Stats NZ has a new website.

For new releases go to

As we transition to our new site, you'll still find some Stats NZ information here on this archive site.

  • Share this page to Facebook
  • Share this page to Twitter
  • Share this page to Google+
Household Economic Survey (Income): Year ended June 2014
Embargoed until 10:45am  –  27 November 2014
Data quality

Period-specific information
This section contains information about changes affecting the latest data.

General information
This section contains information about data that does not generally change between releases. 

Period-specific information

Recall period

We collected data in this release between 1 July 2013 and 30 June 2014. The majority of housing-cost expenditure was collected as 'latest payment' – meaning the amount most recently spent on this item. However, for some housing costs, we asked respondents about their spending in the 12 months before the interview – examples include easement or ground rent, and lump-sum payments connected with renting (bond payments or rent administration fees). Expenditure data collected by 12-month recall period essentially covers a two-year period – from 1 July 2012 (for households contacted on the first day of the survey,1 July 2013) through to 30 June 2014 (those interviewed in the last month of the survey).

For information on income, each household member aged 15 years and over is asked about their income for the year before their interview date. As a result, income data also covers a two-year period.

The figure below demonstrates how the recall period can overlap with a previous reporting period.

Graph, Recall period for income/expenditure measures in HES and HES (Income), 2009/10 to 2013/14.  

External influences

Changes in income and expenditure will be influenced by real world changes that come into effect during the collection period.

Changes to the benefit system

Significant changes for benefits types, and obligations beneficiaries must meet, came into effect on 15 July 2013. Three new benefits replaced most of the previous main benefits as outlined in the table below.

Changes to New Zealand's benefit system

 Old benefit  New benefit (effective 15 July 2013)
 Unemployment benefit  Jobseeker support
 Sickness benefit
 Domestic purposes benefit – women alone

 Domestic purposes benefit – sole parent if youngest child is aged 14 or over

 Widow's benefit – without children, or if youngest child is aged 14 or over
 Domestic purposes benefit – sole parent if youngest child is aged under 14  Sole parent support
 Widow's benefit – if youngest child aged under 14
 Invalid's benefit  Supported living payments
 Domestic purposes benefit – care of sick or infirm

There was no change to: emergency benefit, orphan’s benefit, unsupported child’s benefit, youth payment, and young parent payment.

As a result of these changes, we redesigned the questions relating to payments from Work and Income (WINZ). This was to ensure that respondents reported both the old and new benefits they received (where applicable), and to avoid any overlap in the number of weeks the new and old benefits were received. However, from survey figures it is evident that some respondents may not have reported both their old and new benefits, which has led to a decrease in the length of time benefits were received. This in turn has affected the total income from government benefits. It is difficult to assess how much of this is due to mis-reporting by respondents and how much is due to real-world changes.

Other events that could have influenced the HES (Income) 2013/14 income data include:

  • annual increases in the adult minimum wage – from $13.00 in April 2011 to $14.25 from 1 April 2014.
  • increases in government transfer maximum rates for main benefits and student allowances. The most-recent increase of 1.38 percent was from 1 April 2014.
  • increase in New Zealand Superannuation rates. The most-recent increase of 2.66 percent was from 1 April 2014.
Other changes

The move by most insurance companies in New Zealand to insure homes for a ‘maximum specified amount’ rather than ‘total replacement cost’ may have affected household spending on housing costs.

Changes to the questionnaires

Benefit changes necessitated our making multiple changes to the questions asked in the income questionnaire in HES (Income). Compared with HES 2012/13 and HES (Income) 2011/12, we made the following changes:

  • Listed WINZ benefits across four showcards instead of a single showcard. While showcard 16a listed continuing benefits (those that did not change from 15 July 2013), showcard 16b only listed benefits discontinued from 15 July 2013; showcard 16c only listed new benefits introduced from 15 July 2013 and showcard 16d listed only emergency benefits. 
  • Listed WINZ supplements in two different showcards – while showcard P18a listed supplementary benefits that were included with a main benefit or pension, showcard P18b listed those received as a standalone supplement. 
  • Added a new question to capture any other benefit that respondents may have received from WINZ or Studylink, which had not been reported in any previous question. 
  • Replaced 'independent youth benefit' with 'youth benefit/youth parent payment'. 
  • Deleted special transfer allowances and special needs grants from the benefits/supplements listed in the showcard because fewer people received these benefits. 
  • Deleted recoverable assistance payments – these payments are to be paid back and hence are not income.

