|
In statistics, a spurious relationship (or, sometimes,
spurious correlation) is a mathematical relationship in which two occurrences have no logical connection, yet it may be
implied that they do, due to a certain third, unseen factor (referred to as a "lurking variable"). The spurious relationship
gives an impression of a worthy link between two groups that is invalid when objectively examined.
General example
An example of a spurious relationship can be delineated by a city's ice cream
sales. These sales are highest when the city's crime rate is highest. To allege that ice cream sales cause crime would be to
imply a spurious relationship between the two. In reality, a heat wave may have
caused both. The heat wave is an example of a hidden or unseen variable.
Statistics
The term is commonly used in statistics and in particular in experimental research techniques. Experimental research
attempts to understand and predict causal relationships (X -> Y). A causal relationship can be contaminated by spurious
variables (W -> X & Y), intervening variables (X -> W -> Y), and antecedent variables (W -> Y, X). Because of
this, it is safest to present the conclusions of experimental research in terms of correlation instead of causation.
See also
External links and references
|