Phi coefficient

In <a href="/facts/Statistics/DNPsKGYU">statistics</a>, the phi coefficient (or mean square contingency coefficient and denoted by φ or rφ) is a measure of association for two <a href="/facts/Binary_variables/PSFa5S2Q">binary variables</a>.
In <a href="/facts/Machine_learning/e0w0XJTu">machine learning</a>, it is known as the Matthews correlation coefficient (MCC) and used as a measure of the quality of binary (two-class) <a href="/facts/Binary_classification/MeYYAMwp">classifications</a>, introduced by biochemist <a href="/facts/Brian_Matthews_(biochemist)/GdSaK3IR">Brian W. Matthews</a> in 1975.
Introduced by <a href="/facts/Karl_Pearson/fXB7GT5Q">Karl Pearson</a>, and also known as the Yule phi coefficient from its introduction by <a href="/facts/Udny_Yule/3MHsP37s">Udny Yule</a> in 1912 this measure is similar to the <a href="/facts/Pearson_correlation_coefficient/Igf0xDPc">Pearson correlation coefficient</a> in its interpretation. 
In <a href="/facts/Meteorology/xblFr28q">meteorology</a>, the phi coefficient, or its square (the latter aligning with M. H. Doolittle's original proposition from 1885), is referred to as the Doolittle Skill Score or the Doolittle Measure of Association.

Phi coefficient open-in-new

Phi coefficient