2018/19 Household Economic Survey (Expenditure)
The information collected as part of the Household Economic Survey (Expenditure) 2018/19 provides data on Household income and housing cost statistics as well as household economic statistics (expenditure). It also provides data on child poverty.
This section contains data information that has changed since the last release.
Change in sample size
Two samples have been drawn for HES ()Expenditure) 2019 - one overall sample of around 28,500 permanent private dwellings for HES Income (used to derive income and housing-cost measures including the information used to measure child poverty), and a subsample of 5,500 to measure detailed expenditure information from private sampled households asked every three years.
Use of income data from administrative data sources
We are using income data from the Integrated Data Infrastructure (IDI) to replace the following sources of income for all eligible individuals:
- income from wages and salaries;
- benefits; and
- other payments received from the New Zealand Government.
The IDI is a large research database that holds microdata about people and households. The use of admin data reduces measurement errors as well as errors arising from treatment of these errors in income collected from survey data. The use of admin data improves the precision of measures of household income and child poverty. For more details on the use of admin data please read Changes to the Household Economic Survey year ended June 2019
Recall period in the survey varies from latest payment made/income received, to payments made/income received in the last 12 months. As the survey was carried out continuously from 1 July 2018 to 30 June 2019, different households would therefore have different recall periods. Thus, households interviewed on 1 July 2018 would have recall periods earlier than the date interviewed, so from 1 July 2017 to 30 June 2018 while households interviewed on 30 June 2019 would have recall period from 01 July 2018 to 30 June 2019.
Changes in income and housing costs may be influenced by one-off real-world events. Events that could have influenced the HES 2018/19 data are:
increase in the adult minimum wage from $15.75 to $16.50 effective 1 April 2018 and further to $17.70 effective 1 April 2019.
increase in the starting out and training wage from $12.60 to $13.20 effective 1 April 2018 and to $14.16 effective 1 April 2019.
New Zealand Superannuation rate (gross) increasing for single living-alone from $463.04 to $475.42 on 01 April 2019; single sharing from $425.55 to $437.14 on 01 April 2019; and ‘both partners qualifying’ from $350.76 each to $360.42 on 01 April 2019.
Introduction of the families package in the 2018 budget which introduced the Winter Energy Payment and Best Start tax credit and made changes to Accommodation Supplement and Working for Families tax credits.
low OCR kept short-term mortgage rates down.
Response rate for HES 2018/19
The sample size for collecting information pertaining to household income and housing cost statistics was approximately 28,500 households. The achieved sample rate was 73.41 percent and response rate was 82.77 percent.
The subsample used for collecting information for household economic statistics (expenditure) which covered detailed household expenditure, including the 1-week diary was approximately 5,500 households. The achieved sample rate was 71.03 percent and response rate was 81.37 percent.
Achieved sample rate compared with the response rate
The achieved sample rate is calculated as the number of eligible households that responded divided by the total number of dwellings sampled. Essentially, it tells you what percentage of the sample responded to the survey. Expressing the achieved sample as a rate controls for population growth.
|Eligible responding households|
|Achieved Sample Rate||=||____________________|
The response rate is calculated as the number of eligible households that responded to the survey as a proportion of the estimated number of total eligible households in the sample.
|Eligible responding households|
|Eligible responding households + eligible non-responding households|
The achieved sample rate differs from the response rate because it includes the ineligible dwellings in the denominator. This difference means that the response rate is particularly sensitive to the classification of household eligibility. As a result, the achieved sample rate is more stable over time than the response rate. The impact of any bias arising from non-responses is minimised by non-response adjustment and the calibration to population benchmarks.
Imputation for HES 2019
Imputation replaces missing values with actual values from similar respondents.
Two imputation methods are used in HES – nearest neighbour donor imputation and median imputation (the latter for expenditure only).
The nearest neighbour donor imputation method replaces missing values by data values from another record called a donor. A donor is selected by finding a respondent with matching characteristics to the recipient. Median imputation uses the median of the acceptable values to replace a missing value.
We introduced donor imputation into HES in 2009/10, and now use it in all HES releases. We also applied imputation to every previous HES cycle and revised the data accordingly.
The donor imputation is applied to a household where the household does not supply all the required income or expenditure information but supplies sufficient information to be retained in the sample.
For individuals aged 15 years and over, we imputed income from investments and self-employment. We use income from wages & salaries and benefits from admin data, however we impute for eligible individuals (aged 15+) who did not link to the IDI. In addition, we impute age for respondents who do not provide an age.
We also impute local and regional council rates for respondents who have not provided enough information for us to calculate their rates. A form of manual imputation is used to impute interest rates. We also use donor imputation for all eligible individuals (aged 15+) who did not complete a diary but are in-scope for the diary, ie, not away overseas.
We calculate sampling errors using the jackknife method. It is based on the variation between estimates of different subsamples taken from the whole sample. Sampling errors by income source and housing-cost type are provided for each published table. Customers should take care when interpreting income or housing-costs estimates with sampling errors greater than 20 percent – they are statistically less reliable than estimates with sampling errors less than or equal to 20 percent.