Sevei blong Inkam mo Expendija blong Haoshol long Vanuatu 2010
The 2010 Household Income and Expenditure Survey (HIES) is the second survey of income and expenditure in Vanuatu to provide reliable sub-national estimates, with the 2006 HIES being the first time this was attempted. The first HIES was conducted in 1985 in the two urban centres of Luganville and Port Vila. Another was conducted in 1998 but unfortunately, for a number of reasons to do with errors of estimation and observation, the 1998 HIES did not provide reliable and accurate estimates. With the lessons learnt from past experience, the main objectives for the 2010 survey were to:
- Supply monitoring data needed for the then Millennium Challenge Account, Vanuatu (MCA) infrastructure projects;
- Supplement the data available for use in compiling official estimates of household accounts in the system of national accounts and subsequent estimates of Gross Domestic Product (GDP);
- Obtain expenditure weights and other data for the updating of the basket of items and weights used in the Consumer Price Index (CPI);
- Provide data for assessing the impact on household living conditions of existing and proposed economic and social policies and programmes, particularly those resulting in changes in the structure of household expenditure and consumption; and
- Gather information on key poverty indicators and statistics for poverty analysis.
Kind of Data
Sample survey data [ssd]
Version 01: Cleaned, labelled and anonymized version of the Master file.
consumption/consumer behaviour [1.1]
income, property and investment/saving [1.5]
economic conditions and indicators [1.2]
health care and medical treatment [8.5]
specific diseases and medical conditions [8.9]
general health [8.4]
There are eight main populations of interest for which estimates are required for the 2010 Household Income and Expenditure Survey (HIES): the provincial rural areas of Torba, Sanma, Penama, Malampa, Shefa, Tafea and the urban areas of Luganville and Port Vila. For this reason, the detailed analysis focuses on households from each of the eight sub-populations.
Unit of Analysis
Households (private) and individuals.
The survey coverage included only persons living in private households during the survey period (September to November 2006). Persons living in institutions, such as school dormitories, hospital wards, hostels, prisons, as well as those households which had temporarily vacated their dwellings were excluded from the survey. Also excluded from the survey were ex-patriot temporary residents and permanent residents who were not residing (and intending to reside) in Vanuatu for at least 12 months.
Producers and sponsors
Authoring entity/Primary investigators
Vanuatu National Statistics Office
Ministry of Finance and Economic Management
Milllanium Challenge Corperation
Department of Education
Department of Agriculture
Department of Health
Department of labour
Reserve Bank of Vanuatu
Department of Treasury
The sampling method adopted for the survey was a two-stage approach. The first stage involved the selection of Enumeration Areas (EA) using probability proportional to size (PPS) sampling. The size measure was the number of expected households in the EA, based on 2010 population census estimates. Although it would be desirable to cover all of Vanuatu for this survey, due to cost and time constraints some EAs were excluded from the frame before the selections were made. The impact on sub-population estimates will differ, as some areas have had larger scope reductions.
The second stage of sampling adopted systematic sampling from a list of all households contained in the EA. These lists were produced in the field by enumerators during the first visit to the EA. Once the sample had been selected, a review of where the selections were made was conducted to see how well they covered the projects of interest to the MCA. Approximately 18 enumeration areas (EA) were selected on Efate and 21 between Port Olry and Luganville in Santo, providing good representation of each of the areas. A final sample size of 4,737 households was selected for the survey representing around 10% of the households in Vanuatu.
In order to achieve the required level of accuracy for estimates for the target areas of the six provinces and two urban centres different sample allocations were tested to determine which allocation would produce estimates of similar levels of accuracy for each target area. This sample allocation resulted in the selection of approximately 600 in each province, with the exceptions of Luganville and Torba where less than 600 households were selected.
Each of the eight target areas was then further stratified to improve the representation within each of the different area types. Strata were determined by allocating Area Councils to area types based on the Area Council’s accessibility. As a result, 21 strata were used the final sample selection. Sample allocation to each stratum was derived by the proportionate allocation of the population within each “target area”.
