Kendall's W

Kendall's W (also known as Kendall's coefficient of concordance) is a non-parametric statistic. It is a normalization of the statistic of the Friedman test, and can be used for assessing agreement among raters. Kendall's W ranges from 0 (no agreement) to 1 (complete agreement).

Suppose, for instance, that a number of people have been asked to rank a list of political concerns, from most important to least important. Kendall's W can be calculated from these data. If the test statistic W is 1, then all the survey respondents have been unanimous, and each respondent has assigned the same order to the list of concerns. If W is 0, then there is no overall trend of agreement among the respondents, and their responses may be regarded as essentially random. Intermediate values of W indicate a greater or lesser degree of unanimity among the various responses.

While tests using the standard Pearson correlation coefficient assume normally distributed values and compare two sequences of outcomes at a time, Kendall's W makes no assumptions regarding the nature of the probability distribution and can handle any number of distinct outcomes.

Definition

Suppose that object i is given the rank ri,j by judge number j, where there are in total n objects and m judges. Then the total rank given to object i is

${\displaystyle R_{i}=\sum _{j=1}^{m}r_{i,j},}$

and the mean value of these total ranks is

${\displaystyle {\bar {R}}={\frac {1}{n}}\sum _{i=1}^{n}R_{i}.}$

The sum of squared deviations, S, is defined as

${\displaystyle S=\sum _{i=1}^{n}(R_{i}-{\bar {R}})^{2},}$

and then Kendall's W is defined as[1]

${\displaystyle W={\frac {12S}{m^{2}(n^{3}-n)}}.}$

If the test statistic W is 1, then all the judges or survey respondents have been unanimous, and each judge or respondent has assigned the same order to the list of objects or concerns. If W is 0, then there is no overall trend of agreement among the respondents, and their responses may be regarded as essentially random. Intermediate values of W indicate a greater or lesser degree of unanimity among the various judges or respondents.

Kendall and Gibbons (1990) also show W is linearly related to the mean value of the Spearman's rank correlation coefficients between all ${\displaystyle m \choose {2}}$ possible pairs of rankings between judges

${\displaystyle {\bar {r}}_{s}={\frac {mW-1}{m-1}}}$

Incomplete Blocks

When the judges evaluate only some subset of the n objects, and when the correspondent block design is a (n, m, r, p, λ)-design (note the different notation). In other words, when

1. each judge ranks the same number p of objects for some ${\displaystyle p,
2. every object is ranked exactly the same total number r of times,
3. and each pair of objects is presented together to some judge a total of exactly λ times, ${\displaystyle \lambda \geq 1}$, a constant for all pairs.

Then Kendall's W is defined as [2]

${\displaystyle W={\frac {12\sum _{i=1}^{n}(R_{i}^{2})-3r^{2}n\left(p+1\right)^{2}}{\lambda ^{2}n(n^{2}-1)}}.}$

If ${\displaystyle p=n}$ and ${\displaystyle \lambda =r=m}$ so that each judge ranks all n objects, the formula above is equivalent to the original one.

Correction for Ties

When tied values occur, they are each given the average of the ranks that would have been given had no ties occurred. For example, the data set {80,76,34,80,73,80} has values of 80 tied for 4th, 5th, and 6th place; since the mean of {4,5,6} = 5, ranks would be assigned to the raw data values as follows: {5,3,1,5,2,5}.

The effect of ties is to reduce the value of W; however, this effect is small unless there are a large number of ties. To correct for ties, assign ranks to tied values as above and compute the correction factors

${\displaystyle T_{j}=\sum _{i=1}^{g_{j}}(t_{i}^{3}-t_{i}),}$

where ti is the number of tied ranks in the ith group of tied ranks, (where a group is a set of values having constant (tied) rank,) and gj is the number of groups of ties in the set of ranks (ranging from 1 to n) for judge j. Thus, Tj is the correction factor required for the set of ranks for judge j, i.e. the jth set of ranks. Note that if there are no tied ranks for judge j, Tj equals 0.

