Methods and algorithms using more than one input variable are usually
called multivariate statistics. A special case with only two input
variables is sometimes called bivariate statistics.
Here are some examples of problems which may require multivariate statistics:
- Can the risk of dying of cancer be related to the environmental conditions
of the investigated persons? In order to find an answer to this question,
one has to consider many factors, ranging from special chemical hazards
to eating habits or smoking.
- Is there a way to identify counterfeit money? If the counterfeiting is
badly done, a single variable will not be sufficient to identify forged
banknotes. A set of variables will be necessary (size, color depth, geometry,
- How is it possible to distinguish between different flavours of wine?
The flavour of wines is determined by many parameters such as the concentration
of various chemical substances, the temperature, the psychological conditions
when drinking the wine, etc.