- availability of small-area data
means the availability of data for small geographic areas and for small groups of statistical units;
- capturing
means the process by which collected data are put into a machine-readable form;
- census population
means the set of statistical units which is factually represented by the census results on one or more specified topics for a specified target population.
- coding
means the process of converting information into codes representing classes within a classification scheme;
- coefficient of variation
means the standard error (square root of the variance of an estimator) divided by the expected value of the estimator;
- complementary set of statistical units
means the set of those statistical units that belong to an estimated target population, but about which the data source contains no data records as a result of an applied sampling methodology;
- coverage assessment
means a study of the difference between a specified target population and its census population;
- data extraction
means the process of retrieving census information from information contained in a register and relating to individual statistical units;
- data source
means the set of data records for statistical units and/or events related to statistical units which forms a basis for the production of census data about one or more specified topics for a specified target population;
- data structure definition
means a set of structural metadata associated with a data set, which includes information about how concepts are associated with the measures, dimensions, and attributes of a hypercube, along with information about the representation of data and related descriptive metadata.
- defined periodicity
means the capacity to conduct censuses regularly at the beginning of every decade, including the continuity of registers;
- estimated target population
means the best available approximation of the target population.
- estimation
means the calculation of statistics or estimates using a mathematical formula and/or algorithm applied to the available data;
- generation of a family
means the identification of a family based on information on whether the persons live in the same household, but with no or incomplete information on family relationships between persons.
- generation of a household
means the identification of a private household according to the household-dwelling concept as defined in the Annex to Regulation (EC) No 1201/2009 under the topic ‘Household status’;
- identifying variable
means a variable in the data records in a data source or any list of statistical units which is used
- individual enumeration
means that information on each statistical unit is obtained so that their characteristics can be recorded separately and cross-classified with other characteristics;
- item imputation
means the insertion of artificial but plausible information into a data record where the data record already exists in a data source but does not contain this information;
- item no-information
means the failure to collect data on one or more specified topics for a statistical unit that is in the census population, while data on at least one other topic can be collected for that statistical unit;
- matching of registers
means a record linkage where all matched data sources are contained in registers;
- model assumption error
means an error due to assumptions underlying the estimation and containing uncertainty or lack of detail;
- over-coverage
means the set of all statistical units that are included in a census population used to report on a specified target population without belonging to that target population;
- post-enumeration survey
means a survey conducted shortly after the enumeration for coverage and content assessment purposes;
- questionnaire-based data
means data that are originally obtained from respondents by the means of a questionnaire in the context of a collection of statistical data which refer to a specified point in time;
- record deletion
means the act of deleting or ignoring a data record that is included in a data source used to report on a specified target population, but does not report any valid information on any statistical unit within that target population;
- record editing
means the process of checking and modifying data records to make them plausible while at the same time preserving major parts of these records;
- record imputation
means the assignment of an artificial but plausible data record to exactly one geographical area at the most detailed geographical level for which census data are produced, and the imputation of that data record into a data source;
- record linkage
means the process of merging information from different data sources by comparing the records for the individual statistical units and merging the information for each statistical unit where the unit to which the records refer is the same;
- register
means a repository which stores information about statistical units and is directly updated in the course of events affecting the statistical units.
- register-based data
means data that are in or originate from a register;
- simultaneity
means that the information obtained in a census refers to the same point in time (reference date);
- statistical disclosure control
means the methods and processes applied in order to minimise the risk of disclosing information on individual statistical units while releasing as much statistical information as possible;
- statistical unit
means the basic observation unit, namely a natural person, household, family, living quarter, or conventional dwelling;
- target population
means the set of all statistical units in a defined geographical area at the reference date which qualify for reporting on one or more specified topics.
- under-coverage
means the set of all statistical units that belong to a specified target population, but are not included in the corresponding census population;
- unit no-information
means the failure to collect any data from a statistical unit that is in the census population;
- universality within a defined territory
means that data are provided for all statistical units within a precisely defined territory.