Population and Housing Census 2006
Tokelau, 2006
Statistics New Zealand, Tokelau National Statistics Office
Identification
IDNO
SPC_TKL_2006_PHC_v02_M
Title
Population and Housing Census 2006
Translated Title
Tuhiga igoa a Tokelau i te 2006
Country
| Name | Country code |
|---|---|
| Tokelau | TKL |
Abstract
The 2006 Census of Tokelau was conducted on the 19th of October 2006, by both local representatives and Statistics New Zealand staff. Significant planning went into both the collection and output phases of the 2006 Census
– with consultation on various aspects of the census (for example, questionnaire content consultation) carried out in Tokelau, Samoa and New Zealand, where appropriate. The 2006 Census questionnaire was based on a
standard form developed by the Secretariat of the Pacific Community (SPC), with some changes as appropriate to the Tokelau situation.
Tokelau has a unique population composition. A significant proportion of the Tokelauan population are away from the islands at any one time, for various reasons (e.g. healthcare, education). Considerable time and effort has been
put into developing effective population measures for the 2006 Census of Tokelau, with a focus on ensuring all usual residents were counted – in particular those who were not present in Tokelau on census night. Core demographic information was completed by the head of the household, on behalf of people who usually live in Tokelau, but were away on census night.
– with consultation on various aspects of the census (for example, questionnaire content consultation) carried out in Tokelau, Samoa and New Zealand, where appropriate. The 2006 Census questionnaire was based on a
standard form developed by the Secretariat of the Pacific Community (SPC), with some changes as appropriate to the Tokelau situation.
Tokelau has a unique population composition. A significant proportion of the Tokelauan population are away from the islands at any one time, for various reasons (e.g. healthcare, education). Considerable time and effort has been
put into developing effective population measures for the 2006 Census of Tokelau, with a focus on ensuring all usual residents were counted – in particular those who were not present in Tokelau on census night. Core demographic information was completed by the head of the household, on behalf of people who usually live in Tokelau, but were away on census night.
Kind of Data
Census/enumeration data [cen]
Version
Version number
Version 01: Cleaned, labelled and de-identified version of the Master file.
Version Date
2007-02-01
Version Notes
Dataset has been removed from the documentation.
Scope
Topic Classification
| Topic |
|---|
| PHC |
Keywords
| Keyword |
|---|
| Census |
| Dwellings |
| Population |
| Demography |
| Employment |
| Education |
| Life satisfaction |
| Economic activity |
Coverage
Geographic Coverage
National coverage: the census covers residents of Tokelau and also Tokelau public servants and their families who are employed in Apia, Samoa.
Unit of Analysis
Individuals and Households.
Universe
The Census covers residents of the non-selfgoverning New Zealand territory of Tokelau and includes Tokelau public servants and their families who are employed in Apia, Samoa. While visitors to Tokelau on Census night are also included, the ultimate aim of the Census is to provide an accurate assessment of the de jure population.
Producers and sponsors
Authoring entity/Primary investigators
| Agency Name | Affiliation |
|---|---|
| Statistics New Zealand | New Zealand Government |
| Tokelau National Statistics Office | Tokelau Government |
Producers
| Name | Affiliation | Role |
|---|---|---|
| Statistics New Zealand | New Zealand Government | Contractor |
Funding Agency/Sponsor
| Name | Abbreviation | Role |
|---|---|---|
| Tokelau National Statistics Office | TNSO | Operational support |
Other Identifications/Acknowledgments
| Name | Affiliation | Role |
|---|---|---|
| Mike Berry | Statistics New Zealand | StatsNZ Census team leader |
| Kele Lui | Tokelau National Statistics Office | National Statistician |
Data Collection
Dates of Data Collection (YYYY/MM/DD)
| Start date | End date | Cycle |
|---|---|---|
| 2006-10-19 | 2006-10-19 | Data collection |
Mode of data collection
Face-to-face [f2f]
Supervision
In Tokelau, SNZ recruited people from each atoll to work as district supervisors and interviewers - there were three district supervisors and 26 interviewers in the field.
Supervisors helped the census management team to conduct quality checks of every census form. This quality check helped to ensure that essential information had been gathered, and codes were assigned to openended questions. It also provided information used to produce the provisional count.
Supervisors helped the census management team to conduct quality checks of every census form. This quality check helped to ensure that essential information had been gathered, and codes were assigned to openended questions. It also provided information used to produce the provisional count.
Type of Research Instrument
The questionnaire of the 2006 Tokelau Census consisted of three different forms:
- Dwelling form: Dwelling characteristics; sources of water; means of cooking; rubbish disposal; hosuehold items; access to Sky TV, internet; numbers of pigs and chickens; sources of income.
