# On Similarity Coefficients for 2×2 Tables and Correction for Chance

- 613 Downloads
- 48 Citations

## Abstract

This paper studies correction for chance in coefficients that are linear functions of the observed proportion of agreement. The paper unifies and extends various results on correction for chance in the literature. A specific class of coefficients is used to illustrate the results derived in this paper. Coefficients in this class, e.g. the simple matching coefficient and the Dice/Sørenson coefficient, become equivalent after correction for chance, irrespective of what expectation is used. The coefficients become either Cohen’s kappa, Scott’s pi, Mak’s rho, Goodman and Kruskal’s lambda, or Hamann’s eta, depending on what expectation is considered appropriate. Both a multicategorical generalization and a multivariate generalization are discussed.

## Keywords

indices of association resemblance measures correction for chance Cohen’s kappa Scott’s pi Mak’s rho Goodman and Kruskal’s lambda Hamann’s eta simple matching coefficient Dice/Sørenson coefficient## 1 1. Introduction

*a, b, c*, and

*d*, presented in Table 1. Instead of probabilities, Table 1 may also be defined on counts or frequencies; probabilities are used here for notational convenience.

Bivariate proportions table for binary variables.

Variable two | ||||
---|---|---|---|---|

Proportions | Value 1 | Value 2 | Total | |

Variable one | Value 1 | | | |

Value 2 | | | | |

Total | | | 1 |

The data in Table 1 may be obtained from a 2×2 reliability study: *a, b, c*, and *d* are observed proportions resulting from classifying *m* persons using a dichotomous response (Fleiss, 1975; Bloch & Kraemer, 1989; Blackman & Koval, 1993). In cluster analysis, Table 1 may be the result of comparing partitions from two clustering methods: *a* is the proportion of object pairs that were placed in the same cluster according to both clustering methods, *b* (*c*) is the proportion of pairs that were placed in the same cluster according to one method but not according to the other, and *d* is the proportion of pairs that were not in the same cluster according to either of the methods (Albatineh, Niewiadomska-Bugaj & Mihalko, 2006; Steinley, 2004).

*S*. Table 2 presents ten similarity coefficients that will be used to illustrate the results in this paper. Following Sokal and Sneath (1963, p. 128) and Albatineh et al. (2006), the convention is adopted of calling a coefficient by its originator or the first we know to propose it. The coefficients in Table 2 may be considered both as population parameters as well as sample statistics; in this paper we use the latter. Some of these coefficients have been proposed in different domains of data analysis, but turn out to be equivalent after recoding.

Ten 2 × 2 similarity coefficients.

Symbol | Formula | Source |
---|---|---|

S | a + d | Sokal and Michener (1958), Rand (1971), Brennan and Light (1974) |

S | a – b –c +d | |

S | \({{2a} \over {{p_1} + {p_2}}}\) | Czekanowski (1932), Dice (1945), Sørenson (1948), Nei and Li (1979) |

S | \({{2a - b - c} \over {2a + b + c}}\) | |

S | \({{2d - b - c} \over {b + c + 2d}}\) | |

S | \({{2\min (a,d) - b - c} \over {2\min (a,d) + b + c}}\) | |

S | \({{2d} \over {{q_1} + {q_2}}}\) | No source |

S | \({a \over {{p_1} + {p_2}}} + {d \over {{q_1} + {q_2}}}\) | |

S | \({{4ad - {{(b + c)}^2}} \over {({p_1} + {p_2})({q_1} + {q_2})}}\) | |

S | \({{2(ad - bc)} \over {{p_1}{q_2} + {p_2}{q_1}}}\) |

*S*

_{Cohen}satisfies this requirement; coefficients

*S*

_{SM}and

*S*

_{Cze}do not. If a coefficient does not have zero value under statistical independence, it may be corrected for agreement due to chance (Fleiss, 1975; Zegers, 1986; Krippendorff, 1987; Albatineh et al., 2006). After correction for chance, a similarity coefficient

*S*has a form

*E*(

*S*) is conditional upon fixed marginal proportions in Table 1. Various authors have noted that some coefficients become equivalent after correction (1). For example, Fleiss (1975) and Zegers (1986) showed that

*S*

_{SM}and

*S*

_{Cze}become

*S*

_{Cohen}after correction (1). In addition, Zegers (1986) showed that

*S*

_{Ham}, and Fleiss (1975) showed that

*S*

_{GK1}and

*S*

_{RG}, become

*S*

_{Cohen}after correction for chance.

