Data Collection
Agricultural Production Statistics: June 2024 (Provisional)
Methodology
Period-specific information
Survey information
This release contains provisional results from the 2024 Agricultural Production Survey. Provisional results can change after further processing and analysis of data. We will release final results on 5 May 2025. The final figures will be available at a regional level.
The 2024 survey was part of the current programme of agricultural production statistics that started in 2002. Previous censuses were held in 2002, 2007, 2012, 2017 and 2022, with annual sample surveys in 2003–06, 2008–11, 2013–16, 2018-21 and 2023.
Responses from farmers and foresters in the 2024 Agricultural Production Survey resulted in an estimated eligible population of 46,000 geographic locations.
2024 questionnaire changes (from 2023)
Horticulture – we included questions on the area of fruit trees and vines planted, and the area of vegetables and other horticulture crops harvested.
Irrigation – we included questions on area actually irrigated.
Forestry – we included two forestry questions to capture standard forest (for harvest) and permanent forest (not for harvest).
Effective milking area – we included a new question to capture effective milking area on dairy farms.
Dairy companies or customers – we included a question to capture companies and customers name from dairy farmers.
Sheep for milking – we included a question on the number of dairy sheep used primarily for milk.
Goats – we included two questions on goats to capture the number of goats used primarily for milk and those used primarily for meat.
Solid set systems – we included a sperate question to capture farmers using solid set system (or fixed grid) for irrigation.
Organic farm – we included a new question to identify whether a farm is organic.
Velvet production
We have improved the validation and imputation method for deer velvet production figures. As a result, we believe we were previously undercounting velvet production. We will continue to assess the impact of this change until the final release, on 5 May 2025.
Sample design
For the 2024 Agricultural Production Survey, we used a stratified sample design to select a sample from the population. In selecting this sample, we stratified the population by regional council area, ANZSIC06 group, and size group.
We determined the size groups as follows:
For businesses that had previously responded to one or more of the agricultural production censuses or surveys since 2002, we used the most-recent production data to form size groups. The variables used covered a range of livestock and cropping variables. Typically, three size groups were formed: small, medium, and large.
For new businesses or businesses that had not responded to any of the 2002 to 2023 agricultural collections, a random sample was taken.
The 2024 survey had a sample size of 24,300 geographic locations.
Response rates
The estimated proportion of eligible businesses that responded to the 2024 Agricultural Production Survey for this provisional release was 68.4 percent.
2024 sampling error and imputation levels
Sampling error and imputation levels for the 2024 Agricultural Production Survey
Description | Relative sampling errors at 95% confidence interval (%) | % of total estimate imputed |
---|---|---|
Calves born alive to dairy heifers/cows | 8 | 38 |
Dairy cows and heifers, in milk or calf | 8 | 38 |
Total dairy cattle | 8 | 38 |
Calves born alive to beef heifers/cows | 6 | 31 |
Beef cows and heifers in calf (age 1–2 years) | 10 | 29 |
Beef cows and heifers in calf (aged 2 years and over) | 6 | 30 |
Total beef cattle | 4 | 30 |
Lambs born to ewe hoggets | 9 | 29 |
Lambs born to ewes | 4 | 33 |
Total lambs | 4 | 32 |
Ewe hoggets put to ram | 9 | 32 |
Breeding ewes (2-tooth and older) put to ram | 5 | 32 |
Total sheep | 4 | 32 |
Fawns born on the farm | 12 | 27 |
Female deer mated | 12 | 27 |
Total deer | 13 | 29 |
Breeding sows (aged 1 year and over) | 2 | 9 |
Mated gilts | 3 | 11 |
Total pigs | 0 | 3 |
Wheat tonnage harvested | 30 | 26 |
Wheat area harvested (hectares) | 27 | 26 |
Barley tonnage harvested | 16 | 39 |
Barley area harvested (hectares) | 18 | 39 |
Oat grain tonnage harvested | 18 | 40 |
Oat grain area harvested (hectares) | 16 | 37 |
Maize grain tonnage harvested | 33 | 33 |
Maize grain area harvested (hectares) | 33 | 32 |
Kiwifruit | 2 | 29 |
Wine grapes | 4 | 14 |
Apples | 2 | 16 |
Onions | 0 | 22 |
Potatoes | 22 | 18 |
Squash | 0 | 21 |
General information
About the estimates
Figures in this release are rounded. However, we calculate all percentages in this release using unrounded figures. The figures from the agricultural production surveys may differ from those produced from other sources, such as the National Exotic Forestry Description Survey produced by the Ministry for Primary Industries, the Stock Number Survey from Beef and Lamb New Zealand Limited, and Dairy Statistics from Livestock Improvement Corporation Limited. These surveys use different survey frames and designs.
When converting livestock numbers into stock units, for the various livestock types and class, stock unit conversion ratios from Beef and Lamb New Zealand were used as a guide. These are also known as the ‘Economic Service Conversions’ and can be found in the definitions section of the Beef and Lamb New Zealand benchmarking tool.
Population frame
The agricultural production surveys include all units identified on Statistics NZ's Business Register as having agricultural activity. The Business Register is a list of businesses in New Zealand, based on their registration for goods and services tax (GST) with Inland Revenue.
