next page  >>

Data structure

This section describes the format that we have adopted for coding information related to multivariate discrete time series. It is a general purpose format and for this reason some people may find it too heavy for simple examples, especially if they do not need the possibility of coding multivariate data. If you have data in a special format and would like our assistance for translation into our format, please contact us. We are collecting users' suggestions and in the future we might offer translators on the Internet.


1. THE BASICS

The data is coded by triplets of numbers: the first two numbers describe the event and the third number a time value.
The first number describes the TYPE of the event.
The second number is used to provide additional information associated to the event and is referred to as the QUALIFIER.
The third describes the time of occurrence, expressed as an INTERVAL from the previous event.
The meaning of the first pair of number in each data item (triplet) is always a code for some event that the user wishes to define and mark its time of occurrence in the file.


      Example:

      1 1 43   1 3 17   1 5 0   1 2 11   ...

It would read: an event of TYPE=1 and QUALIFIER=1 occurred 43 time units after the previous event, then an event of TYPE=1 and QUALIFIER=3 occurred 17 time units later, then another event of TYPE=1 and QUALIFIER=5 occurred within less then a time unit which means 0 time units later (i.e. both events occurred simultaneously), then an event of TYPE=1 and QUALIFIER=2 occurred 11 time units later, etc...

In this simple example only one type of event with many qualifiers has been illustrated. You may think to this example as a series of cars stopping to a gas station to fill the tank. TYPE=1 would mean that the automobile is a car and the qualifier corresponds to the size of car, e.g. QUALIFIER=1 to subcompact, QUALIFIER=2 to compact, and so on. In addition, TYPE=2 could correspond to pick-up cars, TYPE=3 to buses, TYPE=4 to trucks, etc. In some circumstances the TYPE may be used to describe one parameter of an event (such as its frequency), while the QUALIFIER may be used to describe another parameter (such as its intensity).

next page  >>