Albatineh et al. (2006) studied correction (1) for a specific family of coefficients. They showed that coefficients may coincide after correction for chance, irrespective of what expectation is used. The main result of their paper is Proposition 1 in Section 3. In this paper, we continue the general approach by Albatineh et al. (2006) and present several new results with respect to correction (1).

The paper is organized as follows. Similar to Albatineh et al. (2006) correction (1) is studied for a general family of coefficients. This family of coefficients, of a form *S* = *λ* + *μ*(*a + d)*, is introduced in the next section. Section 3 is used to present the main results. In addition to a powerful result by Albatineh et al. (2006), Section 3 considers two additional functions. If coefficients are related by one of these functions, they become equivalent after correction (1), irrespective of what expectation *E*(*S*) is used.

Additional results may be obtained by considering different expectations *E*(*S*). The specific results in Section 4 unify and extend the findings for individual coefficients in Fleiss (1975) and Zegers (1986). Section 5 discusses corrected coefficients and some of their properties. Also in Section 5, we discuss a generalization of an inequality in Blackman and Koval (1993) for Cohen’s kappa and Scott’s pi. Sections 6 and 7 discuss two natural generalizations of the results in Sections 3 to 5. Section 6 presents a multicategorical extension; Section 7 describes a family of multivariate coefficients. Section 8 contains the discussion.

## 2 2. A Family of Coefficients

Consider a family *L* of coefficients of a form *S* = *λ*+*μ*(*a* +*d*), where proportions *a* and *d* are defined in Table 1, and where *λ* and *μ*, different for each coefficient, depend on the marginal probabilities of Table 1. Since *S* _{SM} = *a* + *d*, all members in *L* family are linear transformations of *S* _{SM}, the observed proportion of agreement, given the marginal probabilities. Clearly, *S* _{SM} is in *L* family. Furthermore, all ten coefficients in Table 2 are in *L* family.

*Example 1*. Coefficient

*S*

_{Cze}was independently proposed by Czekanowski (1932), Dice (1945), and Sørenson (1948). The coefficient is often attributed to Dice (1945), and it was also derived by Nei and Li (1979). Bray (1956) noted that coefficient

*S*

_{Cze}could be found in Gleason (1920). Coefficient

*S*

_{Cze}

*S*

_{Cze}can be written in a form

*S*

_{Cze}=

*λ*+

*μ*(

*a*+

*d*), where

*Example 2*. Scott (1955) proposed a measure of interrater-reliability denoted by the symbol pi. For two dichotomized variables Scott’s pi

*S*

_{Scott}, we have

*S*

_{Scott}

*S*

_{Scott}=

*λ*+

*μ*(

*a*+

*d*) where

*Example 3*. The best-known index for interrater-reliability is the kappa-statistic proposed by Cohen (1960). Since

*S*

_{Cohen}can be written in a form

*S*

_{Cohen}=

*λ*+

*μ*(

*a*+

*d*), where

Since \(a = {p_2} - {q_1} + d\), probabilities *a* and *d* are also linear in (*a* + *d*). Linear in (*a* + *d*) is therefore equivalent to linear in *a* and linear in *d*. Furthermore, Albatineh et al. (2006) studied coefficients that are linear in ΣΣ*n* _{ ij } ^{2} , where *n* _{ ij } is the number of data points placed in cluster *i* according to the first clustering method and in cluster *j* according to the second clustering method. Because \(ma = (\sum {\sum {n_{ij}^2 - m)/2} } \), linear in ΣΣ*n* _{ ij } ^{2} is equivalent to linear in *a* and equivalent to linear in (*a* + *d*).

*L*family can be found in Albatineh et al. (2006) and Baulieu (1989).

## 3 3. Main Results

Albatineh et al. (2006) showed that correction (1) is relatively simple for coefficients that belong to *L* family. Two members in *L* family become equivalent after correction for chance agreement if they have the same ratio (2).

**Proposition 1**(Albatineh et al., 2006, p. 309).

*Two members in L family become identical after correction*(1)

*if they have the same ratio*

*Proof*: E (

*S*) =

*E*[

*λ*+

*μ*(

*a*+

*d*)] =

*λ*+

*μE*(

*a*+

*d*) and consequently the

*CS*becomes

Thus, the value of a similarity coefficient after correction for chance depends on ratio (2), where *λ* and *μ* characterize the particular measure within *L* family.