- Individual form: Individual characteristics; realationship to household head; living where; ethnicity; religion; birth mother and father still alive; language skills: speaking and writing; address 5 years ago; education and qualifications; marital status; paid and unpaid employment; children given birth to.
- Absentee form: Individual characteristics; reason for / length of absence; income.
The 2006 Census questionnaire was based on a standard form developed by the Secretariat of the Pacific Community (SPC), with some changes appropriate to the Tokelau situation.
Some modifications were made in the 2006 Questionnaire, for instance:
- In 2001, the questionnaire only asked for items owned and not necessarily partial or shared ownership as it did in 2006.
A thorough review of the employment and work sections of the questionnaire was undertaken to ensure the unique work force in Tokelau was represented, while at the same time ensuring international comparability.
Questions on languages spoken, cigarette smoking and household income were added.
The English version of the questionnaire was reviewed using cognitive testing with four Wellington-based Tokelauan families. The near-final English version of the questionnaire was then tested in Tokelau in July 2006.
Consultation about the content of the census forms was also undertaken in Tokelau and Samoa, with Tokelau government representatives and decision-makers. This consultation was an opportunity to determine what information was required by various data users and how it could best be delivered. After the July visit to Tokelau, the questionnaire was finalised and translation into Tokelauan was carried out.
A shorter version of the full individual questionnaire was used for Tokelau Public Service (TPS) working in Samoa, which consisted of only basic demographic questions about each member of the household. No dwelling questions were asked in Samoa.
The census questionnaire was a paperbased, interviewer-administered questionnaire available in two languages (English and Tokelauan).
- Dwelling form: Dwelling characteristics; sources of water; means of cooking; rubbish disposal; hosuehold items; access to Sky TV, internet; numbers of pigs and chickens; sources of income.
- Individual form: Individual characteristics; realationship to household head; living where; ethnicity; religion; birth mother and father still alive; language skills: speaking and writing; address 5 years ago; education and qualifications; marital status; paid and unpaid employment; children given birth to.
- Absentee form: Individual characteristics; reason for / length of absence; income.
The 2006 Census questionnaire was based on a standard form developed by the Secretariat of the Pacific Community (SPC), with some changes appropriate to the Tokelau situation.
Some modifications were made in the 2006 Questionnaire, for instance:
- In 2001, the questionnaire only asked for items owned and not necessarily partial or shared ownership as it did in 2006.
A thorough review of the employment and work sections of the questionnaire was undertaken to ensure the unique work force in Tokelau was represented, while at the same time ensuring international comparability.
Questions on languages spoken, cigarette smoking and household income were added.
The English version of the questionnaire was reviewed using cognitive testing with four Wellington-based Tokelauan families. The near-final English version of the questionnaire was then tested in Tokelau in July 2006.
Consultation about the content of the census forms was also undertaken in Tokelau and Samoa, with Tokelau government representatives and decision-makers. This consultation was an opportunity to determine what information was required by various data users and how it could best be delivered. After the July visit to Tokelau, the questionnaire was finalised and translation into Tokelauan was carried out.
A shorter version of the full individual questionnaire was used for Tokelau Public Service (TPS) working in Samoa, which consisted of only basic demographic questions about each member of the household. No dwelling questions were asked in Samoa.
The census questionnaire was a paperbased, interviewer-administered questionnaire available in two languages (English and Tokelauan).
Data Collectors
| Name | Abbreviation | Affiliation |
|---|---|---|
| Statistics New Zealand | SNZ | New Zealand Government |
| Tokelau National Statistics Office | TNSO | Tokelau Government |
Data Processing
Cleaning Operations
The vast majority of editing was done on the dataset rather than on the raw data. Data evaluation identified cases that needed editing, the resolution was researched by the census manager, and any changes were recorded. This approach was taken to allow for a record to be kept of how many changes (consistency edits) have been undertaken, allowing the process to be defendable.
Census data processing was done using CSPro v 3.0 (Census and Survey Processing System). The Pacific Community (SPC) endorsed CSPro as the standard processing system for all population statistics in the Pacific. For the census of Tokelau, CSPro was used for key entry, editing, and verification of the census data.
Census data processing was done using CSPro v 3.0 (Census and Survey Processing System). The Pacific Community (SPC) endorsed CSPro as the standard processing system for all population statistics in the Pacific. For the census of Tokelau, CSPro was used for key entry, editing, and verification of the census data.
Other Processing
Census data processing was done using CSPro v 3.0 (Census and Survey Processing System). The Pacific Community (SPC) endorsed CSPro as the standard processing system for all population statistics in the Pacific. For the census of Tokelau, CSPro was used for key entry, editing, and verification of the census data.
