Acessibilidade / Reportar erro

ALTERNATIVE METHODS TO MULTIPLE CORRESPONDENCE ANALYSIS IN RECONSTRUCTING THE RELEVANT INFORMATION IN A BURT'S TABLE

ABSTRACT

In this work, the reconstruction of the Burt's table, Greenacre (1988)'s Joint Correspondence Analysis (JCA), and Gower & Hand (1996)'s Extended Matching Coefficient (EMC) are compared to Multiple Correspondence Analysis (MCA) in order to check the quality of the methods. In particular, for the whole table, the ability is considered separately the diagonal, and the off-diagonal tables, that is the ability to describe either each character's distribution or the interaction between pairs of characters, or both. The theoretical aspects are discussed first, and finally the results obtained in an application are shown and discussed.

Keywords:
Correspondence Analysis; Multiple Correspondence Analysis; Joint Correspondence Analysis; Extended Matching Coefficient; Singular Value Decomposition

1 INTRODUCTION

Both Multicriteria Analysis and Multicriteria Decision Models (4)4 BELTON V & STEWART T. 2002. Multiple Criteria Decision Analysis. Boston, Kluwer Academic Publishers., (37)37 ROY B & BOUYSSOU D. 1985. Aide à la décision: méthodes et cas. Paris, Economica. are tools largely adopted in operational research, in particular when dealing with Knowledge Discovering in Databases (14)14 FRAWLEY WJ, PIATETSKY-SHAPIRO G & MATHEUS CJ. 1992. Knowledge Discovery in Databases: An Overview, Artificial Intelligence Magazine, 13(3): 57-70.. In present days it may be of high interest to deal with qualitative unstructured data, whose treatment may be more complex. Studies in this framework are found in recent operational research literature (16)16 GÓES ART, STEINER MTA & PENICHE RA. 2015. Classification of Power Quality Considering Voltage Sags in Distribution Systems Using KDD Process. Pesquisa Operacional, 35(2): 329-352., (17)17 GOMES LFAM & DE ANDRADE RM. 2012. Performance evaluation in assets management with the AHP. Pesquisa Operacional, 32(1): 31-53., (30)30 LOPES YG & DE ALMEIDA AT. 2013. A multicriteria decision model for selecting a portfolio of oil and gas exploration projects. Pesquisa Operacional, 33(3): 417-441., (40)40 SASSI RJ. 2012. An Hybrid Architecture for Clusters Analysis: Rough Sets Theory and Self-Organizing Map Artificial Neural Network. Pesquisa Operacional, 32(1): 139-163.. In this context, data reduction through exploratory multidimensional scaling may contribute to clarify the data at hand, by revealing structures and factors. In particular, factors, together with the observed characters most associated to them, may lead to a consistent dimension reduction and at the same time to the ability to select the most appropriate characters to take into account for further, more focused investigation. Thus, the identification of the proper dimension of a data table may be a topic of investigation per se.

In exploratory multidimensional scaling the identification of the proper dimension of the solution is the basis to define a threshold between relevant information and residuals. The relevant information is also tied to the possibility of interpreting the factors according to the paradigms of the methods at hand: in the linear case, the percentage of explained inertia is the most widely used. Thus, to take into account a large share of inertia is the most evident rough method that may be used and a higher-dimensional solution is normally preferred rather than a smaller one only if its corresponding inertia is significantly larger than a smaller-dimensional solution. Tied to this aspect, the reconstruction of the original data table according to a lower rank matrix is of relevance, since a good reconstruction of the data obtained this way is helpful to better understand to what extent the reduction in dimension, through the use of factors, is a reasonable approximation of the original data.