With the correction for ties, the formula for W becomes

${\displaystyle W={\frac {12\sum _{i=1}^{n}(R_{i}^{2})-3m^{2}n(n+1)^{2}}{m^{2}n(n^{2}-1)-m\sum _{j=1}^{m}(T_{j})}},}$

where Ri is the sum of the ranks for object i, and ${\displaystyle \sum _{j=1}^{m}(T_{j})}$ is the sum of the values of Tj over all m sets of ranks.[3]

Significance Tests

In the case of complete ranks, a commonly used significance test for W against a null hypothesis of no agreement (i.e. random rankings) is given by Kendall and Gibbons (1990)[4]

${\displaystyle \chi ^{2}=m(n-1)W}$

Where the test statistic takes a chi-squared distribution with ${\displaystyle df=n-1}$ degrees of freedom.

In the case of incomplete rankings (see above), this becomes

${\displaystyle \chi ^{2}={\frac {\lambda (n^{2}-1)}{k+1}}W}$

Where again, there are ${\displaystyle df=n-1}$ degrees of freedom.

Legendre[5] compared via simulation the power of the chi-square and permutation testing approaches to determining significance for Kendall's W. Results indicated the chi-square method was overly conservative compared to a permutation test when ${\displaystyle m<20}$. Marozzi[6] extended this by also considering the F test, as proposed in the original publication introducing the W statistic by Kendall & Babington Smith (1939):

${\displaystyle F={\frac {W(m-1)}{1-W}}}$

Where the test statistic follows an F distribution with ${\displaystyle v_{1}=n-1-(2/m)}$ and ${\displaystyle v_{2}=(m-1)v_{1}}$ degrees of freedom. Marozzi found the F test performs approximately as well as the permutation test method, and may be preferred to when ${\displaystyle m}$ is small, as it is computationally simpler.

Notes

1. Dodge (2003): see "concordance, coefficient of"
2. Gibbons & Chakraborti (2003)
3. Siegel & Castellan (1988, p. 266)
4. Kendall, Maurice G. (Maurice George), 1907-1983. (1990). Rank correlation methods. Gibbons, Jean Dickinson, 1938- (5th ed.). London: E. Arnold. ISBN 0195208374. OCLC 21195423.CS1 maint: multiple names: authors list (link)
5. Legendre (2005)
6. Marozzi, Marco (2014). "Testing for concordance between several criteria". Journal of Statistical Computation and Simulation. 84 (9): 1843–1850. doi:10.1080/00949655.2013.766189.

References

• Kendall, M. G.; Babington Smith, B. (Sep 1939). "The Problem of m Rankings". The Annals of Mathematical Statistics. 10 (3): 275–287. doi:10.1214/aoms/1177732186. JSTOR 2235668.
• Kendall, M. G., & Gibbons, J. D. (1990). Rank correlation methods. New York, NY : Oxford University Press.
• Corder, G.W., Foreman, D.I. (2009). Nonparametric Statistics for Non-Statisticians: A Step-by-Step Approach Wiley, ISBN 978-0-470-45461-9
• Dodge, Y. (2003). The Oxford Dictionary of Statistical Terms, OUP. ISBN 0-19-920613-9
• Legendre, P (2005) Species Associations: The Kendall Coefficient of Concordance Revisited. Journal of Agricultural, Biological and Environmental Statistics, 10(2), 226245.
• Siegel, Sidney; Castellan, N. John, Jr. (1988). Nonparametric Statistics for the Behavioral Sciences (2nd ed.). New York: McGraw-Hill. p. 266. ISBN 978-0-07-057357-4.
• Gibbons, Jean Dickinson; Chakraborti, Subhabrata (2003). Nonparametric Statistical Inference (4th ed.). New York: Marcel Dekker. pp. 476–482. ISBN 978-0-8247-4052-8.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.