2006 Post-enumeration Survey
2006 Post-enumeration Survey
The data collection captures the methodological, collection and analysis information for the 2006 Post -e numeration Survey.
Note: refer to 'A Report on the 2006 Post-enumeration Survey' for in depth information on the 2006 PES linked in this series.
The 2006 PES was based on a stratified, multi-stage sample of 10,900 permanent private dwellings. The survey population consisted of New Zealand residents, either usually resident in a New Zealand private dwelling, or staying at one during the survey period. For the first time, in 2006 overseas visitors who were resident in a private dwelling at the time of the PES and were somewhere in New Zealand on census night, were also included. Overseas visitors were surveyed to investigate the consistency of identification of person type (resident or overseas visitor) between the census and the PES. For practical reasons, n on-private and other private dwellings were excluded from the survey, as were dwellings in remote areas.
T he survey period was chosen to avoid overlap of census enumerators and PES interviewers in the field, while being close enough to census date (7 March) to assist respondent recall.
Matching was done to determine if a PES respondent was counted in the census at each address at which they stated that they had completed a census form, or at each address where a census form may have been completed for them (search address). This was achieved by comparing the information given by PES respondents with the information given on census forms. If an address given was different to the PES address, searching was carried out to locate the address.
Data collected in the PES is used to estimate census coverage for both people and private dwellings.
The n et undercount estimates produced from the PES are subject to both sampling and non-sampling errors.
The estimation methodology for the 2006 PES includes several improvements over that used in 2001 and 1996. This change in methodology has had some impact on the comparability of undercount estimates between 2006 and earlier PESs. Essentially, the 2006 methodology has reduced bias at the expense of some increase in sampling error. The main changes are:
- Not all people responding in the PES are eligible to be included in the estimation formula.
- In 1996 and 2001, the estimation methodology incorporated special procedures for census forms received after PES interviews had started. In 2006, difficulties with the census field management system meant that the number of census late returns was unable to be accurately determined (that is, we could not always identify whether a census form was returned late or on time).
- The information collected from the PES sample is combined using weights to provide an estimated undercount for the whole population. In 2001, a person’s ‘weight’ was determined initially by their probability of selection into the PES sample, and then adjusted to account for non-response in the sample.
- Prior to the 2006 PES, estimates of sampling error were calculated using an approximate analytical formula. The changes to the weight adjustment methodology and standardisation of methods for calculating sampling errors within Statistics NZ has meant that the 2006 PES sampling errors are calculated using a replicated sampling technique.
Sample design The 2006 PES was based on the sample design of Statistics NZ’s Household Labour Force Survey (HLFS). The main reasons for choosing the HLFS design included:
- reduced costs for enumeration and field collection – interviewers were already working in and familiar with the geographic areas used in the sample, and fieldwork made use of existing maps and street listings
- minimisation of respondent burden by controlling the overlap between the PES and other household surveys.
The sampling process was complex. The geographical framework of New Zealand consists of 41,392 meshblocks (a meshblock in urban areas is usually a block of residential area containing about 40 dwellings s urrounded by streets; in rural areas a meshblock covers a much wider area because dwellings are sparsely spread). For the purposes of the HLFS, these meshblocks are aggregated into 20,394 primary sampling units (PSUs). To improve the sampling efficiency these PSUs are stratified into 119 groups (or strata) based on region, urban/rural mix, ethnic population, and other socioeconomic variables (income, employment status, population aged 65 years and over). Each stratum consists of about 160 PSUs on average.
Across the 119 strata, 1,768 PSUs were randomly selected for the HLFS. The PES randomly selected PSUs from among these, using sampling fractions dependent on the stratum characteristics:
- All PSUs from strata with simultaneously high numbers of Mäori, Asian and Pacific residents, or simultaneously high numbers of Mäori and Pacific residents .
- 5/8 of PSUs from other strata with high numbers of Mäori, Asian or Pacific residents
- 1/2 of PSUs from other South Island strata
- 3/8 of PSUs from the remaining strata.
Experience in New Zealand and overseas suggests that ethnic minorities and young persons are more likely to be missed by the census. The higher sample ratios for ethnically diverse areas were therefore designed to help increase the accuracy of the undercount estimates for subgroups of the population by reducing their sampling errors.
Each PSU in the HLFS comprises six or seven panels, and each panel consists of about 10 randomly selected private dwellings. Most of the panels within a PSU are used by the HLFS on a rotational basis with one panel being used for each survey quarter in a year. A spare panel from each of the PSUs was used to make up the PES sample frame for sample selection.
The 2006 PES sample comprised 1,011 PSU panels containing 10,900 dwellings (or about 0.7 percent of total permanent private dwellings in New Zealand).