In this paper, we consider the special case of qualitative data, that are usually summarized by the so-called Burt's matrix, the super-contingency table that cross-tabulates all characters taken into account. Multiple Correspondence Analysis (MCA) (7)7 BENZÉCRI JP ET AL. 1973-82. L'Analyse des données, Tome 2. Paris: Dunod., (19)19 GREENACRE MJ. 1983. Theory and Application of Correspondence Analysis. London: Academic Press. is the best known exploratory factor analysis method to deal with it, but alternative methods are proposed in literature, based on different rationale. Critics to MCA emphasize the misuse of the chi-square metrics (18)18 GOWER JC & HAND DJ. 1006. Biplots. London, Chapman and Hall., a metrics that for contingency tables finds its rationale in the partition of the chi-square in independent components (27)27 LANCASTER HO. 1949. The derivation and partition of χ2 in certain discrete distributions. Biometrika, 36: 117-129., (35)35 ORLÓCI L. 1978. Multivariate Analysis in Vegetation Research, 2nd ed. Den Haag: Junk., (44)44 WILLIAMS EJ. 1952. Use of scores for the analysis of association in contingency tables. Biometrika, 39: 274-289., thus on the deviation from the expectation. Now, to compute distances between lines in both the indicator matrix and its square, the Burt's table, such metrics is tremendously biased by the obvious (squared) differences between levels belonging to the same character (20)20 GREENACRE MJ. 1988. Correspondence analysis of mutlivariate categorical data by weighted least squares. Biometrika, 75: 457-467., (21)21 GREENACRE MJ. 2006. From Simple to Multiple Correspondence Analysis. In: GREENACRE & BLASIUS (Eds.), pp. 41-76.. In addition, rare levels raise their importance in the computation but enhance aspects that reveal being useless, since the chi-square statistics may not be applied to these tables; hence, its use is hardly justifiable (18)18 GOWER JC & HAND DJ. 1006. Biplots. London, Chapman and Hall.. Eventually, it is known since long the problem of the underestimation of the inertia explained by the factors, that deserve being re-evaluated in some way (2)2 ABDI H & VALENTIN D. 2007. Multiple Correspondence Analysis. In: SALKIND N (Ed.), Encyclopedia of Measurement and Statistics. Thousand Oaks, CA: Sage: pp. 651-657., (8)8 BENZÉCRI JP. 1979. Sur les calcul des taux d'inertie dans l'analyse d'un questionnaire. Les Cahiers de l'Analyse des Données, 4(3): 377-379., (19)19 GREENACRE MJ. 1983. Theory and Application of Correspondence Analysis. London: Academic Press.. Indeed, applying the chi-square metrics to such a table, the highest contributions to the total inertia result from the block-diagonal tables crossing each character with itself, which is information without noticeable value, since this way the expected values provide the maximum deviation from expectation. Along with this, a problem results in the unpredictability of the partial data reconstruction of the Burt's table, as already put in evidence by (10)10 CAMIZ S & GOMES GC. 2013. Joint Correspondence Analysis Versus Multiple Correspondence Analysis: A Solution to an Undetected Problem. In: GIUSTI A et al. (eds.), Classification and Data Mining, Studies in Classification, Data Analysis, and Knowledge Organization, Berlin, Springer: pp. 11-18.. The problem may be relevant in qualitative discriminant analysis (39)39 SAPORTA G. 1975. Liaison entre plusieurs ensembles de variables et codage de données qualitatives. Thèse de troisième cycle, Paris VI, Université Pierre et Marie Curie., which is based on MCA coordinates. Here, a bad reconstruction would prevent the reduction of the number of factors to take into account.

In this paper, we consider two different alternatives: the Joint Correspondence Analysis (JCA, (20)20 GREENACRE MJ. 1988. Correspondence analysis of mutlivariate categorical data by weighted least squares. Biometrika, 75: 457-467.) and the Principal Component Analysis (PCA, (26)26 JOLLIFFE IT. 2002. Principal Components Analysis. Berlin, Springer.) of the Extended Matching Coefficient matrix (EMC, (18)18 GOWER JC & HAND DJ. 1006. Biplots. London, Chapman and Hall.), which are suggested by the corresponding authors as a solution. It must be noted that the aims of both MCA and EMC are the same: to perform a kind of PCA on qualitative data, i.e. to find uncorrelated quantitative characters giving independent ordinations to the units, that optimize the explained inertia. It is the definition of inertia that is different, bearing in mind that EMC aims at fixing the emphasis given to the rare levels of MCA by the chi-square metrics. Since the solutions of both methods are based on the eigendecomposition, their different dimensional solutions are encapsulated, so that the reconstruction of the original data may be seen as a sum of 1-rank independent tables. On the opposite, JCA aims at finding the best reconstruction of the off-diagonal tables of the Burt's table only, generalizing the Simple Correspondence Analysis to the simultaneous analysis of several 2-way contingency tables. The idea is analogous to the one of (42)42 THOMSON GH. 1934. Hotelling's method modified to give Spearman's g. Journal of Educational Psychology, 25: 366-374. to fit the off-diagonal elements of a correlation matrix and is obtained by numerical optimization. Therefore, this time different dimensional solutions are not encapsulated.