Corollary 1 below extends Corollary 4.2(i) in Albatineh et al. (2006) from three measures (*S* _{SM}, *S* _{Ham}, and *S* _{Cze}) to the ten coefficients in Table 2. The coefficients in Table 2 coincide after correction (1), irrespective of what expectation *E*(*S*) is used.

**Corollary 1**. *Coefficients* *S* _{SM}, *S* _{Ham}, *S* _{Cze}, *S* _{GK1}, *S* _{GK2}, *S* _{GK3}, *S* _{NS}, *S* _{RG}, *S* _{Scott}, *and* *S* _{Cohen} *become equivalent after correction* (1).

*Proof:*By Proposition 1 it suffices to inspect ratio (2). Using the formulas of

*λ*and

*μ*corresponding to each coefficient we obtain the ratio (2)

*S*

_{Scott}and

*S*

_{Cohen}are presented. Using the formulas for

*λ*and

*μ*from Example 2 we obtain the ratio (2)

*λ*and

*μ*from Example 3 we obtain the ratio (2)

Note that (1 − *λ*)/*μ* = 1 for all coefficients in Table 2 (ratio (4)). The value 1 is also the maximum value regardless of the marginal probabilities of these similarity coefficients.

*S*

_{2}= 2

*S*

_{1}− 1 is in

*L*family if and only if

*S*

_{1}is in

*L*family, and if

*S*

_{1}and

*S*

_{2}are in

*L*family, then

*S*

_{3}= (

*S*

_{1}+

*S*

_{2})/2 is in

*L*family. Two coefficients

*S*

_{1}and

*S*

_{2}that are related by

*S*

_{2}= 2

*S*

_{1}− 1 become equivalent after correction for chance.

**Proposition 2**. *Let* *S* _{1} *be a member in L family*. *S* _{1} *and* *S* _{2} = 2*S* _{1} − 1 *become identical after correction* (1).

*Proof:*

*S*

_{2}= 2

*λ*+ 2

*μ*(

*a*+

*d*) − 1 and

*E*(

*S*

_{2}) = 2

*λ*− 1 + 2

*μE*(

*a*+

*d*). Consequently the

*CS*

_{2}becomes

*Example 4*. Various similarity coefficients have a relationship *S* _{2} = 2*S* _{1} − 1. Examples from Table 2 are *S* _{Ham} = 2*S* _{SM}−1, *S* _{GK1} = 2*S* _{Cze} − 1, and *S* _{GK2} = 2*S* _{NS} − 1. Due to either Proposition 1 with Corollary 1 or Proposition 2, these coefficients coincide after correction (1).

**Theorem 1**.

*Let*

*S*

_{ i }

*for i*= 1, 2, …,

*n be members in L family that become identical after correction*(1).

*Then*

*S*

_{ i }

*for i*= 1, 2, …,

*n and the arithmetic mean*

*become equivalent after correction*(1).

*Remark*. The original proof has been simplified with the help of an anonymous referee.

*Proof:*

*y*equals ratio

*x*. We have

This completes the proof.

*Example 5*. Coefficient

*S*

_{Cze}and

*S*

_{NS}. Due to either Proposition 1 with Corollary 1 or Theorem 1, these three coefficients become equivalent after correction (1).

## 4 4. Specific Results

*E*(

*a*+

*d*) is unspecified, coefficient (7) is a general corrected coefficient. Specific cases of (7) may be obtained by specifying

*E*(

*a*+

*d*) in (7).

Different opinions have been stated on what the appropriate expectations are for the 2 × 2 contingency table. Detailed discussions on the various ways of regarding data as the product of chance can be found in Krippendorff (1987), Mak (1988), Bloch and Kraemer (1989), and Pearson (1947). In cluster analysis it is general consensus that the popular coefficient *S* _{SM}, called the Rand index, should be corrected for agreement due to chance (Morey & Agresti, 1984; Hubert & Arabie, 1985), although there is some debate on what expectation is appropriate (Hubert & Arabie, 1985; Steinley, 2004; Albatineh et al., 2006). We consider five examples of *E*(*a* + *d*).

