Household Income and Expenditure Survey 2019
Marshall Islands, 2019 - 2020
Economic Policy Planning and Statistics Office
Identification
IDNO
SPC_MHL_2019_HIES_v01_M_v01_A_PUF
Title
Household Income and Expenditure Survey 2019
Country
| Name | Country code |
|---|---|
| Marshall Islands | MHL |
Abstract
The primary purpose of this survey was to gather more accurate and detailed information on income and expenditure levels and flows in the Marshall Islands (MHL) and to update and revise the MHL Consumer Price Index (a separate series of publications document the CPI revision efforts).
Kind of Data
Sample survey data [ssd]
Version
Version number
Version 01: Cleaned, labelled and anonymized version of the Master file.
Version Date
2021-03-04
Scope
Topic Classification
| Topic |
|---|
| pacific-skills, education, training pacific-skills, education, training |
| pacific-skills, industry, training |
| pacific-skills, occupation |
| pacific-skills, gender |
| pacific-skills, disability |
Keywords
| Keyword |
|---|
| Expenditure |
| Income |
| Consumption |
| Education |
| Health |
| Economic activities |
| Food away from home |
| Own-production |
| Deprivation |
| Partaker |
| Migrant worker |
| Disability |
| COICOP |
| PACCOI |
| PNDB |
Coverage
Geographic Coverage
National coverage; urban and rural.
Unit of Analysis
Household and Individual.
Universe
All usual household residents in private dwellings.
Producers and sponsors
Authoring entity/Primary investigators
| Agency Name | Affiliation |
|---|---|
| Economic Policy Planning and Statistics Office | Government of Marshall Islands |
Producers
| Name | Affiliation | Role |
|---|---|---|
| Statistics for Development Division | Pacific Community (SPC) | Technical assistance |
| International Labour Organization | United Nations | Technical assistance |
| Food and Agriculture Organization | United Nations | Technical assistance |
Funding Agency/Sponsor
| Name | Role |
|---|---|
| Government of Marshall Islands | Funding |
Sampling
Sampling Procedure
SAMPLE SIZE:
In determining an appropriate sample size for a survey of this nature, numerous factors come into the equation. These include:
a) The degree of accuracy required for key estimates;
b) The population size of the country;
c) The manner in which the sample is selected;
d) Cost or staffing constraints which may exist;
e) Whether or not estimates are required for sub-populations;
f) The level of variability in the data being collected.
Each of these factors have different magnitudes of importance, but the major priority should always be on selecting a sample big enough to produce results of suitable accuracy. Many of these issues are generally known as well - for instance:
· A user group may pre-specify what level of accuracy they may wish to achieve for the survey
· The population of a country can normally be estimated to a reasonable level of accuracy
· The sample selection technique adopted is known
· Cost and staff constraints are generally known, and
· A user group can once again provide information on whether estimates for sub-populations are required.
The Marshall Islands 2020 Household Income and Expenditure Survey (HIES) aims to release outputs at the Urban Rural level and National level.
The sampling strategy has been developed around a stratification of urban and rural domains of the Marshall Islands. This stratification aims to improve the robustness of the indicators at urban and rural level. The urban sector has been stratified in 2 different atolls (Majuro and Kwajalein) and the rural region has been stratified in group of atolls that show similarities as follow:
- Rural 1: peri urban atolls; located close to Majuro and Kwajalein (Arno, Mili)
- Rural 2: most important rural atolls with facilities (boarding schools; health center…) (Jaluit; Wotje)
- Rural 3: atolls where population benefit from US Government for nuclear testing (Enewatak, Kili, Utirik)
- Rural 4: other atolls
The targeted sample size has been determined around 880 households based on the results of the previous 2011 population census that provided the mean and standard deviation of the total cash household income at the strata level:
The cluster size has been determined at 12 households.