The processing system key-entry screens were designed to closely resemble the census forms. The system allowed range edits and auto-tabbing to be added to aid the key-entry process.
Three Apia-based key entry operators and four members of the census management team were trained to use the key-entry system and subsequently spent four days doing the initial key entry of data. Three further days were spent verifying that the information entered into the system was accurately recorded.
The census data was then exported to Microsoft Excel for evaluation, and imported into the program SAS (Statistical Analysis System) for detailed data analysis.
The processing system key-entry screens were designed to closely resemble the census forms. The system allowed range edits and auto-tabbing to be added to aid the key-entry process.
Three Apia-based key entry operators and four members of the census management team were trained to use the key-entry system and subsequently spent four days doing the initial key entry of data. Three further days were spent verifying that the information entered into the system was accurately recorded.
The census data was then exported to Microsoft Excel for evaluation, and imported into the program SAS (Statistical Analysis System) for detailed data analysis.
Data Appraisal
Estimates of Sampling Error
Not applicable: Census
Data Appraisal
Given the small population size, no post-enumeration survey was done.
In some cases a respondent’s birth day or month was imputed. In these cases the date was randomly selected from one to thirty one and the birth month was randomly selected (from January to December). Any imputed dates were checked to ensure they were valid dates eg not 31 February. Overall the census management team felt that the editing, imputation and mandatory variables methods used were successful. They provided a good balance between quality and practicality for a small census.
In some cases a respondent’s birth day or month was imputed. In these cases the date was randomly selected from one to thirty one and the birth month was randomly selected (from January to December). Any imputed dates were checked to ensure they were valid dates eg not 31 February. Overall the census management team felt that the editing, imputation and mandatory variables methods used were successful. They provided a good balance between quality and practicality for a small census.
Data access
Contact
| Name | Affiliation | URI | |
|---|---|---|---|
| Tokelau National Statistics Office | Tokelau Government | [email protected] | https://www.tokelau.org.nz/Contact.html |
Confidentiality Declaration
Note that all output datasets have had individual names removed. However, a raw CSPro dataset remains with names attached. This has been retained for future system development and testing purposes.
It is recommended that SAS datasets and FINAL Excel datasets are used wherever possible as these contain no duplicates and contain clean edited data, with derivations. Other datasets may be subject to error.
To offer a degree of confidentiality protection and ensure that Tokelau census tables are of good quality, a confidentiality calculation was used to control the size of tables that were produced for the census outputs. The confidentiality rule, called the “mean cell size rule”, states that there must be on average more than two observations per cell before the information for a geographic area can be released.
For the Tokelau census there are three output geographies: national, atoll and village. The smallest geography is the village (as Fakaofo atoll has two villages).
The main purpose of these rules is to prevent tables from becoming sparse, ie with many cells containing zeros and ones. In the output tables, some categories within variables were aggregated to ensure tables complied with the confidentiality rule.
Conditions
Licensed datasets, accessible under conditions.
Given the smal population of Tokelau, de-identified unit records will be available only to licenced users.
Given the smal population of Tokelau, de-identified unit records will be available only to licenced users.
Citation requirement
"Statistics New Zealand and the Office of the Council for the Ongoing Gvernment of Tokelau, Population and Housing Census 2006 (PHC 2006), Version 01 of the licensed datasets (February 2007) provided by the Pacific Microdata Library. https://microdata.pacificdata.org/index.php/home"
Disclaimer and copyrights
Disclaimer
All care and diligence has been used in processing, analysing, and extracting data to provide this information. However, neither TNSO nor SNZ can give a warranty it is error-free and will not be liable for any loss or damage suffered by the use directly, or indirectly, of the information in this publication.
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.
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.
Copyright
Crown copyright (c) New Zealand and Tokelau 2007
Contacts
Contact
| Name | Affiliation | URI | |
|---|---|---|---|
| Tokelau National Statistics Office | TNSO | [email protected] | https://www.tokelau.org.nz/Contact.html |
Metadata production
Document ID
DDI_SPC_TKL_2006_PHC_v02_M
Producers
| Name | Abbreviation | Affiliation | Role |
|---|---|---|---|
| Tokelau National Statistics Office | TNSO | Tokelau Government | Documentation of study |
| Statistics for Development Division | SDD | Pacific Community | Review of the documentation |
Date of Production
2019-03-01
Document version
Version 01 (March 2019): Created during South-to-South training at the Pacific Community, using material from the StatsNZ website as well as unit records and data dictionary supplied by StatsNZ.
Version 02 (April 2019): Review of the existing documentation. Done at Noumea, New Caledonia by Statistics for Development Division.
Version 02 (April 2019): Review of the existing documentation. Done at Noumea, New Caledonia by Statistics for Development Division.