


French
Equivalent: Série temporelle 
Definition: 
A time series is a set of regular timeordered observations of a quantitative characteristic of an individual or collective phenomenon taken at successive, in most cases equidistant, periods / points of time.

Context: 
The essential quality of the series is the order of the observations according to the time variable, as distinct from those which are not ordered at all, e.g. in a random sample chosen simultaneously or are ordered to their internal properties, e.g. a set arranged in order of magnitude.
In GESMES/TS, a time series is a timeordered vector of observations. A time series is uniquely defined within a data set by its key. (European Central Bank (ECB), Bank for International Settlement (BIS), Eurostat, International Monetary Fund (IMF), Organisation for Economic Cooperation and Development (OECD), "GESMES/TS User Guide", Release 3.00, February, 2003; unpublished on paper available at http://www.sdmx.org/Data/GesmesTS_rel3.pdf)
In the context of subannual [infraannual] statistics, a time series (TS) can be decomposed into unobservable components. In the most complete case, these components are the trend (T), the cyclical ( C), the seasonal (S) and the irregular (I) components.
The four components of the time series may each be independent of all the others, in which case the behaviour of the time series is simply the sum of the components which are additively related (i.e. TS = T+C+S+I). However, most analysts believe that it is unlikely that the time series components are perfectly independent of each other, and are therefore more likely to be multiplicatively related (i.e. TS=T*C*S*I).

Source
Publication: 
OECD, 2005, Data and Metadata Reporting and Presentation Handbook, OECD, Paris, Section 4: Guidelines for the reporting of different forms of data.

Statistical
Theme: Methodological information (metadata) 
Glossary
Output Segments: 
SDMX

Created
on Tuesday, September 25, 2001 
Last
updated on Tuesday, June 11, 2013 