To compare the results, we consider the reconstruction quality only. At the end, these methods will be applied to a very small table, taken from studies in linguistics (32)32 NARDY MNS. 2007. A sintaxe no interior das palavras - efeitos de gênero na lingua escrita contemporânea. PhD Thesis in Linguistics. Rio de Janeiro, Facultade de Leteras da Universidade Federal de Rio de Janeiro..

2 THEORETICAL FRAMEWORK

2.1 Singular Value Decomposition

We may ground our further discussion on the well-known Singular Value Decomposition (SVD, (1)1 ABDI H. 2007. Singular Value Decomposition (SVD) and Generalized Singular ValueDecomposition (GSVD). In: SALKIND N (Ed.), Encyclopedia of Measurement and Statistics. Thousand Oaks, CA: Sage: pp. 940-945., (19)19 GREENACRE MJ. 1983. Theory and Application of Correspondence Analysis. London: Academic Press.) theorem, which states

Theorem 1.Any real matrix X may be decomposed as X = UΛ1/2V', with Λ the diagonal matrix of the real non-negative eigenvalues of XX', U the orthogonal matrix of the corresponding eigenvectors, and V the matrix of eigenvectors of X'X (with the same eigenvalues), with both constraints U'U = I and V'V = I.

This theorem corresponds to the reconstruction formula of an S-rank matrix X ∈

(1)

or, in vector notation

on which the Eckart & Young's theorem (13)13 ECKART C & YOUNG G. 1936. The approximation of one matrix by another of lower rank. Psychometrika, 1: 211-218. is based:

Theorem 2. (Eckart and Young) The s-rank reconstruction of any real matrix X, with s < S, the rank of X, once its singular values are sorted in decreasing order,

is the best one in the least-squares sense.

This means that, for every s < S, the matrix Ĥs solves the problem to approximate a matrix X by another matrix H of lower rank at the best in the least-squares sense, thus by minimizing

(2)

As it is trivial that (ĤsĤ's) = ∑sα=1λα the minimum of (2) reached by Ĥs equals

It is well-known that Principal Component Analysis (PCA, (26)26 JOLLIFFE IT. 2002. Principal Components Analysis. Berlin, Springer.) finds its rationale in this theorem, once the data table is standardized according to zij = σj the average and the standard deviation of the j-th character; indeed, this way Z'Z = cor(X) = C, the matrix of correlations between the columns of X. Thus, given the PCA of the correlation matrix C, with Λ and V as their diagonal matrix of eigenvalues and unit matrix of eigenvectors respectively, and given U as the unit eigenvectors of ZZ', the reconstruction formula (1) becomes and , with

(3)

For correspondence analysis, we shall adopt the Generalized Singular Values Decomposition (GSVD, (1)1 ABDI H. 2007. Singular Value Decomposition (SVD) and Generalized Singular ValueDecomposition (GSVD). In: SALKIND N (Ed.), Encyclopedia of Measurement and Statistics. Thousand Oaks, CA: Sage: pp. 940-945., (19)19 GREENACRE MJ. 1983. Theory and Application of Correspondence Analysis. London: Academic Press.), in which two other matrices are involved:

Theorem 3.Given two real positive definite matrices M and N, any real matrix X may be decomposed as X = ŨΛ1/2Ṽ', under constraints Ũ'MŨ = 1 and Ṽ'NṼ = 1.

