|
About HES | Tables | Reliability | Rules | Changes | More information
In addition to Household Economic Survey: Year ended 30 June 2007, we're making more Household Economic Survey (HES) data free as part of the Making More Information Freely Available initiative.
About HES
HES collects information about household income and expenditure, including information about food, clothing, housing, transportation, household operation and recreation expenditure. HES also collects demographic information on households and individuals.
Run annually until 1998, it is now conducted three-yearly. The majority of the survey questions relate to people aged 15 or over.
Excel tables
Expenditure on goods and services
Household expenditure by expenditure on goods and services with percentages and sampling errors (69.5KB) (xls)
Storetype expenditure group
Aggregate annual household expenditure by storetype and expenditure group (103KB) (xls)
The following tables can be downloaded from the Statistics New Zealand website in Excel format. If you do not have access to Excel, you may use the Excel file viewer to view, print and export the contents of the file.
Household expenditure
Household expenditure by group, subgroup and class
Revised tables
The data published on 30 November was incorrect. The tables containing household expenditure by broad region, household income group and number of people in the household have been replaced. The national totals were correct, however the denominators for the sub-groups were incorrect. These have now been corrected.
Household expenditure by broad region
Household expenditure for group and subgroup by broad region
Household expenditure by household income group
Household expenditure for group and subgroup by household income group
Household expenditure by number of people in household
Household expenditure for group and subgroup by number of people in household
Latest tables
Household expenditure by principle source of income
Household expenditure for group and subgroup by principle source of income
Household expenditure by household composition and number of dependent children
Household expenditure for group and subgroup by household composition and number of dependent children
Household expenditure by tenure of household
Household expenditure for group and subgroup by tenure of household
Material Standard of Living Ownership
Social Participation
Customised data is available on request.
If you have any queries, contact our Information Centre staff on 0508 525 525 or email info@stats.govt.nz. Our hours are 8am to 5pm, Monday to Friday (excluding public holidays).
The HES survey sample contains about 3,000 private households with about 7,000 individuals. Households are sampled from rural and urban areas throughout New Zealand on a statistically representative basis, and information is obtained for each household member.
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).
Sampling errors are calculated for each published cell. For example, the estimated average weekly expenditure on food was $155.60 per household. This estimate is subject to a sampling error (or margin of error) of plus or minus 4.0 percent (measured at the 95 percent confidence level). This means that there is a 95 percent chance that the true value lies between $149.40 and $161.60.
In general, the sampling errors associated with subnational estimates (eg breakdowns by broad regional group) are larger than those associated with national estimates.
The following rules apply to all HES tables (including those in Table Builder):
For tables with cross-tabulations:
- only data with a sample error under 21 percent of the estimate will be available for cross-tabulation with another variable
- all cells where there are fewer than five households contributing data will be suppressed for confidentiality and quality reasons.
Where there are no cross-tabulations:
- Data with a sample error in the range 21 to 50 percent of the estimate will be marked with an asterisk (*). Caution should be used when interpreting these estimates.
- Data with a sample error of 51 percent or more of the estimate will be suppressed as it is subject to sample error too great for most practical purposes.
For more about sampling error, see reliability of survey estimates (above)
Between 2003/04 and 2006/07 HES underwent significant redevelopment, with major changes to the collection methodology and classifications used. The key changes to the 2006/07 HES were:
- moving from paper-based collection to computer assisted interviewing (CAI)
- basing the population weights on 2006 Census data
- including the Economic Living Standard Index (short form version) questionnaire
- using new expenditure and storetype classifications.
The new expenditure classification was developed to meet the need for a common household consumption classification to better-align with the Consumers Price Index, national accounts and international standards. Consequently there is no expenditure time series in this release, as 2006/07 expenditure data is not directly comparable with data from previous years.
Find out more about Changes to the Household Economic Survey (PDF)(176 KB).
The Hot Off The Press for the Household Economic Survey: Year ended 30 June 2007 was released on 30 November 2007. Find out more about HES.
|