Deviations from the Sample Design
Owing to cost and time constraints, some remote areas were not considered eligible for selection for the survey. Therefore the scope of the survey was reduced to 82.5 percent of all households in the population. Substantial reductions in scope occurred in Torba (62% in scope) and Malampa (68%) provinces. No enumeration areas were excluded in urban areas. While this may introduce some systematic bias, especially for the areas affected, the reduction of scope is not expected to affect the overall representativeness of the sample.
The response rate for the survey showed an improvement when compared with the 2006 Household Income and Expenditure Survey (HIES) as most of the regions recorded over 90%. Shefa, Tafea and Port Vila recorded between 87% and 90% response rates.
Below are some of the response rates by urban-rural regions:
-Urban: 90.9% (1063 responses out of 1169 selected);
-Rural: 92.9% (3314 responses out of 3568 selected);
-VANUATU: 92.4% (4377 responses out of 4737 selected).
The sample weights were calculated for each stratum separately, adjusted for non-response, and benchmarked against projected household counts for 2010 from the 2009 Census of Population and Housing.
Dates of Data Collection (YYYY/MM/DD)
Time periods (YYYY/MM/DD)
Listing of household for the first week of the month
Enumeration in the second week of the month
Diary for the last two weeks of the month
Mode of data collection
The National Statistics Office recruited and trained six provincial coordinators, 30 supervisors and 118 interviewers to conduct the survey in the six provincial areas and two urban centres. Over the survey period each interviewer completed three workloads of about 45 households in total.
Enumerators were asked to report to their supervisors if finding difficulties. If the one workload is completed then the supervisor should check. If the forms are not completed well then should give back to the enumerators to check again. Once the forms are completed the supervisor make the final check and sign it off and send to Provincial Cordinators check again. If there is still problems then the cordinator has to return the form back to the supevisor. Once this is done then the cordintaor will sign off the form then send to the head office. The office will then check if there are problems then will ask for clarification from cordinator and supervisor. The cordinators and supervisors were asked to visit their enumerators once a week.
The enumerators and supervisors were given impress, maps, list of all the villages in the EA and the selected households. Also they were given separate manual for enumerators and separate for the supervisor. The supervsiros were alsom given GPS to record the actual location of the basic services such as hospitals, health centres, clinics, whafts, market centres, schools and shops. The were allso instructed to locate the actual villages locations.
Type of Research Instrument
The questionnaire was developped both in English and Bislama. It is made of 4 forms that are listed below:
- Household Control Form (HCF)- was designed to list all the members of households, their date of birth, sex, maritial status relationship to the head of the household;
- Household Questionnaire Form - Part 1: Dwelling Characteristics, Access to Transport, Communication, Health, Sanitation and Market Centres, Part II: Household Expenditure, Part III: Income and Production;
- Person Questionnaire Form - captures information regarding Demographic, health, education and economic activity for household members;
- Household two weeks diaries to collect daily consumption and expenditure.
Vanuatu National Statistics Office
Ministry of Finance and Economic Management
Some initial editing was carried when the forms were coded and prepared for data entry. There were then several strands of editing carried out after the data entry was completed.
A set of tables designed to identify missing, illegal or potentially incompatible values in the classificatory data was specified.
The development of the "Generate new records" program, described above, required extensive examination of the data. First, it was sometimes necessary to examine original questionnaires to obtain a better understanding of how households responded to certain questions, especially when the recorded responses were unexpected. Second, the development of some of the imputation functions implemented in the program required analysis of detailed data. Third, testing of the program required examination of data before and after transformation to ensure that the program was carrying out its intended functions. These and other more minor reasons for examining the data collectively also played an important editing function, even though it was unstructured from an editing point of view. Most of the editing actions flowing from this work are recorded in Queries.xls.