See Household Economic Survey 2013/14 printable questionnaires for the latest questionnaires.  

Response rate to HES (Income) 2013/14

The target response rate for HES (Income) is 75 percent of eligible households. Our achieved response rate for the year ended 30 June 2014 was 80.9 percent (post-imputation).

We calculate the response rate by determining the weighted number of eligible households that responded to the survey as a proportion of the estimated weighted number of total eligible households in the sample.  

Imputation for HES (Income) 2013/14

Imputation in HES replaces missing values with actual values from similar respondents. The table shows the effect of imputation for the 2013/14 survey.

Number of individuals before and after imputation
Year ended 30 June 2014
   Number of people aged 15+
 Eligible individuals pre-imputation


 Individuals imputed


 Recovered records


 Eligible individuals post-imputation


See imputation for more information.

As a result of recovering and imputing records, the response rate for the year ending 30 June 2014 improved from 78.0 percent to 80.9 percent.

Sampling errors

Sampling error refers to the variability that occurs by chance because we survey a sample rather than an entire population. This is calculated from the variability of the observations in the sample.

We use the jackknife method to calculate sampling errors. It is based on the variation between estimates of different subsamples we take from the whole sample.

The tables below summarise the sampling errors for 2011/12, 2012/13, and 2013/14, by income source and housing-cost type. The tables also indicate the variability of the estimates for the three surveys.

Data users should take care when interpreting income or expenditure estimates with sampling errors greater than 20 percent. They are less statistically reliable than estimates with sampling errors less than or equal to 20 percent.

See Reliability of survey estimates for more information.

Sampling errors for average annual household income, by income source
(for households receiving that source of income)
Year ended 30 June 2012, 2013, and 2014
 Income source

 Level sampling error (%)



 2011/12  2012/13  2013/14
 Wage and salaries














 Private superannuation




 New Zealand Superannuation and war pensions




 Other government benefits




 Other sources




 Total regular income





Sampling errors for average weekly household expenditure, by housing cost type
(for households with that type of expenditure)
Year ended 30 June 2012, 2013, and 2014

Expenditure item

Level sampling error (%)




 Property and ground rent




 Other payments connected with renting




 Total rent payments




 Mortgage principal repayments




 Mortgage interest payments




 Application and service fees for mortgages




 Total mortgage payments




 Property rates




 Building-related insurance




 Other housing costs




 Total housing costs




 1. Diary expenditure excluded from sample error calculations to improve comparability between full HES and HES (Income)

Contact for more detailed sampling errors.

General information

About the survey

As with the full HES, our target population for HES (Income) is the usually resident population of New Zealand living in private dwellings, aged 15 years and over. This population does not include:

  • overseas visitors who are in New Zealand for less than 12 months 
  • people living in non-private dwellings, such as hotels, motels, boarding houses, hostels, and homes for the elderly 
  • patients in hospitals, or residents of psychiatric or penal institutions 
  • members of the permanent armed forces in group living facilities (eg barracks) 
  • people living on offshore islands (excluding Waiheke Island) 
  • members of the non-New Zealand armed forces 
  • non-New Zealand diplomats and their families.  

HES (Income) components

HES (Income) has four survey components:

  • a household questionnaire
  • a shortened expenditure questionnaire collecting household housing costs
  • an income questionnaire for each household member aged 15 years and over 
  • a set of non-monetary indicator questions for one member of the household who is 18 years and over (chosen randomly).  

This survey uses computer-assisted interviewing that we first introduced in the 2006/07 interview period.
See printable versions of the questionnaires for survey questionnaires used for 2013/14.  

Sample design information

We select the sample for HES (Income) using a two-stage stratified cluster design. Households are sampled on a statistically representative random basis from areas throughout New Zealand. The sample is stratified by geographic region, urban and rural area, ethnic density, and socio-economic characteristics.

The HES (Income) sample has approximately 4,700 private households. We obtain information for each member of sampled households that fall within the scope of the survey and meet survey coverage rules.  

Accuracy of the data

Reliability of survey estimates

Two types of error are possible in estimates based on a sample survey – sampling error and non-sampling error.

