Goodman and Kruskal's gamma

The estimate of gamma, G, depends on two quantities:

:*N_s, the number of pairs of cases ranked in the same order on both variables (number of concordant pairs),

:*N_d, the number of pairs of cases ranked in reversed order on both variables (number of reversed pairs),

where "ties" (cases where either of the two variables in the pair are equal) are dropped.

Then

:$G=\backslash frac\{N\_s-N\_d\}\{N\_s+N\_d\}\backslash \; .$

This statistic can be regarded as the maximum likelihood estimator for the theoretical quantity $\backslash gamma$, where

:$\backslash gamma=\backslash frac\{P\_s-P\_d\}\{P\_s+P\_d\}\backslash \; ,$

and where P_s and P_d are the probabilities that a randomly selected pair of observations will place in the same or opposite order respectively, when ranked by both variables.

Critical values for the gamma statistic are sometimes found by using an approximation, whereby a transformed value, t of the statistic is referred to Student t distribution, where{{Citation needed|date=August 2010}}

: $t\; \backslash approx\; G\; \backslash sqrt\{\; \backslash frac\{\; N\_s+N\_d\}\{n(1-G^2)\}\; \}\backslash \; ,$

and where n is the number of observations (not the number of pairs):

: $n\; \backslash ne\; N\_s+N\_d.\; \backslash ,$

A special case of Goodman and Kruskal's gamma is Yule's Q, also known as the Yule coefficient of association,{{cite journal

|title=On the methods of measuring association between two attributes

|first=G U. |last=Yule

|journal=Journal of the Royal Statistical Society

|volume=49 |issue=6 |year=1912 |pages=579–652

|doi=10.2307/2340126 |jstor=2340126

|url=https://zenodo.org/record/1449482}} which is specific to 2×2 matrices. Consider the following contingency table of events, where each value is a count of an event's frequency:

Yule's Q is given by:

:$Q=\backslash frac\{ad\; -\; bc\}\{ad\; +\; bc\}\backslash \; .$

Although computed in the same fashion as Goodman and Kruskal's gamma, it has a slightly broader interpretation because the distinction between nominal and ordinal scales becomes a matter of arbitrary labeling for dichotomous distinctions. Thus, whether Q is positive or negative depends merely on which pairings the analyst considers to be concordant, but is otherwise symmetric.

Q varies from −1 to +1. −1 reflects total negative association, +1 reflects perfect positive association and 0 reflects no association at all. The sign depends on which pairings the analyst initially considered to be concordant, but this choice does not affect the magnitude.

In term of the odds ratio OR, Yule's Q is given by

:$Q=\; \backslash frac\{\{OR\}-1\}\{\{OR\}+1\}\backslash \; .$

and so Yule's Q and Yule's Y are related by

:$Q\; =\; \backslash frac\{2Y\}\{1+Y^2\}\backslash \; ,$

:$Y\; =\; \backslash frac\{1-\backslash sqrt\{1-Q^2\}\}\{Q\}\backslash \; .$

• Kendall tau rank correlation coefficient
• Goodman and Kruskal's lambda
• Yule's Y, also known as the coefficient of colligation

{{Reflist}}

• Sheskin, D.J. (2007) The Handbook of Parametric and Nonparametric Statistical Procedures. Chapman & Hall/CRC, {{ISBN|9781584888147}}

{{Statistics}}

{{DEFAULTSORT:Gamma Test (Statistics)}}

Category:Rankings

Category:Statistical tests

Category:Summary statistics for contingency tables