Te Kupenga data collection 2018

Cross-section survey Te Kupenga was run as a post-census survey. A post-census survey provides a unique opportunity to run a large survey of a small sub-group of the population in a cost-effective manner. Administrative lists, such as the electoral roll, suffer from serious under coverage and using the Stats NZ household survey frame is expensive because of the need to screen a large number of households in order to find the target population. Using the Census as a frame provides a degree of coverage not matched by any other single method. In addition, information collected from respondents in Te Kupenga can be linked with their census responses to questions, such as income and labour force status. This minimises respondent burden and helps to reduce data collection costs. Sample population The usually resident population of New Zealand, aged 15 years or older, of Māori ethnicity and/or descent, and living in occupied private dwellings on 2018 Census night. Sample size For 2018, we increased the sample size to 11,500 people, the target response rate was 75 percent, or around 8,500 individuals. We achieved a sample of 8,500 people, which is a response rate of 73.2 percent. This result is comparable to 2013 when around 5,500 people completed the Te Kupenga survey, a response rate of 74 percent. The sample size was increased in response to researchers and other interested parties, such as iwi, wanting to do more with Te Kupenga data. More information can be found in: Differences between Te Kupenga 2013 and 2018 surveys. Sample design The sample was created based on primary sampling units that cover New Zealand and ensure representation of different subgroups, that is region, urban, and rural areas, and areas with different levels of concentration of Māori population. Respondents from the 2018 Census living in the primary sampling units were selected. To ensure representation of different age groups, the sample was selected from three age groups: 15 to 29 years, 30 to 54 years, and 55 years and over (sample population: people of Māori ethnicity or descent aged 15 years or older who live in occupied private dwellings). Collection of Te Kupenga data is designed to begin within weeks of the completion of census enumeration to minimise the number of people who may have moved subsequent to census day, so the sample frame was derived from an interim census dataset in May 2018. Potential bias There was under-coverage in the interim dataset from the 2018 Census (accessed in May 2018), due to lower than expected response rates in the 2018 Census, particularly for Māori. This raised concerns about how well the Te Kupenga sample frame represents the Māori population of New Zealand as a whole, and the impact this may have had on the Te Kupenga data. This potential bias was covered in Assessment of potential bias in the Te Kupenga sample frame: 2018. Note: the investigation showed there is some bias in the sample frame, but this bias is small. Reliability of survey estimates (RSE) Data with high sampling errors should be used with caution. Estimates with RSEs between 50 and 100 percent are considered unreliable for most uses and are flagged with double asterisks **. Estimates with RSEs over 100 are also provided and are flagged with triple asterisks ***. They are deemed to not be useful. The absolute sampling errors are available in the published tables. Two types of error are possible in estimates based on a sample survey: sampling error and non-sampling error. Sampling error can be measured and quantifies the variability that occurs by chance because a sample rather than an entire population is surveyed. Non-sampling errors are all errors that are not sampling errors. These errors are not quantifiable and include unintentional mistakes by respondents, variation in the respondent's and interviewer's interpretation of the questions asked, and errors in recording and coding data. We endeavour to minimise the impact of these errors by applying best survey practices and monitoring known indicators (ie non-response). We estimate sampling errors using a jack-knife method, which is based on the variation between estimates and on taking 100 mutually exclusive subsamples from the whole sample. Sampling errors are quoted at the 95 percent confidence level. For example, if the estimated proportion of the population is 20 percent, and the estimate is subject to a sampling error of plus or minus 2 percentage points (measured at the 95 percent confidence level), that shows there is a 95 percent chance the true proportion of the population lies between 18 and 22 percent. Suppressed estimates Some estimates are suppressed (replaced by 'S' in the tables) for reliability reasons. These suppressed estimates have a weighted value of less than 1,000 and reflect a low number of responses that are subject to larger relative sampling errors. en-NZ