Methods - how we monitor
The data are sourced from the quarterly Household Labour Force Survey (HLFS) and the New Zealand Census, both administered by Statistics New Zealand.3
The Household Labour Force Survey (HLFS) is a nationwide, quarterly survey and is the official measure of employment and unemployment in New Zealand. It has been providing the only comprehensive and ongoing picture of the labour force since it began in October 1985. From the information provided, Statistics New Zealand estimates the official unemployment rate and other labour market indicators.
The purpose of the census is to collect demographic and social statistics, which can be used by government, business and community organisations for planning and other decision making.
The New Zealand and Waikato region indicator is updated every year after the March quarter HLFS results are published. The district-level and Maori unemployment rates are updated every 5years after the results of each census are published. The next census is due in 2018.
Census information on the population’s growth rates and structure, including unemployment rate, are available for the period 1991 to 2013. The HLFS results have been used since 2007 and there are no temporal breaks in the data.
The Population Census is a hand-delivered, self-administered survey carried out every 5 years. Statistics New Zealand tries to cover all people in New Zealand on census night. Data are entered into a national database and rounded to ensure anonymity. Data are summarised into various levels including national, regional and territorial authority.
The HLFS is initially a face-to-face survey administered by Statistics New Zealand staff to a randomly selected rolling sample of New Zealand households. After the initial visit, it is administered by telephone. There are about 15,000 households in the sample, which is roughly 30,000 people, from both rural and urban localities. Households and household members are interviewed every 3 months and asked about their activities during a particular week.
Only unemployment rate data from New Zealand residents aged 15 years and over are included in this indicator
We used the following steps to derive data for this indicator:
- Data for New Zealand, the Waikato region and its districts were sourced from table 8 of the Census Regional Summary and table 6 of the HLFS.
- The unemployment rates were either already listed as a per cent in the tables or were calculated using the formula:
‘Total labour force’ comprises all those 15 years and older who were employed full time, employed part time or were unemployed. The total labour force does not include:
- people who said they were not in the paid labour force – for example, people who were retired, working unpaid in the home or beneficiaries who were not actively seeking work
- people who did not identify their work and labour force status.
None relevant to this indicator.
Not everyone who filled in the census form in the Waikato region completed this question. In the 2006 census, 10,998 people (3.7 per cent of all Waikato people aged 15 years or over) did not have an identifiable ‘Work and Labour Force Status’.
There is no means of checking whether the data provided was accurate. Although it is an offence under Part III of the Statistics Act 1975 to falsify answers, and people have to sign a declaration on the census form that the information is true and correct, some people may have given false answers.
The Household Labour Force Survey has an additional limitation because it is sample-based. The HLFS sample contains about 15,000 private households and about 30,000 individuals each quarter. 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. A non-sampling error is very difficult to measure, and if present can lead to biased estimates.
Statistics New Zealand endeavours to minimise the impact of these errors through the application of best survey practices and monitoring of known indicators (eg non-response). In general, the sampling errors associated with subnational estimates (eg breakdowns by regional council area or ethnic group) are larger than those associated with national estimates.
No changes are planned for this indicator.
Quality control procedures
Statistics New Zealand does not check the quality of the data supplied by individuals. Checks are made on the quality of data entry and on the analysis.