Page 310 - Invited Paper Session (IPS) - Volume 1
P. 310
IPS155 Stefan B. et al.
Sampling: This item describes the type of the sample and sample design used
to select the observations to represent the population. As an INEXDA
convention, the value of the item will be set to "Total Population" if dataset
contains no sampling, i.e. dataset is the population.
Example: Total Population
Temporal Coverage: The item “Temporal Coverage” refers to the sample
period of the dataset, which is the time period during which the data was
collected or observations were made. The time period should be expressed
in ISO 8601 format. As an INEXDA convention, information on month and
quarter may be omitted if frequency of the dataset is annual.
Example: 2005-12 to 2016-03
Time Dimension: Describe the time dimension of the data collection. In the
INEXDA schema, the following three time dimensions are allowed,
• "Panel" datasets contains information collected from the same (or
almost the same) set of entities over time.
• "Time Series" data is collected repeatedly over time to study changes in
observations. The "Time Series" category is appropriate for almost all
macro datasets, e.g. data on GDP or unemployment rates.
• "Cross-section" dataset are data about a population collected only once.
These items are further broken down by the frequency (e.g. monthly,
quarterly) with which data about entities is collected in the dataset.
Furthermore, the following INEXDA conventions apply to this metadata
item.
• In case time intervals between consecutive data collections are not
equally-spaced (e.g. datasets collected from event-driven reporting),
the highest available frequency in the dataset is selected, that allows
for a meaningful analysis of the data.
• In case the frequency of data collection changes over time (e.g.
because of structural breaks following a change in regulation
governing the collection of the dataset) the most recent frequency
available in the dataset should be used.
Example: Panel: monthly
Collection mode: This item provides information on the method used to
collect the data.
Example: Reporting agents file their reports electronically to Deutsche
Bundesbank.
Unit descriptions: Microdata are data on the level of the individual
observation. Microdata regularly contain numbers or strings attached to
individual observations with the aim to make identification easier. These
identifiers may exist on the company level (e.g. country tax number, LEI) or
299 | I S I W S C 2 0 1 9