*Example 6a*. Suppose it is assumed that the frequency distribution underlying the two variables in Table 1 is the same for both variables (Scott, 1955; Krippendorff, 1987, p. 113). Coefficients used in this case are sometimes referred to as agreement indices. The common parameter

*p*must be either known or it must be estimated from

*p*

_{1}and

*p*

_{2}. Different functions may be used. For example, Scott (1955) and Krippendorff (1987) used the arithmetic mean

*m*denote the number of elements of the binary variables. Mak (1988) proposed the expectation

*Example 6b*. Instead of a single distribution function, it may be assumed that the data are a product of chance concerning two different frequency distributions, each with its own parameter (Cohen, 1960; Krippendorff, 1987). Coefficients used in this case are sometimes referred to as association indices. The expectation of an entry in Table 1 under statistical independence is defined by the product of the marginal probabilities. We have

*E*(

*a*+

*d*)

_{Cohen}can be obtained by considering all permutations of the observations of one of the two variables, while preserving the order of the observations of the other variable. For each permutation the value of (

*a*+

*d*) can be determined. The arithmetic mean of these values is

*p*

_{1}

*p*

_{2}+

*q*

_{1}

*q*

_{2}.

*Example 6c*. A third possibility is that there are no relevant underlying continua. For this case two forms of

*E*(

*a*+

*d*) may be found in the literature. Note that

*a*and

*d*in Table 1 may be interpreted as the proportions of positive and negative matches, whereas

*b*and

*c*are the proportions of nonmatching observations. Goodman and Kruskal (1954, p. 757) used expectation

*E*(

*a*+

*d*)

_{GK}focuses on the largest group of matching observations. According to Krippendorff (1987, p. 114) an equity coefficient is characterized by expectation

In the case of association (Example 6b) the observations are regarded as ordered pairs. In the case of agreement (Example 6a) the observations are considered as pairs without regard for their order; a mismatch is a mismatch regardless of the kind. In the case of equity one only distinguishes between matching and nonmatching observations (cf. Krippendorff, 1987).

*E*(

*a*+

*d*) from Examples 6a to 6c is used, the coefficients in Table 2 become, after correction for chance, either Scott’s (1955) pi (

*S*

_{Scott}), Cohen’s (1960) kappa (

*S*

_{Cohen}), Goodman and Kruskal’s (1954) lambda (

*S*

_{GK3}), Hamann’s (1961) eta (

*S*

_{Ham}), or Mak’s (1988) rho. The latter coefficient can be written as

*m*is the length of the binary variables.

**Theorem 2**.

*Let S be a member in L family for which ratio*(4)

*holds. If the appropriate expectation is*

- (i)
*E*(*a*+*d*)_{Scott},*then S becomes**S*_{Scott}, - (ii)
*E*(*a*+*d*)_{Mak},*then S becomes**S*_{Mak}, - (iii)
*E*(*a*+*d*)_{Cohen},*then S becomes**S*_{Cohen}, - (iv)
*E*(*a*+*d*)_{GK},*then S becomes**S*_{GK3}, - (v)
*E*(*a*+*d*)_{Kripp},*then S becomes**S*_{Ham},*after correction*(1).

*Proof:*(i): Using

*E*(

*a*+

*d*)

_{Scott}in (7) we obtain an index of which the numerator equals

*E*(

*a*+

*d*)

_{Mak}in (7) and multiplying the result by 2(

*m*

^{−1}) we obtain an index of which the numerator equals

Dividing (13) by (11) we obtain coefficient *S* _{Mak}.

*E*(

*a*+

*d*)

_{Cohen}in (7) we obtain

*E*(

*a*+

*d*)

_{GK}in (7) we obtain

## 5 5. Corrected Coefficients

The coefficients in Table 2 become either *S* _{Scott}, *S* _{Mak}, *S* _{Cohen}, *S* _{GK3}, or *S* _{Ham}, depending on what expectation *E*(*a*+*d*) is used. Note that corrected coefficients *S* _{Scott}, *S* _{Cohen}, *S* _{GK3}, and *S* _{Ham} belong to the class of resemblance measures that is considered in Corollary 1 and Theorem 2. This suggests that corrected coefficients may have some interesting properties, which are the topic of this section. If *E*(*S*) in (1) depends on the marginal probabilities in Table 1, then *CS* in (1) belongs to *L* family.

**Proposition 3**. *Let* *E*(*S*) *in* (1) *depend on the marginal probabilities. If S is in L family, then CS in* (1) *is in L family*.

