The 2013-2014 Household Income and Expenditure Survey (HIES) of Palau is the thrid of its kind to be conducted by the country. The previous HIES surveys took place in 2004 (incomplete results therefore no publication) and 2006.
The purpose of the Household Income and Expenditure Survey (HIES) survey is to obtain information on the income, consumption pattern, incidence of poverty, and saving propensities for different groups of people in Palau. This information will be used to guide policy makers in framing socio-economic developmental policies and in initiating financial measures for improving economic conditions of the people.
Some more specific outputs from the survey are listed below:
a) To obtain expenditure weights and other useful data for the revision of the consumer price index;
b) To supplement the data available for use in compiling official estimates of household accounts in the systems of national accounts;
c) To supply basic data needed for policy making in connection with social and economic planning, including producing as many of Palau's National Minimum Development Indicators (NMDI's) as possible;
d) To provide data for assessing the impact on household living conditions of existing or proposed economic and social measures, particularly changes in the structure of household expenditures and in household consumption;
e) To gather information on poverty lines and incidence of poverty throughout Palau.
Kind of Data
Sample survey data [ssd]
Unit of Analysis
Version 01: Cleaned, labelled and de-identified version of the Master file.
National Coverage, excluding Sonsorol and Hatohobei. Urban and Rural.
All private households and group quarters (people living in Work dormitories, as it is an important aspect of the subject matter focused on in this survey, and not addressed elsewhere).
Producers and sponsors
Office of Planning and Statistics
Bureau of Budget and Planning, Ministry of Finance
Statistics for Develepment Division
Technical assistance (data collection and data processing)
Government of Palau
Asian Development Bank
United States Department of Interior
The sampling frame used was the 2012 Palau census, which provided population figures for everyone living in both private households and group quarters (e.g. worker barracks, school dormitories, prison). The sampling selection was done separately in private dwellings and group quarters.
It is an accepted practice for the Household Income and Expenditure Survey (HIES) to cover all living quarters regarded as private dwellings, and the Palau 2013/14 HIES will follow this recommendation.
For group quarters it is also recommended to exclude the prison, as it is not considered appropriate to include such institutions in a survey such as HIES.
A decision as to whether the remaining group quarters should be included is based on the following criteria:
1) Ease in accessing and covering them in a survey such as HIES
2) Relevance to the subject matter of the survey
3) Whether their impact on the subject matter is mostly covered already
Under these criteria, the following recommendations are made:
-School/college dormitories: Will exclude from HIES as these individuals will be covered in the households from which they came (if selected)
-Work dormitories: Aim to include in the HIES as they are an important aspect of the subject matter focused on in this survey, and not addressed elsewhere
-Live aboard: Will exclude due to the movement of such vehicles, and the minimal impact they may have on such a survey
-Convents/religious quarters: Will exclude based on their expected minimum impact on the survey subject matter
NB: Given students in dorms are expected to have a high portion of their income and expenses covered in their original household of origin, and there were no religious group quarters identified during the census, only persons in the prison and living aboard are expected to be excluded from the survey. These people account for 81 out of 2,322 group quarters residents (only 3.6%).
Although the response rates were down in the 2006 HIES, with a smaller more experienced team working over 12 months, it is expected there will be improvements in this area. However, the expected sample loss of 10 per cent was probably too ambitious, and given the actual rate ended up at 287/1,063 = 27 per cent, it is more realistic to assume a sample loss of around 15 per cent with improvements for the 2013/14 HIES.
Based on the RSEs presented in 2.3.2, it also appears that the 20 per cent desirable sample produced sound results for the survey, and with higher response rates anticipated, these results from a sample error perspective should improve. It is therefore proposed for the 2013/14 Palau HIES that a sample size of 20 per cent be adopted, which also allows for sample loss of 15 per cent.
In the 2006 Palau HIES, effort was made to design a sample which could produce results for the six domains (stratum). Whilst reasonable results were generated for each of these domains, it was felt that post survey, there was no great use of these results at that level.
For the 2013 HIES it is proposed to focus on generating reliable results at the national level, with focus also being place on producing results for the urban/rural split. In the case of Palau, the urban population is considered to consist of the states of Koror and Airai.