Outlier analysis is an important part of the editing process for household surveys. For the Household Income and Expenditure Survey (HIES), formal outlier analysis has largely been confined to examining households with very high income or expenditure. However, outliers were also detected during the processes described in the previous paragraphs.
Some obvious errors were fixed and missing data supplied manually at the time of the initial coding and checking of the questionnaires prior to the data entry stage. Similarly changes were made as a result of editing queries described in the previous section.
A more automated form of imputation was implemented for certain instances of missing data.
For those transactions recorded in diaries where a quantity was supplied without a value, a value was imputed on the basis of transactions in the same commodity in the same province/urban area. Consideration was given to imputing separately for each transaction type (purchases, own account production, gifts given, gifts received) but there is not sufficient data to use a cross classification of province/urban and transaction type. Examination of differences in unit values between provinces/urban areas and between transaction types showed greater differences between provinces/urban areas than between transaction types. Where there was no required data for a commodity in a particular province/urban area, the unit value from a similar province/urban area was used. Calculations are included in value and quantity by prov city 2.xls. Transaction values imputed in this way are flagged on the file by means of the "data source" variable.
For employees who did not report their gross wages and salaries, a value was imputed on the basis of the average wage/salary of other employees with the same industry and occupation codes and who reported their value. Where there were no other employees in the same category reporting wages/salary, the value for a similar industry and occupation code was used. Calculations are included in supporting file W&S 5.xls. Any imputed values were included in the transaction record for wage and salaries for the household concerned (there is only one aggregate record per household, which combines the wages and salaries of all members of the household). If any component is imputed, the whole transaction is flagged as imputed. However, the imputed value is not included in the PERSON record.
For households that own their own dwelling (including those with a loan or mortgage) but who did not estimate the potential rental value of their dwelling in the household questionnaire, a value was imputed on the basis of the average for other dwellings in the same enumeration area. Potential rental values are not included in aggregate income or expenditure and therefore there are no transaction records for these values. Rather they are stored in the dwelling characteristic and tenure records. The imputed values are NOT flagged as imputed.
The data entry system was developed in CSPro, which requires the captured data to be stored in a complex record structure. In essence, the data from each page of each questionnaire is stored in a separate record, and each of those records has to have all its variables unique to itself.
13 computers were used for data entry with 13 data entry operators (three males and ten females). A program was developed to accommodate first and second entry (Double entry).
The data coding and manual editing of the questionnaires began in March 2011 and the scanning, data entry and micro editing was completed by the mid-June 2011. In 2010 all HIES questionnaires except for the daily expenditure diary were scanned. Scanning was used to decrease the time and resources required for data entry. The diaries were however manually entered into a database developed in-house due to low rates of optical character recognition for the data. After macro-editing and imputation, the data was transferred into a dataset that could be used for analysis, and tabulations were performed using Excel.
Estimates of Sampling Error
At the national level the Relative Sampling Errors (RSE) estimates are less than 5%, the level generally considered to provide reliable estimates.
At the urban and rural levels the RSEs for income and expenditure vary from 3 – 7%, indicating quality varying from very good (3%) to good (7%). At the provincial level the RSEs for the income and expenditure estimates vary from 3% to usable (12%).
Vanuatu National Statistics Office-Government Statistician
"Vanuatu National Statistics Office, Household Income and Expenditure Survey 2010 (HIES 2010), Version 01 of the licensed dataset (December 2019), provided by the Microdata Library. https://microdata.pacificdata.org/index.php/home"
Disclaimer and copyrights
The user of the data acknowledges that the original collector of the data, the authorized distributor of the data, and the relevant funding agency bear no responsibility for use of the data or for interpretations or inferences based upon such uses.
National Statistics Office, 2010 HIES
Vanuatu National Statistics Office-Government Statistician
Version 01 (July 2012): First documentation of the survey using IHSN Toolkit.
Version 02 (December 2019): Review of the exisiting documentation of the 2010 Household Income and Expenditure Survey of Vanuatu. Done by the Statistics for Development Division at Noumea, New Caledonia.