*Proof:*Expectation

*E*(

*S*) =

*E*[

*λ*1 +

*μ*

_{1}(

*a*+

*d*)] is a function of the marginal probabilities. Thus

*E*(

*a*+

*d*),

*λ*, and

*μ*in (3) are functions of the marginal proportions. Equation (3) can therefore be written in a form

*λ*

_{2}+

*μ*

_{2}(

*a*+

*d*) where

Examples of corrected coefficients that are in *L* family are *S* _{Scott}, *S* _{Cohen}, *S* _{GK3}, and *S* _{Ham}. These coefficients may be considered as corrected coefficients as well as ordinary coefficients that may be corrected for agreement due to chance. For example, *S* _{Scott}, *S* _{GK3}, and *S* _{Ham} (and *S* _{Cohen}) become *S* _{Cohen} after correction (1) if expectation *E*(*a* + *d*)_{Cohen} is used. Coefficient *S* _{Mak} cannot be written in a form *λ*+*μ*(*a* + *d*), and does therefore not belong to *L* family.

*S*in

*L*family is corrected twice, using two different expectations,

*E*(

*a*+

*d*) and

*E*(

*a*+

*d*)*. Let the corrected coefficients be given by

*μ*

^{−1}(1 −

*λ*) corresponding to coefficient

*S*, is the same in both

*CS*and

*CS**. The problem is then as follows: if

*E*(

*a*+

*d*) ≥

*E*(

*a*+

*d*)*, how are

*CS*and

*CS** related? It turns out that

*CS*is a decreasing function of

*E*(

*a*+

*d*). Proposition 4 is limited to coefficients in

*L*family of which the maximum value is 1, that is

*S*

_{Mak}satisfy this condition.

**Proposition 4**. *CS is a decreasing function of E*(*a* + *d*).

*Proof: CS*≤

*CS** if and only if

*λ*+

*μ*(

*a*+

*d*) ≤ 1 completes the proof.

*S*=

*λ*+

*μ*(

*a*+

*d*) be in

*L*family and let

*E*(

*a*+

*d*)

_{Name}. Using specific expectations

*E*(

*a*+

*d*) in combination with Proposition 4, we obtain the following result.

**Theorem 3**. *It holds that* \(C{S_{{\rm{GK}}}}\mathop \le \limits^{({\rm{i}})} C{S_{{\rm<Emphasis Type="SmallCaps">ott</Emphasis>}}}\mathop \le \limits^{({\rm{ii}})} C{S_{{\rm{Cohen}}}}\).

*Proof:*(i): Due to Proposition 4, it must be shown that

*E*(

*a*+

*d*)

_{GK}≥

*E*(

*a*+

*d*)

_{Scott}. Suppose

*(p*

_{1}+

*p*

_{2}) ≥

*(q*

_{1}+

*q*

_{2}). We have

*E*(

*a*+

*d*)

_{Scott}≥

*E*(

*a*+

*d*)

_{Cohen}. We have

Blackman and Koval (1993, p. 216) derived the inequality *S* _{Scott} ≤ *S* _{Cohen}. Note that this inequality follows from the more general result Theorem 3 by using a coefficient *S* for which (4) holds (all coefficients in Table 2).

## 6 6. Multicategorical Generalization

*m*people among a set of

*k*mutually exclusive categories. Let

**N**be a contingency table with entries

*n*

_{ ij }, where

*n*

_{ ij }indicates the number of persons placed in category

*i*by the first psychologist and in category

*j*by the second psychologist. Furthermore, let

*n*

_{ i+}and

*n*

_{+j }denote the marginal counts (row and column totals) of

**N**. Moreover, suppose that the categories of both variables are in the same order, so that the diagonal elements

*n*

_{ ii }reflect the number of people put in the same category by the psychologists. If the variables are dichotomized,

*m*

^{t-1}

**N**equals Table 1. A straightforward measure of similarity is the observed proportion of agreement given by

*S*=

*P*in (1) we obtain

Goodman and Kruskal (1954), Scott (1955), and Cohen (1960) proposed measures that incorporate correction for chance agreement of a form (18). The different expectations *E*(*P*) are defined as follows.

No underlying continua: \(E{(P)_{{\rm{GK}}}} = \max _i^k\left( {{{{n_{i + }} + {n_{ + i}}} \over {2m}}} \right)\).

