Statistical processing

Source data

The source basis for the national accounts consists of many different statistics on economic activity. The most important sources can be mentioned: - The consumption survey - Accounting statistics for private city businesses - The working time account - Rent surveys - The income statistics - Accounts for public administration and service - Securities statistics - Accounting statistics for financial companies

The consumption survey is based on data collected via a sample survey, which is divided into an interview part and an accounting part, combined with data from administrative registers. The sample is drawn simply at random from approx. 2,000 addresses every quarter, which together amount to approx. 82,000 annually. The addresses are distributed equally over weeks. In the interview part, information is obtained about the household 12 months back in time. It is primarily information about major fixed expenses, such as rent, insurance, white goods, services and health visits, etc., which is obtained in the interview part. In the accounts section, information is obtained about the household's daily purchases over 14 days. The daily purchases include, for example, groceries, petrol, clothes and restaurant visits etc. Data from administrative registers include information on income, housing conditions, household composition, education and hospital use. IDs include information from registers in the Consumption Survey for 2022, the information comes from the following registers: - The income statistics register - Building and Housing Register, BBR - The Population Statistics Register - The education and work classification register - The hospital utilization statistics - Car register DMR

Frequency of data collection

The consumption survey is carried out annually. Households participate continuously in the survey throughout the year. Annual national accounts figures for the household sector are published twice a year.

Data collection

Data for the national accounts is delivered via internal deliveries.

An external service provider takes care of the data collection for the Consumption Survey. Households that are randomly selected are sent a letter about participation in the survey via E-box and are subsequently contacted by telephone with a view to getting the household to participate. If the household agrees to participate, the household must keep a 14-day account of their consumption and subsequently be visited by an interviewer who asks questions about the household's fixed expenses as well as major expenditure items a year back in time. The 14-day account is digital and can, however, also be completed on paper. The interview is conducted in CAPI (a computer-based personal interview) by an interviewer. Data from administrative registers is retrieved per 31 December in the reference year, or the latest year available. If data is obtained from an earlier year than the reference year, price and quantity data are converted to the price level for the reference year.

Data validation

In addition to the data validation carried out in the primary statistics, a further series of data validation procedures are carried out after receipt for the national accounts. Among other things, validation procedures that ensure that a correct economic interpretation of the results can be made.

Interview data is validated both during and immediately after the visit interview. The validation during the interview consists partly of logical and partly of probable checks, while the validation after the interview is carried out manually. A logical check could be, for example, that the household has a car, but does not report expenses for weight tax, car insurance, etc. A likely check could be, for example, that very high or low amounts are investigated directly in the program used for the interview and that the household is confronted with this and must deal with whether it is correct.

When data comes in to Statistics Denmark, it goes through a validation which, for example, involves assessing the household's consumption in relation to its size. If, for example, there is only one person and a very high water consumption, or there are, for example, two adults with children, where it has not been reported how many months have been used for daycare and school, the household will be contacted to clarify the accuracy of the information. Some corrections are made without contacting the household, where the description of the purchase and the amount seem contradictory. It could be, for example, that a liter of milk is registered with an amount of DKK 1,000. This will be corrected to DKK 10.00.

The 14-day accounts are validated continuously when they come in, and collectively when the collection of accounts for a year has been completed. In the overall validation, it will be checked, for example, whether all purchases are coded correctly in relation to the classification, ECOICOP.

Data compilation

These statistics use data from sector accounts and for household consumption calculated in the overall national accounts.

The consumption survey is based on a 2-year sample, i.e. The consumption survey for e.g. 2022 is compiled from samples taken in 2021 and 2022. When data for 2021 is included as part of the 2022 Consumption Survey, it is adjusted for the development in the general price level. For this adjustment, the same adjustment factor is used that is used to calculate private consumption at fixed prices in the national accounts. When all accounts, interviews and address cards for a year have been received, all this information is collected for each individual household.

The consumption survey 2022 includes register information for 2021 and 2022, as it is a two-year sample that is used. The register information must be linked to the individual individuals in the household. For some people, information will be missing from the registers. In case of missing information, it is retrieved from a previous year or by imputation.

When the imputation of the consumption survey is made for all households in Denmark, the same register information is used as used in the consumption survey, but for all households. The empty gaps are then filled via an imputation, using the method "The Missing Forest imputation", developed by Stekhoven and Buehlmann (2012).

The following variables are used as background information for the imputation: - Demographics: - Number of people in the household and subtotals for the number of adults, children, men and women in the household - Age of the "main person in the household" - Gender of the "main person in the household" - Ethnicity (Danish, immigrant or descendant) of the "main person in the household" - Geographic region in Denmark (NUTS2) - Date of moving into their current home - Socioeconomic: - Socio-economic classification - Educational level of the "main person in the household" - Housing type, i.e. single-family house, apartment, etc. - The size of the home in square meters - Car ownership (if applicable) - Power source: Petrol, diesel, electric or other - Age: Date of first registration of the car - Known variables (from the income register): - D11: Salary received - D5: Paid current income and wealth taxes, etc. - D62: Received social benefits, except social transfers in kind

These variables are used to impute the missing values ​​for the remaining income and consumption variables. Individual figures in the national accounts do not have corresponding micro data, which is why the best possible micro data or the least disturbing for the overall result are distributed. This applies to FISIM, where interest is distributed and, for example, investment income from insurance assets, where disposable income is distributed.

Overview of the link between micro and macro data.

To group the households, we have used the equivalent disposable income, which makes it possible to compare the income of families independently of family size and age composition. Read more about Equivalent disposable income.

Adjustment

No corrections are made to data other than what has already been described under data validation and data processing.