The last phase to finalizing the sample numbers was to adjust the desirable sample numbers, so that they could be easily applied by the HIES team in a practical manner over the course of the 12 month fieldwork.
This was achieved by modifying the sample counts (not too much) to enable sample sizes each round would be of a similar size, and workloads for each enumerator were the same size each round.
The desirable workload for an enumerator covering the PD population was 10 households, whereas this figure was increased to 14 persons for GQs as it was envisaged the amount of time required to cover a person in a GQ would be significantly less.
With this in mind, we wanted to ideally have the PD sample to be divisible by 160 so this would enable an even number of households each round, whilst maintaining a workload of 10 households for interviewers covering these areas.
For the GQ sample, given the desirable number of GQs was already 225, and 16x14=224, then a simple reduction of 1 in the GQ sample would result in a nice even workload of 14 persons per round for 1 interviewer. This logic was also applied to the split between urban and rural resulting in 14 workloads in urban and 2 workloads in rural.
Some 1,145 households were selected (in private dwellings and workers quarters) to participate in the survey, and the response rate was 75.8% (i.e. 869 households responded). This response rate allows for statistically significant analysis at the national, urban and rural level.
Response rates for private households by State:
-Koror: 355 households responded out of 480 selected => 73.9%;
-Airai: 119 households responded out of 160 selected => 74.4%;
-URBAN: 474 households responded out of 640 selected => 74.1%;
-Kayangel: 0 households responded out of 10 selected => 0%;
-Ngarchelong: 27 households responded out of 30 selected => 90%;
-Ngaraard: 22 households responded out of 30 selected => 73.3%;
-Ngiwal: 18 households responded out of 20 selected => 90%;
-Melekeok: 25 households responded out of 30 selected => 83.3%;
-Ngchesar: 29 households responded out of 30 selected => 96.7%;
-Aimeliik: 30 households responded out of 30 selected => 100%;
-Ngatpang: 19 households responded out of 20 selected => 95%;
-Ngardmau: 20 households responded out of 20 selected => 100%;
-Ngaremlengui: 29 households responded out of 30 selected => 96.7%;
-Angaur: 12 households responded out of 20 selected => 60%;
-Peleliu: 35 households responded out of 50 selected => 70%;
-RURAL: 266 households responded out of 320 selected => 83.1%;
-TOTAL: 740 households responded out of 960 selected => 77.1%.
Response rates for households in worker barracks:
-URBAN: 81 households responded out of 135 selected => 60%;
-RURAL: 48 households responded out of 48 selected => 96%;
-TOTAL: 129 households responded out of 129 selected => 69.7%.
Total response rates for all households:
-URBAN: 553 households responded out of 775 selected => 71.3%;
-RURAL: 316 households responded out of 370 selected => 85.4%;
-TOTAL: 869 households responded out of 1145 selected => 75.9%.
Dates of Data Collection
Data Collection Mode
Palau Office of Planning and Statistics
Bureau of Budget and Planning, Ministry of Finance
Developped in English, a questionnaire consisting of four Modules and a Weekly Diary covering 2 weeks was used for the Republic of Palau Household Income and Expenditure Survey (HIES) 2013. Each Module covers distinct but connected portion of the Household.
The Modules are as follows:
-Module 1 - Demographic Information:
· Demographic Profile
· Labor Force Status
· Health Status
· Communication Status
-Module 2 - Household Expenditure:
· Housing Characteristics
· Housing Tenure Expenditure
· Utilities & Communication Details
· Utilities & Communication Expenditure
· Land & Home Details
· Land & Home Expenditure
· Household Goods & Assets Details
· Household Goods & Assets Expenditures
· Vehicles & Accessories Details
· Vehicles & Accessories Expenditures
· Private Travel Details
· Private Travel Expenditures
· Household Services Expenditure
· Contributions to Special Occasions
· Provisions of Financial Support
· Household Assets Insurance & Taxes
· Personal Insurance
-Module 3 - Individual Expenditures:
· Education grants and scholarships
· Education Identifications
· Education Expenditures
· Health Identifications
· Health Expenditures
· Clothing Identification
· Clothing Expenditure
· Communication Identification
· Communication Expenditures
· Luxury Items Identification
· Luxury Items Expenditures
-Module 4 - Income:
· Wages & Salary: In country (current)
· Wages & Salary: Overseas (last 12 months)
· Wages & Salary: In country (last 12 months)
· Income from Non Subsistence Business
· Description of Agriculture & Forestry Activities
· Income from Agriculture & Forestry Activities
· Description of Handicraft & Home Processed Food Activities
· Income from Handicraft & Home Processed Food Activities
· Description of Livestock & Aquaculture Activities
· Income from Livestock & Aquaculture Activities
· Description of Fishing & Hunting Activities
· Income from Fishing & Hunting Activities
· Property Income, Transfer Income & Other Receipts
· Remittances & Other Cash Gifts
-Weekly Diary - Covering 14 Days (2 weeks):
· Daily expenditure of food and non-food items
· Payments of service made
· Gambling winning and losses
· Items received for free
· Home produced food and non-food items.