One frequency distribution: \(E{(P)_{{\rm<Emphasis Type="SmallCaps">ott</Emphasis>}}} = \sum\limits_{i = 1}^k {{{\left( {{{{n_{i + }} + {n_{ + i}}} \over {2m}}} \right)}^2}} \).

Two frequency distributions: \(E{(P)_{{\rm{Cohen}}}} = {1 \over {{m^2}}}\sum\limits_{i = 1}^k {{n_{i + }}{n_{ + i}}} \).

Note that *P* is a natural extension of *S* _{SM} = *a*+*d* to nominal variables. Family *L* can be extended to coefficients of a form *S* = *λ*+*μP*, where *λ* and *μ*, unique for each coefficient, depend on the marginal probabilities of contingency table **N**. All results for the 2 × 2 case naturally generalize to coefficients of a form *S* = *λ* + *μP*. Coefficient *P* and the multicategorical versions of *S* _{GK3}, *S* _{Scott}, and *S* _{Cohen} that are obtained by using expectations *E*(*P*)_{GK}, *E*(*P*)_{Scott}, and *E*(*P*)_{Cohen} in (18), belong to *L* family (have a form *S* = *λ*+*μP*; note Proposition 3). Furthermore, it is not difficult to show that ratio (4) holds for multicategorical coefficients *P*, *S* _{GK3}, *S* _{Scott}, and *S* _{Cohen}. In this section only the generalization of Proposition 1, the powerful result by Albatineh et al. (2006), is presented.

**Proposition 1b**. *Two members in L family become identical after correction* (1) *if they have the same ratio μ* ^{−1}(1 −*λ*).

*Proof: E*(

*S*) =

*E*(

*λ*+

*μP*) =

*λ*+

*μE*(

*P*) and consequently the corrected coefficient becomes

## 7 7. Multivariate Generalization

Multivariate coefficients may be used to determine the degree of agreement among three or more raters in psychological assessment, or to compare partitions from three different cluster algorithms. Multivariate versions of Cohen’s kappa (*S* _{Cohen}) can for instance be found in Fleiss (1971), Light (1971), Popping (1983), and Heuvelmans and Sanders (1993).

*k*raters. Similar to Table 1, we may construct

*k*(

*k*−1)/2 bivariate 2 × 2 tables: each proportion table compares two variables

*i*and

*j*. Let

*a*

_{ ij }denote the proportion of people that possess a characteristic according to both psychologists

*i*and

*j*, let

*d*

_{ ij }denote the proportion of people that lack the characteristic according to both psychologists, and let

*p*

_{ i }denote the proportion of people that possess the characteristic according to psychologist

*i*. Family

*L*may be extended to a multivariate family

*L*

^{(k)}of coefficients of a form

*λ*

^{(k)}and

*μ*

^{(k)}depend on the marginal probabilities of the 2 × 2 tables only. Note that

*S*

_{SM}. Quantity 2/

*k*(

*k*− 1) is used to ensure that the value of coefficient

*S*

_{SM}

^{(k)}lies between 0 and 1. Let us present some other examples of coefficients that belong to

*L*

^{(k)}family.

*Example 1b*. A three-way formulation of

*S*

_{Cze}= 2

_{ a }

_{12}/(

*p*

_{1}+

*p*

_{2}) (Example 1), such that the coefficient is a linear transformation of

*S*

_{SM}

^{(3)}, is given by

*S*

_{Cze}is given by

*S*

_{Cze}

^{(k)}can be written in a form

*S*

_{Cze}

^{(k)}=

*λ*

^{(k)}+

*μ*

^{(k)}

*S*

_{SM}

^{(k)}, where

*λ*

^{(k)}and

*μ*

^{(k)}naturally extend

*λ*and

*μ*corresponding to

*S*

_{Cze}in Example 1.

*Example 3b*. Popping (1983) and Heuvelmans and Sanders (1993) describe the same multivariate extension of Cohen’s (1960) kappa. For

*k*dichotomized variables, the multivariate kappa is given by

*S*

_{Cohen}

^{(k)}can be written in a form

*S*

_{Cohen}

^{(k)}=

*λ*

^{(k)}+

*μ*

^{(k)}

*S*

_{SM}

^{(k)}, where

Using the heuristics in Examples 1b and 3b one may obtain multivariate formulations of other coefficients in Table 2. The remainder of the section is used to present generalizations of Proposition 1, the main result in Albatineh et al. (2006), and Corollary 1. Both extensions show that family *L* ^{(k)} naturally generalizes family *L*, with respect to correction (1), to multivariate coefficients.

