Skip to content

Privacy and Cookie Policy

We use cookies to improve the user experience. By continuing on this page, you accept our use of cookies.

OK

Please read our Privacy and Cookie Policy here to find out more.

Statistical processing

Contact info

Business statistics, Agriculture
Karsten Larsen
+45 39 17 33 78

kkl@dst.dk

Get as PDF

Agricultural and Horticultural Survey

The information is collected by means of a yearly questionnaire based survey where the farmers complete the questionnaire online. The answers are validated for non probable values.

Information on crops and the animals cattle and fur animals is collected from registers, and is thereby not reported by every single farmer.

The survey is a sample survey stratified by region, size and type of farming.

Source data

The information comes from the questionnaire, IACS, the livestock register and information from the fur animals farmers’ organisation.

In 2019 the sample had a size of 6.000 farms, about 25 per cent all farms in Denmark.

The sample is stratified by regions, size and type of farming (e.g. pig farms, cattle farms and plant production).

Frequency of data collection

The survey is yearly.

Data collection

The farmer reports the information on a web questionnaire on Virk.dk

Information on the survey can be found here: Information

The text is Danish.

Data validation

The statistics go through an error detection process which falls into three steps:

  1. In connection with the online reporting it is secured that all questions are answered. It could for example be yes/no questions where a farmer might answer that he does not have any livestock on his farm.
  2. In the next step all the answers are treated and are subject to a validation, a plausibility check. Errors are corrected immediately, sometimes after telephone contact with the farmers.
  3. In the last step the results are analysed by regions and extreme developments – big increases or decreases – are identified. In this step it is often possible to find a few but rather big mistakes which for one or any reasons have been overlooked in the first two steps.

Data compilation

The extrapolation into a total level takes place by obtaining certain known targets:

  • Number of farms and area are distributed by size based on the farmer’s application for agricultural subsidies. (The single payment scheme).
  • Number of pigs in pig surveys April and July same years.
  • Number of fur animals and farms with fur animals according to information from the farmer’s organisation.

In case of non response the farm is excluded from the sample and the extrapolation is increased accordingly for stratum where non response occurs. The non-response is about 5-10 per cent, in 2018 4.1 per cent.

Imputation is normally not done in the farm structure census. If it nevertheless is done the method is to find a donor farm which has answered the question and is rather similar to the farms with a missing answer. One example could be use of water for irrigation where a farmer in the same region and having a similar composition of crops. Use of water for irrigation is not included in the survey every year.

In the survey 2019 the results for about 17.000 farms smaller than 25 hectares will be imputed.

Adjustment

No corrections are made besides what is described in data validation and data compilation.