-Urban 1 & 2: respectively 400 and 150 households spread across 33 and 13 EAs lead to 7.9% RSE in Urban domain
-Rural: respectively 2, 3, 10 and 13 EAs in rural1, 2, 3 and 4 (24, 36, 120 and 150 households) lead to 7.3% RSE in Rural domain
-At the National level this total sample size of 880 households spead across those 6 stratas as mentioned lead to a RSE of 7.1%
SAMPLE SELECTION:
The 2020 Marshall Islands HIES is based on a stratified cluster sampling strategy. The households are selected in 2 steps:
- Step1: the random selection of EA based on the sampling strategy parameters (Primary sampling unit)
- Step2: the random selection of 12 households (+6 replacements) within each selected EA
The final probability of selection combines both probabilities of EA getting selected within the strata and households getting selected with the EA.
In determining an appropriate sample size for a survey of this nature, numerous factors come into the equation. These include:
a) The degree of accuracy required for key estimates;
b) The population size of the country;
c) The manner in which the sample is selected;
d) Cost or staffing constraints which may exist;
e) Whether or not estimates are required for sub-populations;
f) The level of variability in the data being collected.
Each of these factors have different magnitudes of importance, but the major priority should always be on selecting a sample big enough to produce results of suitable accuracy. Many of these issues are generally known as well - for instance:
· A user group may pre-specify what level of accuracy they may wish to achieve for the survey
· The population of a country can normally be estimated to a reasonable level of accuracy
· The sample selection technique adopted is known
· Cost and staff constraints are generally known, and
· A user group can once again provide information on whether estimates for sub-populations are required.
The Marshall Islands 2020 Household Income and Expenditure Survey (HIES) aims to release outputs at the Urban Rural level and National level.
The sampling strategy has been developed around a stratification of urban and rural domains of the Marshall Islands. This stratification aims to improve the robustness of the indicators at urban and rural level. The urban sector has been stratified in 2 different atolls (Majuro and Kwajalein) and the rural region has been stratified in group of atolls that show similarities as follow:
- Rural 1: peri urban atolls; located close to Majuro and Kwajalein (Arno, Mili)
- Rural 2: most important rural atolls with facilities (boarding schools; health center…) (Jaluit; Wotje)
- Rural 3: atolls where population benefit from US Government for nuclear testing (Enewatak, Kili, Utirik)
- Rural 4: other atolls
The targeted sample size has been determined around 880 households based on the results of the previous 2011 population census that provided the mean and standard deviation of the total cash household income at the strata level:
The cluster size has been determined at 12 households.
-Urban 1 & 2: respectively 400 and 150 households spread across 33 and 13 EAs lead to 7.9% RSE in Urban domain
-Rural: respectively 2, 3, 10 and 13 EAs in rural1, 2, 3 and 4 (24, 36, 120 and 150 households) lead to 7.3% RSE in Rural domain
-At the National level this total sample size of 880 households spead across those 6 stratas as mentioned lead to a RSE of 7.1%
SAMPLE SELECTION:
The 2020 Marshall Islands HIES is based on a stratified cluster sampling strategy. The households are selected in 2 steps:
- Step1: the random selection of EA based on the sampling strategy parameters (Primary sampling unit)
- Step2: the random selection of 12 households (+6 replacements) within each selected EA
The final probability of selection combines both probabilities of EA getting selected within the strata and households getting selected with the EA.
Response Rate
Below are the response rates by urban-rural region for Set A (households selected from the sample):
-Urban: 85.3%
-Rural: 89%
-NATIONAL: 86.7%
Below are the response rates by urban-rural region for Set B (households selected from the sample + replacements):
-Urban: 99.8%
-Rural: 95.8%
-NATIONAL: 98.3%
-Urban: 85.3%
-Rural: 89%
-NATIONAL: 86.7%
Below are the response rates by urban-rural region for Set B (households selected from the sample + replacements):
-Urban: 99.8%
-Rural: 95.8%
-NATIONAL: 98.3%
Weighting
Sample weights were calculated for each stratum and adjusted for non-response. 3 sets of sampling weights have been generated according to the following steps:
- 1. Computation of the first set of weights based on the inverse of the probability of selection used in the random selection sampling process
- 2. First adjustment using the population census figures (2011)
- 3. Second adjustment based on the age and sex structure of the population (2011)
The final "weight" variable to be used in the Marshall Islands Household Income and Expenditure Survey dataset is called "fweight" and can be found in each dataset.