All questionnaires are provided as external resources in this documentation.
Program: CSPro 5.1x
Data editing took place at a number of stages throughout the processing, including:
a) Office editing and coding
b) During data entry; Error report correction; Secondary editing by Quality Control Officer (QCO)
c) Structure checking and completeness
Detailed documentation of the editing of data can be found in the "Data processing guidelines" document provided as an external resource.
Data extracted from CSPro was used in the following Programs:
- Microsoft (MS) Excel
Miscrosoft (MS) Excel
- Used to monitor Data Collection
- Decision Making
No formal measure of sample errors has been calculated for the survey results. Non-sampling errors cannot be readily measured, and include issues such as:
- both respondents and interviewers not completely understanding what was required from the survey;
- the questionnaires being in English, which is a second language for both interviewers and respondents;
- the exclusion of remote areas and institutions from the sampling frame.
The Office of Planning and Statistics, when conducting a major survey activity such as the HIES, do so under the Statistics Act, 2011. This is a legislation which has been approved by the senate, specifying the conditions in which the data collection, processing and dissemination should be performed.
Strict guidelines within this Act have been developed to ensure:
a) Officers involved in the survey project adhere to the confidentiality criteria, and
b) Maximum cooperation from the public will be achieved
a) Confidentiality criteria of officers involved in the collection
Section 301 of the Act states that:
"… any person employed in the performance of any duty under or for the purposes of this Act who, without lawful authority, discloses to any person, other than in the course of that employment, any information that comes into their possession in the course of that employment, shall be guilty of a criminal offence and shall, upon conviction, be liable to a fine not exceeding $2,000 or a term of imprisonment not exceeding two (2) years, or both."
b) Cooperation requirements of respondents
Section 302 of the Act (offenses relating to the collection) states that:
"… any person who does any of the following shall be guilty of a criminal offense and shall, upon conviction, be liable for a fine not exceeding $1,000 or to a term of imprisonment not exceeding one year or both:
(a) Knowingly or recklessly makes, in any return, form or other document completed or supplied under this Act, or in any answer to any question or inquiry made under the authority of this Act, any statement which is untrue in any material particular; or
(b) Without lawful authority, destroys, defaces or mutilates any return, form or other document containing particulars collected under this Act"
Section 303 of the Act (offenses relating to obstruction), states that:
"… a person who hinders or obstructs an authorized officer in the performance of their functions under this Act, shall be guilty of a criminal offense and shall, upon conviction be liable for a fine not exceeding $1,000 or to a term of imprisonment not exceeding one year, or both" 4
Breaches of this law can have significant impacts on the successful conduct of not only this survey but future surveys undertaken by the Government of Palau.
Breaches of the law will also have an impact on the individual/s concerned in the sense that their pay can be docked and any other employment opportunities of this nature in the future will be lost.
"Office of Planning and Statistics of Palau, Household Income and Expenditure Survey 2013-2014 (HIES 2013), Version 01 of the licensed dataset (January 2005),provided by the Microdata Library. https://microdata.pacificdata.org/index.php/home"
Disclaimer and copyrights
The data contained herein is provided "as is" without any expressed or implied warranty or responsibility. The Palau Office of Planning and Statistics accepts no responsibility for the use of such data nor for any interpretations or inferences based upon such uses.
Version 01 (February 2014): Initial Documentation; No data.
Version 02 (March 2020): Review of the existing documentation with data included. Done in Noumea, New Caledonia by the Statistics for Development Division (SDD).