The 1996 Papua New Guinea household survey is designed to measure the living standards of a random sample of PNG households. As well as looking at the purchases, own-production, gift giving/receiving and sales activities of households over a short period (usually 14 days), the survey also collects information on education, health, nutrition, housing conditions and agricultural activities. The survey also collects information on community level access to services for education, health, transport and communication, and on the price levels in each community so that the cost of living can be measured.
There are many uses of the data that the survey collects, but one main aim is for the results to help government, aid agencies and donors have a better picture of living conditions in all areas of PNG so that they can develop policies and projects that help to alleviate poverty. In addition, the survey will provide a socio-economic profile of Papua New Guinea, describing the access that the population has to agricultural, educational, health and transportation services, their participation in various economic activities, and household consumption patterns.
The survey is nationwide and the same questionnaire is being used in all parts of the country, including the urban areas. This fact can be pointed out if households find that some of the questions are irrelevant for their own living circumstances: there are at least some Papua New Guinean households for which the questions will be relevant and it is only by asking everyone the same questions that living standards can be compared.
Kind of Data
Sample survey data [ssd]
The survey covers all provinces except Noth Solomons.
Unit of Analysis
Producers and sponsors
Authoring entity/Primary investigators
Unisearch PNG, Institute of National Affairs
University of Waikato
The Household Listing Form and Selection of the Sample
Listing of households is the first job to be done after the team has settled in and completed the introductions to the community. Listing is best done by the whole team working together. This way they all get to know the community and its lay-out. However, if the census unit is too large this wastes too much time. So before beginning asks how many households there are, very roughly, in the census unit (noting that teams are supplied with the number of households that were there in the 1990 census). If the answer is 80 or more, divide the team into two and have each half-team work on one sector of the community/village. See the section below on what to do when the listing work is divided up.
If the census unit is a "line-up point" that does not correspond to any single village or community the number of households will often exceed 200 and frequently they are also quite dispersed. In this case it is not practical to attempt to list the whole census unit, so a decision is made in advance to split the census unit into smaller areas (perhaps groupings of clans). First, a local informant must communicate the boundaries of the census unit and for natural or administrative sub-units with the larger census unit (such as hamlets; or canyons/valleys). The sub-units should be big enough to allow for the selection of a set of households (about 30 or more), but should not be so large that excessive transport time will be needed each day just to find the household. Once the subunit is defined, its boundaries should be clearly described. Then one of the smaller units is randomly selected and the procedures outlined above are then followed to complete the listing. Note: only one of the sub-units are listed, sample chosen, and interviews undertaken.
The most important thing in the listing is to be sure that you list all the households and only the households belonging to the named village or census unit (or subset of the census unit if it is a line-up point). In rural areas, explain to village leaders at the beginning: "We have to write down all the households belonging to (Name) village." In case of doubt, always ask: "Does this household belong to (Name) village?" In the towns, the selected area is shown on a map. Check that the address where you are listing is within the same area shown.
Also explain: "We only write down the name of the head of household. When we have the list of all the households, we will select 12 by chance, for interview."
Procedure for Listing
The listing team walks around in every part of the village, accompanied by a guide who is a member of the village. If possible, find a person who conducted the 1990 Census in this community or someone with similar knowledge of the community and ask them to be your guide. Make sure you go to all parts of the village, including outlying hamlets. In hamlets, on in any place far from the centre, always check: "Do these people belong to (Name) village?"
In every part of the village, ask the guide about every house: "Who lives in this house? What is the name of the household head?" Note that you do not have to visit every household. At best, you just need to see each house but you do not need to go inside it or talk to anyone who lives there. Even the rule of seeing each house may be relaxed if there are far away household for which good information can be provided by the guide.
Enter the names of household heads in the lines of the listing form. One line is used for each household. As the lines are numbered, the procedure gives a number to each household. When you come to the last house, check with the guide: "Are you sure we have seen all the houses in the village?"
NOTE: It does not matter in what order you list the households as long as they are all listed.
After the listing is complete, check that all lines are numbered consecutively with no gaps, from start to finish. The number on the last line should be exactly the number of households listed.
Note: If the list is long (say more than 30 households) interviewer may encounter difficulties when looking for their selected household. One useful way to avoid this is to show the approximately the place in the list here certain landmarks come. This can be done by writing in the margin, CHURCH or STORE or whatever. You can also indicate where the lister started in a hamlet, for example.
The sampling work is done by the supervisor. The first steps are done at the foot of the first page of the listing form. The steps to be taken are as follows:
1. Fill in the numbers asked for at the foot of the last listing page, as follows:
- M: enter the total number of households listed (same as last household number shown).
- Interval L: calculate (M / 15) to the nearest whole number.
- R: This is a random number with 3-digit decimals between 0.000 and 0.999.
- MR: multiply M by R and round to the nearest whole number. (If decimal 0.5, round up).
2. MR gives the 1st selection. (Exception: If MR=0, L gives the first selection.) Enter S against this line in the selection column of the list.
3. Count down the list, beginning after the 1st selection, a distance of L lines to get the 2nd selection, then another L to get the 3rd, etc. When you come to the bottom of the list, jump back to the top as if the list were circular. Stop after the 15th selection. Mark the 13th, 14th, and 15th selections "RES" (for reserve). Mark the 1st - 12th selection "S" (for selection).