**Proposition 1c**.

*Two members in L*

^{(k)}

*family become identical after correction*(1)

*if they have the same ratio*

*Proof:*

**Corollary 1b**. *Coefficients* {tiS} _{SM} ^{(k)} , *S* _{Cze} ^{(k)} , *and* *S* _{Cohen} ^{(k)} *become equivalent after correction* (1).

*Proof:*Using the formulas of

*λ*

^{(k)}and

*μ*

^{(k)}corresponding to each coefficient, we obtain the ratio (19)

*S*

_{SM}

^{(k)}and

*S*

_{Cze}

^{(k)}is straightforward.

*λ*

^{(k)}and

*μ*

^{(k)}from Example 3b, we obtain the ratio (19)

## 8 8. Discussion

The inspiration for this work came from the paper by Albatineh et al. (2006), who studied correction for chance for similarity coefficients from a general perspective. For a specific family of coefficients they showed that coefficients may coincide after correction for chance, irrespective of what expectation is used.

*S*=

*λ*+

*μx*, for which we have

*λ*and

*μ*depend on the marginals of the table corresponding to the data type. Property (20) is central in Proposition 1, the main result in Albatineh et al. (2006), and several other results in this paper. The general coefficients for metric scales in Zegers and Ten Berge (1985), for instance, satisfy condition (20).

## Notes

### Open Access

This article is distributed under the terms of the Creative Commons Attribution Noncommercial License which permits any noncommercial use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.

