The precision varies for the different items of the statistics. The precision is thus highest for the total agricultural area and less precise for specific crops, especially crops grown by only few farmers. Likewise the precision is best for livestock which many farmers have. This is in particular true for cattle.
Coverage: The population includes all active farms in Denmark and is integrated in the Statistical Business Register (ESR), which is kept by Statistics Denmark. In order To ensure that the population is up to date Statistics Denmark regularly makes register merges with IACS and the Central Livestock Register (CHR). The assumption is that if a farm applies for crop subsidies or reports livestock to the livestock register it must be expected to be active in agriculture and should accordingly be marked as such in the register of Statistics Denmark. The sample is selected so that the lowest possible sample error is obtained with respect to agricultural area, pigs, cattle, fur animals and standard output. The farms are divided into groups - strata- by typology and size of standard output. The 2011 survey had 180 strata and 2012 survey 224. Farms known to be specialized horticultural or poultry farms are selected exhaustively. As a general rule the bigger a farm is the more likely it is to be selected. Information on crops is selected from IACS kept by the Ministry of Agriculture. When a farmer applies for subsidies he has to specify his crops carefully. IACS must therefore be assumed to be an extremely reliable source. Information on cattle is collected from the Central Livestock Register and fur animals are collected from The Association of Danish Fur animals farmers. For both these types of livestock the farmer answers yes/no, and for farmers having answered yes the number of animals is taken from respectively The Central Livestock and The Association of Danish Fur animals farmers.
Control: Several computer validations and checks are made before publishing the results.
Due to many different survey characteristics it is not possible to give one figure for the sample error but just some examples:
Certain figures are often reported as round figures, for instance 12.000 chickens. However, there is no reason to assume that there should be any systematic over- or under estimation in the figures. Farmers may forget to answer certain questions. Such errors are difficult to find when it comes to livestock of minor importance like sheep, goats and horses. Questions on work time for the farmer and spouse can be difficult to answer for part time farmers.
Coverage errors must be assumed to be very small. The business register contains information about all Danish agricultural farms. The unit is the local unit. Big efforts are made to secure that all business units of importance with agriculture are included in the register. Among other measures Statistics Denmark uses information from administrative agricultural registers.
Over coverage: 2.700 farms in 2018
Statistics Denmark follows the recommendations on organisation and management of quality given in the Code of Practice for European Statistics (CoP) and the implementation guidelines given in the Quality Assurance Framework of the European Statistical System (QAF). A Working Group on Quality and a central quality assurance function have been established to continuously carry through control of products and processes.
Statistics Denmark follows the principles in the Code of Practice for European Statistics (CoP) and uses the Quality Assurance Framework of the European Statistical System (QAF) for the implementation of the principles. This involves continuous decentralized and central control of products and processes based on documentation following international standards. The central quality assurance function reports to the Working Group on Quality. Reports include suggestions for improvement that are assessed, decided and subsequently implemented.
The quality of the statistics could be assumed to be good for the following reasons:
The survey is of course subject to sample errors. The sample errors are biggest for livestock and crops which only few farms have, e.g. sheep and straw berries, and smaller for frequent occurring livestock like cattle and winter wheat.
Here are some examples on sample errors from the farm structure survey:
The coverage is expected to be good due to frequent updates with sources like The Integrated Agricultural Control Register IACS and the livestock register.
Statistics Denmark revises published figures in accordance with the Revision Policy for Statistics Denmark. The common procedures and principles of the Revision Policy are for some statistics supplemented by a specific revision practice.
In the recent years only final estimates have been made.