Agricultural Production Survey: June 2003 (Final)

Background

The 2003 Agricultural Production Survey follows the 2002 Agricultural Production Census and is part of a programme of agricultural production statistics conducted in partnership with the Ministry of Agriculture and Forestry.

The target population for the 2003 Agricultural Production Survey was all businesses engaged in 'agricultural production activity' (including livestock, cropping, horticulture and forestry) with the intention of selling that production and/or which owned land that was intended for agricultural activity during the year ended 30 June 2003.

In terms of the Australian and New Zealand Standard Industrial Classification (ANZSIC), the target population is taken from:

• A01 Agriculture
• A0301 Forestry (excluding native forestry)

and parts of:

• L771290 Commercial Property Operators and Developers nec (Idle land)
• L781000 Scientific Research (agriculture related research that involves land holding (excl. universities))
• N843100 Higher Education (agriculture related research undertaken by universities that involves land holding), and
• P931120 Horse and Dog Training for Racing (racehorse training and racing stables operations).

The target population excluded:

• A015930 - Beekeeping, and
• part of A015990 Other Livestock nec (worm farming, pet breeding, dog breeding, cat breeding, bird breeding (except poultry, game birds and ostriches)).

The survey population for the 2005 Agricultural Production Survey was all businesses identified on Statistics New Zealand's Business Frame as being engaged in agricultural activity (as defined above) or if there is any indication of a secondary agricultural activity. The Business Frame is a list of businesses in New Zealand based on firms registered for goods and services tax (GST) with Inland Revenue, while the Client Register consists of all businesses registered with that department.

Users should note changes to the population over time. In 1994, 1995, 1996, 2002 and 2003, the livestock, cropping, horticulture and forestry sectors were surveyed. The 2004 survey covered the livestock, cropping and forestry sectors (ie horticulture was excluded). In 1999 the survey covered livestock and cropping, while in 2000 the survey covered the horticultural sector only. The 2005 survey covers the livestock, cropping, horticulture and forestry sectors.

Between 1994 and 1996, the population was all businesses sourced from the Business Frame that were registered for GST and classified to agriculture. The 1999 Agricultural Production Survey population was sourced solely from AgriBase (a geospatial database owned and managed by AgriQuality New Zealand Ltd). The population for the 2000 Horticulture Production Survey was sourced from the Business Frame, supplemented by AgriBase and growers lists. For the 2002 Census the population was sourced from the Business Frame and the Inland Revenue Client Register. These sources were checked against industry lists and AgriBase to ensure all large units were included in the population. The Business Frame was used for the 2003, 2004 and 2005 surveys.

Users should also be aware of changes in questionnaire design when making comparisons between 2003 and earlier years.

Errors are divided into two classes: sampling error and non-sampling error.

Sampling error arises from selecting a sample of businesses rather than taking a complete enumeration, and is not applicable when a census is completed. Estimates for the 2003 survey, as for the 1995, 1996 and 1999 surveys, are subject to sampling error. The 1994 and 2002 Agricultural Production Censuses and the 2000 Horticultural Production Survey are not subject to sampling error.

Non-sampling error arises from biases in the patterns of response and non-response, inaccuracies in reporting by respondents, and errors in the recording and classification of data. Statistics New Zealand adopts procedures to detect and minimise these types of errors, but they may still occur and are not easy to quantify.

The estimated proportion of eligible businesses responding to the 2003 Agricultural Production Survey is 84 percent. These businesses contribute 89 percent of estimated total agricultural output.

Statistics New Zealand has imputed values for farmers and growers in the 2003 Agricultural Production Survey who did not return a completed questionnaire. The method of imputation used is random 'hot deck' imputation. A proportion of non-respondents were estimated as ineligible. The remaining non-respondents were grouped into imputation cells based on regional council, ANZSIC group, 2002 production data and annualised GST. Each non-respondent was then randomly assigned to a respondent in the same imputation cell and the farm production data of the respondent was copied across to the non-respondent. In order to improve the imputation process, respondents with uncharacteristically high levels of agricultural activity were removed from their respective imputation cells, as it was considered unlikely that any of the non-respondents would have similar characteristics to them.

All farm count data has been rounded. The sum of components in a table may therefore not add to the total shown. Any percentages are calculated from the rounded figures.

Information obtained from Statistics New Zealand may be freely used, reproduced, or quoted unless otherwise specified. In all cases Statistics New Zealand must be acknowledged as the source.

While care has been used in processing, analysing and extracting information, Statistics New Zealand gives no warranty that the information supplied is free from error. Statistics New Zealand shall not be liable for any loss suffered through the use, directly or indirectly, of any information, product or service.

Timed statistical releases are delivered using postal and electronic services provided by third parties. Delivery of these releases may be delayed by circumstances outside the control of Statistics New Zealand. Statistics New Zealand accepts no responsibility for any such delays.