- 1. Computation of the first set of weights based on the inverse of the probability of selection used in the random selection sampling process
- 2. First adjustment using the population census figures (2011)
- 3. Second adjustment based on the age and sex structure of the population (2011)
The final "weight" variable to be used in the Marshall Islands Household Income and Expenditure Survey dataset is called "fweight" and can be found in each dataset.
Data Collection
Dates of Data Collection (YYYY/MM/DD)
| Start date | End date | Cycle |
|---|---|---|
| 2019-07-15 | 2020-05-01 | Data collection |
Mode of data collection
Computer Assisted Personal Interview [capi]
Type of Research Instrument
The questionnaire was produced in English and Marshallese languages. The English questionnaire can be found in the External Resources.
Below is the list of all questionnaire modules:
-1. Household ID
-2. Household member roster
-3. Person details: Profile; Education; Health; Physical; Communication; Alcohol & tobacco; Other individual expenses; Labour force; Fisheries hunting; Handicraft & home processed food)
-4. Food away from home: Breakfast; Lunch; Dinner; Snacks; Hot drinks; Bottked water; Non-alcoholic drinks
-5. Own production
-6. Deprivation (persons)
-7. Food recall
-7.1. Partaker
-8. Non-food recall
-9. Household details: Dwelling characteristics; Household assets; Other household items & services; Ceremonies; Remittances; Food insecurity; Copra production; Livestock & aquaculture; Agriculture; Legal services
-10. Deprivation and financial inclusion (household)
-11. Migrant worker
-12. Geographic information + photo.
Below is the list of all questionnaire modules:
-1. Household ID
-2. Household member roster
-3. Person details: Profile; Education; Health; Physical; Communication; Alcohol & tobacco; Other individual expenses; Labour force; Fisheries hunting; Handicraft & home processed food)
-4. Food away from home: Breakfast; Lunch; Dinner; Snacks; Hot drinks; Bottked water; Non-alcoholic drinks
-5. Own production
-6. Deprivation (persons)
-7. Food recall
-7.1. Partaker
-8. Non-food recall
-9. Household details: Dwelling characteristics; Household assets; Other household items & services; Ceremonies; Remittances; Food insecurity; Copra production; Livestock & aquaculture; Agriculture; Legal services
-10. Deprivation and financial inclusion (household)
-11. Migrant worker
-12. Geographic information + photo.
Data Collectors
| Name | Abbreviation | Affiliation |
|---|---|---|
| Economic Policy Planning and Statistics Office | EPPSO | Government of Marshall Islands |
Data Processing
Cleaning Operations
Data editing was done using the software Stata.
Other Processing
Data entry was done using Survey Solutions which is a World Bank software.
Data Appraisal
Estimates of Sampling Error
-RELATIVE SAMPLING ERRORS (RSEs):
Below are the RSEs for total expenditure throughout all COICOP divisions, by urban and rural areas:
.Urban: 3.6%; Mean expenditure: 5,119; Lower 95% confidence interval: 4,747; Upper 95% confidence interval: 5,490.
.Rural: 6.3%; Mean expenditure: 3,280; Lower 95% confidence interval: 2,870; Upper 95% confidence interval: 3,691.
.NATIONAL: 3.3%; Mean expenditure: 4,659; Lower 95% confidence interval: 4,348; Upper 95% confidence interval: 4,969.
Below are the RSEs for total income throughout all PACCOI divisions, by urban and rural areas:
.Urban: 7.6%; Mean income: 3,612; Lower 95% confidence interval: 3,061; Upper 95% confidence interval: 4,162.
.Rural: 9.2%; Mean income: 3,585; Lower 95% confidence interval: 2,928; Upper 95% confidence interval: 2,928.
.NATIONAL: 6.2%; Mean income: 3,605; Lower 95% confidence interval: 3,161; Upper 95% confidence interval: 3,161.
