AIDS, STIs, male circumcision and attitudes towards domestic violence.

Cleaning operations

Data entry commenced on 3 September after an initial training and ended on 17 December 2010. Data were entered on 10 computers by 10 data entry operators and two data entry supervisors using the CSPro software. In order to ensure quality control, all questionnaires were double entered and two secondary editors complemented the efforts of entry supervisors to perform internal consistency checks. Procedures and standard programmes developed under the global MICS4 survey were adapted, based on the modified Swaziland MICS questionnaires, and used throughout the processing. Data were analyzed using the Statistical Package for Social Sciences (SPSS) software programme, and syntax and tabulation plans developed for the global MICS4 were customized for this purpose.

Response rate

Of the 5,475 households selected for the sample nationally, 5,074 households were found to be occupied. Of these, 4,834 households were interviewed successfully yielding a household response rate of 95 percent. Among the interviewed households, 4,956 women age 15–49 years and 4,646 men age 15–59 years were identified. Of this number, 4,688 women and 4,179 men were successfully interviewed, yielding a response rate of 95 percent and 90 percent respectively. In addition, 2,711 children under age five were listed in the household questionnaire. Of these, questionnaires were completed for 2,647, corresponding to a response rate of 98 percent. Overall response rates of 90, 86 and 93 percent are calculated for under-five’s, women’s and men’s interviews respectively.

Responses varied slightly by residence with higher rates for women and men in rural areas than in urban areas. The situation was the reverse for children under-five where rural areas had higher response rates than urban areas. The overall response rate for women, men and children under five years in rural areas were, however, higher than in urban areas. The main reason for non-response among households and eligible individuals was the failure to find these individuals at home despite several visits to the households. Regional differentials also exist with all the regions having a 90 percent or higher response rate for all the questionnaires with the exception of Hhohho and Shiselweni regions that had 88 and 89 percent response rate, respectively, for the men’s questionnaire.

Sampling error estimates

The sample of respondents selected in the 2010 Kingdom of Eswatini MICS is only one of the samples that could have been selected from the same population, using the same design and size. Each of these samples would yield results that differ somewhat from the results of the actual sample selected. Sampling errors are a measure of the variability between all possible samples. The extent of variability is not known exactly, but can be estimated statistically from the survey results.

The following sampling error measures are presented in this appendix for each of the selected indicators:

Standard error (se): Sampling errors are usually measured in terms of standard errors for particular indicators (means, proportions etc). A standard error is the square root of the variance. The Taylor linearization method is used for the estimation of standard errors. Coefficient of variation (se/r) is the ratio of the standard error to the value of the indicator. Design effect (deff) is the ratio of the actual variance of an indicator, under the sampling method used in the survey, to the variance calculated under the assumption of simple random sampling. The square root of the design effect, called the design factor (deft) is used to show the efficiency of the sample design. A deft value of 1.0 indicates that the sample design is as efficient as a simple random sample, while a deft value above 1.0 indicates the increase in the standard error due to the use of a more complex sample design. Confidence limits are calculated to show the interval within which the true value for the population can be reasonably assumed to fall. For any given statistic calculated from the survey, the value of that statistics will fall within a range of plus or minus two times the standard error (p + 2.se or p – 2.se) of the statistic in 95 percent of all possible samples of identical size and design. For the calculation of sampling errors from the MICS data, the SPSS Complex Samples module has been used. The results are shown in the tables that follow. In addition to the sampling error measures described above, the tables also include weighted and unweighted counts of denominators for each