Sampling error is a measure of the variability that occurs by chance because a sample rather than an entire population is surveyed.

Non-sampling errors arise from biases in the patterns of response and non-response, questionnaire design, inaccuracies in reporting by respondents, and errors in recording and coding data. We endeavour to minimise the impact of these errors by applying best practice survey methods and monitoring known indicators (eg non-response).  

Data validation and editing

As part of the quality check process, we put HES (Income) data through a validation process at the end of each quarter of the survey cycle. This involves looking for any unexplained outliers, as well as comparing data against previous HES data, as well as other sources, for any movements we cannot explain by real-world changes.

Using computer-assisted interviewing allows range and consistency edits to be made in the questionnaire, meaning interviewers can check improbable values and the consistency of responses during the interview. This reduces errors within the data.

Once the data are electronically loaded to the processing database, we edit the data and resolve inconsistencies and errors.


We allow a proxy to provide information for the income questionnaire in ‘family type’ households:

  • where the whole household is informed about the survey. All agree to participate, but are not able to be present when we administer the questionnaires 
  • for children away at boarding school 
  • for people who don't work and have no source of income
  • for the elderly, sick, or mentally incapacitated.

In all cases of proxy interviews, the interviewer must be convinced the proxy is totally familiar with the other respondent’s information.  


Imputation is a type of error treatment where we determine replacement values for some or all fields, and then assign these values to fields in individual records to replace erroneous or suspicious data. Imputation in HES replaces missing values with actual values from similar respondents. We use the nearest neighbour donor imputation method, where missing values are replaced by data values from another record called a donor. We select a donor is by finding a respondent with matching characteristics to the recipient, on variables correlated to the missing values.

We introduced imputation into HES in 2009/10. We also applied it to data for 2006/07 (HES), and 2007/08 and 2008/09 (HES Income) and revised the data. Imputation is applied to a household where the household does not supply all the required income or diary information, but supplies sufficient information to be retained in the sample.

For households where at least one significant person has a fully completed income questionnaire, we impute income questionnaires for other household members who have not fully completed their income questionnaire(s). In full HES years, we apply the same process when diaries are not supplied by all eligible members of the household. In addition, we impute age for respondents who do not provide an age.

Before imputation was introduced, we discarded households where one or more questionnaire(s) were missing. With imputation, some of these households are recovered.  

Population weighting and benchmarks

Population weighting and adjustments

Weighting plays a vital role in estimation. We give each unit in the sample a weight that indicates the contribution of the sampled unit to the final population estimate. Weighting ensures that estimates reflect the sample design, adjusts for non-response to minimise the potential for non-response bias, and reduces sampling errors. For household surveys, deriving the weight is a multi-phase process.

The first stage of the weighting involves calculating a unit’s initial weight, which is dependent on the sample design and equals the inverse of the probability of selection.

The second stage involves adjusting the initial weights to account for unit non-response. Unit non-response refers to a household that either provides no information, or the amount of information provided (and/or quality of) is insufficient to be regarded as a response. We reduce the initial weight of a non-responding unit to zero, while initial weights of responding units are scaled up accordingly by region and interview month.

The final stage in the weighting process is integrated weighting. Integrated weighting also aligns estimates with externally sourced population, person, and household benchmarks and adjusts for under-counting of specific sub-population groups, such as young males and Māori.

The population we used for the integrated weighting was benchmarked to estimates based on the 2006 Census.

HES benchmarks

The person benchmarks we use for HES are: regional population estimates; children sub-population estimates by three age groups; adult sub-population estimates by sex and 13 age groups (including 75 years and over); and adult Māori sub-population estimates by two age groups (including 30 years and over).

The household benchmarks are: two categories of household composition (two-adult households and non-two-adult households), and these categories further by regions.

Population estimates are based on the 2006 Census of Population and Dwellings. 

Under-reporting expenditure

For some types of housing-cost expenditure, the estimated amount for all private households is less than expenditure reported from other data sources.

There are three main reasons for this difference.

  • We exclude expenditure by residents of non-private households, or by those ineligible for the survey (eg overseas visitors). 
  • Respondents to the survey forget or omit some types of purchases because they are unable to recall expenditure, or cannot refer to records at the time of the interview. 
  • A bias associated with non-response affects some statistics.