The detailed relative sampling errors (RSEs) for the 2019 Marshall Islands Household Income and Expenditure Survey (HIES) will be included in the Appendix section of the final analytical report (when released).
Below are the RSEs for total expenditure throughout all COICOP divisions, by urban and rural areas:
.Urban: 3.6%; Mean expenditure: 5,119; Lower 95% confidence interval: 4,747; Upper 95% confidence interval: 5,490.
.Rural: 6.3%; Mean expenditure: 3,280; Lower 95% confidence interval: 2,870; Upper 95% confidence interval: 3,691.
.NATIONAL: 3.3%; Mean expenditure: 4,659; Lower 95% confidence interval: 4,348; Upper 95% confidence interval: 4,969.
Below are the RSEs for total income throughout all PACCOI divisions, by urban and rural areas:
.Urban: 7.6%; Mean income: 3,612; Lower 95% confidence interval: 3,061; Upper 95% confidence interval: 4,162.
.Rural: 9.2%; Mean income: 3,585; Lower 95% confidence interval: 2,928; Upper 95% confidence interval: 2,928.
.NATIONAL: 6.2%; Mean income: 3,605; Lower 95% confidence interval: 3,161; Upper 95% confidence interval: 3,161.
The detailed relative sampling errors (RSEs) for the 2019 Marshall Islands Household Income and Expenditure Survey (HIES) will be included in the Appendix section of the final analytical report (when released).
Data access
Contact
| Name | Affiliation | URI | |
|---|---|---|---|
| Economic Policy Planning and Statistics Office | Government of Marshall Islands | [email protected] | https://www.rmieppso.org/contact |
Confidentiality Declaration
The Household Income and Expenditure Survey (HIES) data is protected under the National Statistics Act and cannot be disclosed to any individual without authorisation from the Government Statistician.
Conditions
Licensed datasets.
Users and Depositors should note that the data and documentation in the Pacific Data Hub Microdata Library do not belong to the archive but to the individual depositors (data owners of the data) to the archive.
Note: Prior to distributing certain licensed data and documentation, the Pacific Community (SPC) has to contact the data owner in order to obtain permission and that may cause some delays with microdata release.
Users and Depositors should note that the data and documentation in the Pacific Data Hub Microdata Library do not belong to the archive but to the individual depositors (data owners of the data) to the archive.
Note: Prior to distributing certain licensed data and documentation, the Pacific Community (SPC) has to contact the data owner in order to obtain permission and that may cause some delays with microdata release.
Citation requirement
"Economic Policy Planning and Statistics Office of Marshall Islands, Household Income and Expenditure Survey 2019 (HIES 2019), Version 01 of the licensed dataset (March 2021), provided by the Pacific Data Hub - Microdata Library. https://microdata.pacificdata.org/index.php/home"
Disclaimer and copyrights
Disclaimer
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.
Contacts
Contact
| Name | Affiliation | URI | |
|---|---|---|---|
| Economic Policy Planning and Statistics Office | Government of Marshall Islands | [email protected] | https://www.rmieppso.org/contact |
Metadata production
Document ID
DDI_SPC_MHL_2019_HIES_v01_M_v01_A_PUF
Producers
| Name | Abbreviation | Affiliation | Role |
|---|---|---|---|
| Statistics for Development Division | SDD | Pacific Community (SPC) | Documentation of the study |
Date of Production
2020-12-04
Document version
Version 01 (December 2020): This is the first attempt at documenting the 2019-2020 Household Income and Expenditure Survey (HIES) of the Republic of Marshall Islands. Done in Noumea, New Caledonia by the Statistics for Development Division (SDD).
Version 02 (March 2021): This is the second version of the documentation that consists in providing and documenting the anonymized datasets. Done in Noumea, New Caledonia by the Statistics for Development Division (SDD).
Version 02 (March 2021): This is the second version of the documentation that consists in providing and documenting the anonymized datasets. Done in Noumea, New Caledonia by the Statistics for Development Division (SDD).