The compulsory registration level for GST is $60,000, so there is a partial and unquantifiable coverage of units below this level.
Survey population
The survey population for the agricultural production surveys is all businesses engaged in 'agricultural production activity' (including livestock, cropping, horticulture, and forestry), or which own land intended for agricultural activity. The survey population includes businesses engaged in agriculture or forestry production as a secondary activity.
Industries in scope
The survey population specifically includes businesses classified to the following ANZSIC06 codes:
A01 Agriculture
A0301 Forestry (excluding native forestry).
It also includes parts of:
L671200 Non-residential property operators
M691000 Scientific research services (agriculture-related research that involves land holding (excluding universities))
P802300 Combined primary and secondary education (agricultural high school operation)
P802400 Special school education (special needs education involving agricultural production activity)
P810200 Higher education (agriculture-related research undertaken by universities that involves land holding)
R912100 Horse and dog racing administration and track operation
R912900 Other horse and dog racing activities (racehorse training and racing stables operations)
R892200 Nature reserves and conservation parks operation.
The survey population specifically excludes:
A019300 Beekeeping
part of A019900 Other livestock farming nec (worm farming, pet breeding, dog breeding, cat breeding, bird breeding (except poultry, game birds, ostriches, and emus))
A017100 Poultry meat (except growers who also produce eggs for human consumption).
Population changes
For the 2002 Agricultural Production Census, we sourced the population from the Business Register and the Inland Revenue Client Register. We checked these sources against industry lists and AgriBase to ensure all large units were included in the population.
After the 2002 Census, we use the Business Register for the census and survey populations.
Survey content changes
Over the years, we have changed the core information we gather in agricultural production collections.
Since 2002, these collections have gathered information on livestock and arable farming, horticulture, and forestry with the following exception:
In 2004, 2006, 2008, 2010, 2013, 2015, 2016, 2018, 2021 and 2023 the surveys collected information on livestock and arable farming, and forestry (we did not collect horticulture production information).
Stats NZ no longer collects information or compiles statistics relating to forestry production. These statistics can be found on the MPI website. Please note, Stats NZ does continue to collect information and compile statistics relating to forestry land use.
Past questionnaire changes
Fawns
Since the 2005 survey, the data relates to fawns born on the farm that were alive at four months. In 2003 and 2004, data related to fawns weaned on the farm. In 2002, data related to fawns born on the farm. The change took industry recommendations into account.
Deer
Deer figures since the 2004 survey are not directly comparable with 2002 and 2003 figures. Improvements we made to the questions about deer in the 2004, 2005, and 2006 surveys have resulted in improved deer number estimates.
While it is not possible to quantify the exact extent of the previous under coverage, we estimate an undercount of about 70,000 deer at 30 June 2002, and 50,000 at 30 June 2003.
Reliability of sample survey estimates
This release contains statistics from the 2002–2024 agricultural production collections. These results are subject to non-sampling error, and as well as sampling error in non-census years.
Non-sampling error arises from bias in the patterns of response and non-response, inaccuracies in reporting by respondents, and errors in recording and classifying data. Non-sampling error comprises coverage error, measurement error (which arise from respondents, questionnaires, and collection methods), non-response error, and processing error. We use procedures to detect and minimise these types of error, but they may still occur and are not easy to quantify.
Sampling error occurs because we base inferences about the entire population on information obtained from only a sample of that population. As 2003–06, 2008–11, 2013–16, 2018-2021, and 2023-24 collections are sample surveys, not censuses, these results are subject to sampling error.
Imputation
We impute values for farmers and foresters who do not return a completed questionnaire. Imputation involves replacing missing items with values based on other information available.
The Agriculture Production Survey uses random ‘hot deck’ imputation. Using this method, we replace missing values of one or more variables for a non-respondent with observed values from a respondent with similar characteristics.
The imputation class is formed from common characteristics such as regional council area, ANZSIC06 group, and production data from previous years. We randomly assign each non-respondent to a respondent in the same imputation cell, and the farm production data of the respondent is copied across to the non-respondent.
To improve the imputation process, we remove respondents with uncharacteristically high levels of agricultural activity from their respective imputation cells. It is unlikely that any of the non-respondents would have similar characteristics to the removed respondents.
Confidentiality
Data collected and information contained in this release must conform to the provisions of the Data and Statistics Act 2022. Published information must maintain the confidentiality of individual respondents.
Prior to 2017, figures in tables affected by these provisions are denoted by ‘C’. Since 2017, the confidentiality of the tables has been implemented using an input perturbation method which involves adding noise to data at an individual farm level, and figures in output tables no longer have to be replaced with ‘C’s.
Quality suppression
Data with high sample errors or imputation levels are suppressed and are indicated by 'S' in the table.
More information
See more information about the Agricultural Production Survey
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.
Liability
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.
Timing
Our information releases are delivered electronically by third parties. Delivery may be delayed by circumstances outside our control. Statistics NZ accepts no responsibility for any such delay.
Crown copyright©
This work is licensed under the Creative Commons Attribution 4.0 International 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.
en-NZ