## References

- Albatineh, A.N., Niewiadomska-Bugaj, M., & Mihalko, D. (2006). On similarity indices and correction for chance agreement.
*Journal of Classification*,*23*, 301–313. CrossRefGoogle Scholar - Baulieu, F.B. (1989). A classification of presence/absence based dissimilarity coefficients.
*Journal of Classification*,*6*, 233–246. CrossRefGoogle Scholar - Blackman, N.J.-M., & Koval, J.J. (1993). Estimating rater agreement in 2×2 tables: Correction for chance and intraclass correlation.
*Applied Psychological Measurement*,*17*, 211–223. CrossRefGoogle Scholar - Bloch, D.A., & Kraemer, H.C. (1989). 2×2 Kappa coefficients: Measures of agreement or association.
*Biometrics*,*45*, 269–287. CrossRefPubMedGoogle Scholar - Bray, J.R. (1956). A study of mutual occurrence of plant species.
*Ecology*,*37*, 21–28. CrossRefGoogle Scholar - Brennan, R.L., & Light, R.J. (1974). Measuring agreement when two observers classify people into categories not defined in advance.
*British Journal of Mathematical and Statistical Psychology*,*27*, 154–163. Google Scholar - Cohen, J. (1960). A coefficient of agreement for nominal scales.
*Educational and Psychological Measurement*,*20*, 37–46. CrossRefGoogle Scholar - Czekanowski, J. (1932). Coefficient of racial likeliness und Durchschnittliche Differenz.
*Anothropologidcher*,*14*, 227–249. Google Scholar - Dice, L.R. (1945). Measures of the amount of ecologic association between species.
*Ecology*,*26*, 297–302. CrossRefGoogle Scholar - Fleiss, J.L. (1971). Measuring nominal scale agreement among many raters.
*Psychological Bulletin*,*76*, 378–382. CrossRefGoogle Scholar - Fleiss, J.L. (1975). Measuring agreement between two judges on the presence or absence of a trait.
*Biometrics*,*31*, 651–659. CrossRefPubMedGoogle Scholar - Gleason, H.A. (1920). Some applications of the quadrat method.
*Bulletin of the Torrey Botanical Club*,*47*, 21–33. CrossRefGoogle Scholar - Goodman, L.A., & Kruskal, W.H. (1954). Measures of association for cross classifications.
*Journal of the American Statistical Association*,*49*, 732–764. CrossRefGoogle Scholar - Gower, J.C., & Legendre, P. (1986). Metric and Euclidean properties of dissimilarity coefficients.
*Journal of Classification*,*3*, 5–48. CrossRefGoogle Scholar - Hamann, U. (1961). Merkmalsbestand und Verwandtschaftsbeziehungen der Farinose. Ein Betrag zum System der Monokotyledonen.
*Willdenowia*,*2*, 639–768. Google Scholar - Heuvelmans, A.P.J.M., & Sanders, P.F. (1993). Beoordelaarsovereenstemming. In T.J.H.M. Eggen & P.F. Sanders (Eds.),
*Psychometrie in de praktijk*(pp. 443–470). Arnhem: Cito Instituut voor Toetsontwikkeling. Google Scholar - Hubálek, Z. (1982). Coefficients of association and similarity based on binary (presence-absence) data: An evaluation.
*Biological Reviews*,*57*, 669–689. CrossRefGoogle Scholar - Hubert, L.J. (1977). Nominal scale response agreement as a generalized correlation.
*British Journal of Mathematical and Statistical Psychology*,*30*, 98–103. Google Scholar - Hubert, L.J., & Arabie, P. (1985). Comparing partitions.
*Journal of Classification*,*2*, 193–218. CrossRefGoogle Scholar - Jaccard, P. (1912). The distribution of the flora in the Alpine zone.
*The New Phytologist*,*11*, 37–50. CrossRefGoogle Scholar - Krippendorff, K. (1987). Association, agreement, and equity.
*Quality and Quantity*,*21*, 109–123. CrossRefGoogle Scholar - Light, R.J. (1971). Measures of response agreement for qualitative data: Some generalizations and alternatives.
*Psychological Bulletin*,*76*, 365–377. CrossRefGoogle Scholar - Mak, T.K. (1988). Analyzing intraclass correlation for dichotomous variables.
*Applied Statistics*,*37*, 344–352. CrossRefGoogle Scholar - Morey, L.C., & Agresti, A. (1984). The measurement of classification agreement: An adjustment to the Rand statistic for chance agreement.
*Educational and Psychological Measurement*,*44*, 33–37. CrossRefGoogle Scholar - Nei, M., & Li, W.-H. (1979). Mathematical model for studying genetic variation in terms of restriction endonucleases.
*Proceedings of the National Academy of Sciences*,*76*, 5269–5273. CrossRefGoogle Scholar - Pearson, E.S. (1947). The choice of statistical tests illustrated on the interpretation of data classed in a 2×2 table.
*Biometrika*,*34*, 139–167. Google Scholar - Popping, R. (1983).
*Overeenstemmingsmaten voor nominale data*. Ph.D. thesis, Groningen, Rijksuniversiteit Groningen. Google Scholar - Rand, W. (1971). Objective criteria for the evaluation of clustering methods.
*Journal of the American Statistical Association*,*66*, 846–850. CrossRefGoogle Scholar - Rogot, E., & Goldberg, I.D. (1966). A proposed index for measuring agreement in test-retest studies.
*Journal of Chronic Disease*,*19*, 991–1006. CrossRefGoogle Scholar - Scott, W.A. (1955). Reliability of content analysis: the case of nominal scale coding.
*Public Opinion Quarterly*,*19*, 321–325. CrossRefGoogle Scholar - Sokal, R.R., & Michener, C.D. (1958). A statistical method for evaluating systematic relationships.
*University of Kansas Science Bulletin*,*38*, 1409–1438. Google Scholar - Sokal, R.R., & Sneath, P.H. (1963).
*Principles of numerical taxonomy*. San Francisco: Freeman. Google Scholar - Sørenson, T. (1948). A method of stabilizing groups of equivalent amplitude in plant sociology based on the similarity of species content and its application to analyses of the vegetation on Danish commons.
*Kongelige Danske Videnskabernes Selskab Biologiske Skrifter*,*5*, 1–34. Google Scholar - Steinley, D. (2004). Properties of the Hubert–Arabie adjusted Rand index.
*Psychological Methods*,*9*, 386–396. CrossRefPubMedGoogle Scholar - Warrens, M.J. (2008, in press). On the indeterminacy of resemblance measures for binary (presence/absence) data.
*Journal of Classification*. Google Scholar - Zegers, F.E. (1986).
*A General family of association coefficients*. Ph.D. thesis, Groningen, Rijksuniversiteit Groningen. Google Scholar - Zegers, F.E., & Ten Berge, J.M.F. (1985). A family of association coefficients for metric scales.
*Psychometrika*,*50*, 17–24. CrossRefGoogle Scholar