We do not adjust the data to compensate for any under-reporting.

HES does not collect rent payments made by businesses (including insurance companies). For example, if EQC or an insurance company is paying rent for a household we do not collect this information. This is of particular importance for data collected in Canterbury, where a greater number of earthquake-damaged households may still be having their rent paid by the EQC or an insurance company. Rent payments we collect in HES include rent from all private eligible households. This includes rent payments for council and state-owned dwellings.

Comparing data with other HES years

HES (Income) has a relatively small sample size (approximately 4,700 households). Although we adjust survey results for various demographic variables (age, sex, and region), there can be variability in survey estimates from one survey collection period to the next. This variability may be caused by the selection of a different group of households for each survey.  

Comparing full HES data with estimates in HES (Income) releases: data exclusions

To make HES (Income) and full HES as comparable as possible, we exclude some expenditure data from full HES that is not collected in HES (Income) – such as housing costs expenditure reported in the diaries and some insurance expenditure that is only collected in full HES years.

In this 2013/14 release, as in the 2010/11 and 2011/12 HES (Income) releases, we revised expenditure figures from the previous full HES years (2006/07, 2009/10, and 2012/13) to exclude diary-sourced housing costs, and to adjust for the different level of details collected in the expenditure questionnaire in full HES. These adjustments are aimed at improving time-series comparability.

Other differences between the surveys, including questionnaire structure, are not adjusted for. We have evidence that these structural differences (eg level of detail and length of questionnaire) are affecting the comparability of housing costs data between HES (Income) and full HES years. These differences particularly affect the mortgages and loans expenditure data, which are a significant component of total housing costs. For this reason, we only compare mortgages and loans, and total housing costs, in the current HES (Income) with previous HES (Income) years in the commentary.

See Differences between the full HES and HES (Income) for more information on the differences between the surveys.

Using non-monetary indicator data

The set of non-monetary indicator questions collects information on material standard of living. The questions are about ownership of certain essential items, affordability to do certain activities, and the extent to which people economise. We also ask respondents how they rate their overall life satisfaction.

From this set of questions, we publish selected results for life satisfaction levels, and adequacy of income to meet everyday needs. We do not produce an index measurement of material well-being from this data. Other agencies use such data in conjunction with other measures (eg income, expenditure on housing costs, or household demographics), to give an indication of the material well-being of New Zealanders. 

Interpreting the data and confidentiality

Interpreting the data

The following factors need to be considered while interpreting data from this survey.

  • A household’s expenditure or income can be influenced by household size, household composition, geographic location, and employment-related factors.
  • All income figures refer to gross (before tax) income, and housing-cost expenditure includes GST, where it applies.
  • Our geographical breakdown into five broad regions is the lowest available for HES, due to the sample design.  

Confidentiality and suppression

Data in this information release is suppressed if based on fewer than five people or households. Below this level there is a risk to respondents’ confidentiality or data would be unreliable. Data is also suppressed if they have a relative sample error of 51 percent or higher (21 percent for cross-tabulated data).  

Customised data

The tables in this information release do not contain all possible analyses of HES (Income) data. We can customise data requests to users' specifications.  

More information

See HES and HES (Income) for more information about HES.  

Statistics in this release have been produced in accordance with the Official Statistics System principles and protocols for producers of Tier 1 statistics for quality. They conform to the Statistics NZ Methodological Standard for Reporting of Data Quality.


While all care and diligence has been used in processing, analysing, and extracting data and information in this publication, Statistics NZ gives no 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.  


Our information releases are delivered electronically by third parties. Delivery may be delayed by circumstances outside our control. Statistics NZ does not accept responsibility for any such delay

Crown copyright©

Creative Commons logo.
This work is licensed under the Creative Commons Attribution 3.0 New Zealand licence. You are free to copy, distribute, and adapt the work, as long as you attribute the work to Statistics NZ and abide by the other licence terms. Please note you may not use any departmental or governmental emblem, logo, or coat of arms in any way that infringes any provision of the Flags, Emblems, and Names Protection Act 1981. Use the wording 'Statistics New Zealand' in your attribution, not the Statistics NZ logo.

  • Share this page to Facebook
  • Share this page to Twitter
  • Share this page to Google+
  • Share this page to Facebook
  • Share this page to Twitter
  • Share this page to Google+