PNGHS96 was not a self-weighting survey. The sampling frame (the 1990 Census) was sufficiently old to mean that the selection of Primary Sampling Units (CUs) according to the probability proportional to estimated size rule would not give equal probabilities for the selection of each household if that selection had been based on 1996 household counts.
Therefore, survey teams listed all households in the selected CU and this, along with other information (described in para. 24-29 of “Measuring the Standard of Living”) was used to form sampling weights, so that statistics estimated from the survey are representative of 1996. Another reason for the use of sampling weights is that non-respondent households were replaced only at the first interview stage. If a household did not respond to the consumption recall interview (e.g., they had left the village for an extended period) a replacement household was not used. This differs from the practice used in some surveys. The reason for not seeking replacement households for non-respondents at the consumption recall stage was that the rate of progress of survey teams would be impeded if they had to stay behind in a village to re-do the survey (with a 14 day bounded recall period) for one replacement household. The other alternative would be to just use an unbounded recall and just ask the replacement household about their activities in the last two weeks but this would then defeat the efforts made to accurately measure consumption (particularly the recording of own-food production). Nonreplacement means that there are more first visit interviews than second visit interviews, and hence there are also differing weights. A final reason for the use of weights is to deal with the households in the longitudinal subsample.
For most purposes, one of the two observations on these households should be given zero weight when calculating summary statistics (these weights are referred to as the N1200 rule, with this name based on the approximate sample size under this rule). The alternative would be to give weights of 0.5 to each of the two observations (these weights are referred to as the N1400 sample, with this name based on the approximate sample size under this rule).
There are just two files in this folder. The file cu_wghts.wk3 calculates the sampling weights for each Census Unit. These weights are discussed in para. 24-29 of “Measuring the Standard of Living”.
The file surv_des.wk3 reports the stratum number, the cluster number, and the household weight for each household in the N1200 sample (i.e., putting a zero weight on one of the two observations on the households in the longitudinal sub-sample). The details on the stratification are in para. 8-11 of “Measuring the Standard of Living”. The data in this file are essential to the correct calculation of the sampling errors for any statistics of the survey data.
Note that if population weights are required, they can be calculated by multiplying the household weight by the number of people in the household.
Dates of Data Collection (YYYY/MM/DD)
Mode of data collection
Type of Research Instrument
The 1996 Papua New Guinea Household Survey questionnaire consists of three basic parts:
Household questionnaire first visit: asks a series of questions about the household, discovering who lives there, what they do, their characteristics, where they live, and a little about what kinds of things they consume. This questionnaire consists of the following sections.
- Section 1. Household Roster
- Section 2. Education
- Section 3. Income Sources
- Section 4. Health
- Section 5. Foods in the Diet
- Section 6. Housing Conditions
- Section 7. Agricultural Assets, Inputs and Services
- Section 8. Anthropometrics
- Section 9. Household Stocks
Consumption recall (second visit questionnaire): is focused primarily on assessing the household's expenditure, gift giving and recieving, production, and level of wealth. The information in the first and second visits will provide information that can determine the household's level of consumption, nutrition, degree of food security, and ways in which it organizes its income earning activities. This questionnaire consists of the following sections.
- Section 1. Purchases of Food
- Section 2. Other Frequent Purchases
- Section 3. Own-production of Food
- Section 4. Gifts Received: Food and Frequent Purchases (START)
- Section 5. Annual Expenses and Gifts
- Section 6. Inventory of Durable Goods
- Section 7. Inward Transfers of Money
- Section 8. Outward Transfers of Money
- Section 9. Prices
- Section 10. Repeat of Anthropometric Measurements
- Section 11. Quality of Life
Community Questionnaire: which is completed by the interview team in consultation with community leaders. This questionnaire also includes market price surveys that are carried out by the team when they are working in the community. Associated with this is a listing of all households in the community, which has to be done prior to the selection of the 12 households. This questionnaire consists of the following sections.
- Section A. Listing of Community Assets
- Section B. Education
- Section C. Health
- Section D. Town or Government Station
- Section E: Transport and Communications
- Section F. Prices
- Section G. Changes in Economic Activity, Infrastructure, and Services
National Statistical Office
National Statistical Office
In receiving these data it is recognized that the data are supplied for use within your organization, and you agree to the following stipulations as conditions for the use of the data:
1. The data are supplied solely for the use described in this form and will not be made available to other organizations or individuals. Other organizations or individuals may request the data directly.
2. Three copies of all publications, conference papers, or other research reports based entirely or in part upon the requested data will be supplied to:
The World Bank Development Economics Research Group
LSMS Database Administrator
MSN MC3-306 1818 H Street, NW Washington, DC 20433, USA
tel: (202) 473-9041
fax: (202) 522-1153
e-mail: [email protected]
3. The researcher will refer to the 1996 Papua New Guinea Household Survey as the source of the information in all publications, conference papers, and manuscripts. At the same time, the World Bank is not responsable for the estimations reported by the analyst(s).
4. Users who download the data may not pass the data to third parties.
5. The database cannot be used for commercial ends, nor can it be sold.
Use of the dataset must be acknowledged using a citation which would include:
- the Identification of the Primary Investigator
- the title of the survey (including country, acronym and year of implementation)
- the survey reference number
- the source and date of download
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.