The solution is given by the SVD of the matrix ŨŨ' = M-1 and ṼṼ' = N-1 respectively.. It results that , and , with

In this case the minimization problem (2) becomes

with s < S = rank(). with

Using the matrix

(4)

as trace (ĤĤ') = , the minimization problem is solved as:

(5)

In the particular case in which both M and N are diagonal, (5) simplifies to

(6)

Therefore, the exploratory analysis paradigm states that the most relevant information is tied to the largest eigenvalues and the non-relevant to the least ones. The problem of distinguishing among them, that is to identify at least a tentative cutpoint of either the singularor the eigen-values sequence, remains a crucial issue, that did not find a univocal solution so far (for PCA see, e.g., (11)11 CAMIZ S & PILLAR VD. (In press). Identifying the True Dimension in Principal Component Analysis. Submitted to Community Ecology., (25)25 JACKSON DA. 1993. Stopping rules in principal component analysis: a comparison of heuristical and statistical approaches. Ecology, 74: 2204-2214., (36)36 PERES-NETO PR, JACKSON DA & SOMERS KM. 2005. How Many Principal Components? Stopping Rules for Determining the Number of Non-trivial Axes Revisited. Computational Statistics and Data Analysis, 49: 974-997.). In Simple Correspondence Analysis (SCA, (7)7 BENZÉCRI JP ET AL. 1973-82. L'Analyse des données, Tome 2. Paris: Dunod., (19)19 GREENACRE MJ. 1983. Theory and Application of Correspondence Analysis. London: Academic Press.), it seems more easily solved, since the special chi-square metrics adopted allows a useful solution and an easy interpretation of the results, and regarding MCA we shall see that (5)5 BEN AMMOU S & SAPORTA G. 1998. Sur la normalité asymptotique des valeurs propres en ACM sous l'hypothèse d'indépendance des variables. Revue de Statistique Appliquée, 46(3): 21-35., (6)6 BEN AMMOU S & SAPORTA G. 2003. On the connection between the distribution of eigenvalues in multiple correspondence analysis and log-linear models. REVSTAT-Statistical Journal, 1(0): 42-79. propose an interesting method.

2.2 Simple Correspondence Analysis

Let N an r × c contingency table, with n = n.. the table grand total, X = N/n the table of relative frequencies pij = nij/n, r = (p1, ..., pr.)' the vector of row marginal profile, c = (p.1, ..., p.c)' the vector of column marginal profile, and Dr = diag(r), Dc = diag(c) the corresponding diagonal matrices. Let E = rc' represents the table with equal marginal profiles of X under the independence hypothesis. The SCA of N results from the application of GSVD to the matrix X with the real positive definite matrices represented by the diagonal matrices Dr-1 and Dc-1. In this particular case the decomposition results 1 = 1 to which the eigenvectors s-rank reconstruction formula (s < S = min(r, c)) may be little transformed: and both matrices and and correspond respectively. It can also be shown that the other non-trivial eigenvalues are always contained between 0 and 1. If we take off the summation the trivial eigenvalue, the have a trivial eigenvalue λ

(7)

Incidentally, we observe that, in order to produce graphics with simultaneous symmetrical representation of both rows and columns, the SCA eigenvectors are usually rescaled by defining as coordinates the vectors φα and ψα given by and respectively. In this case the reconstruction formula (7) becomes

Thus, depending on which coordinates one chooses, the reconstruction formula for N becomes:

(8)

Returning to the optimization problem (6), we may explicitly write the residual as

(9)

Now, if we consider the 1-rank reconstruction, that is Ĥ1 = E = rc', the residual takes the particular form

(10)

that is the sum of squared deviations of the observed values from the expected ones under independence divided by the expected ones. This is commonly called the inertia of the table X that is, up to the factor n, the chi-square of N; indeed, multiplying (10) by n, we get

(11)

Hence, the decomposition of the inertia along the non-trivial eigenvectors of SCA leads to the decomposition of the chi-square along each corresponding dimension:

χ2 = n2 + ... + λS) = χ22 + ... + χ2S

α equals χα2 = nλα.

Based on (44)44 WILLIAMS EJ. 1952. Use of scores for the analysis of association in contingency tables. Biometrika, 39: 274-289., this result led (35)35 ORLÓCI L. 1978. Multivariate Analysis in Vegetation Research, 2nd ed. Den Haag: Junk. to check for significance the partial chi-squares associated to each eigenvalue, χα2 with df = (r + c - 2α - 1) degrees of freedom, to detect if there are linear ordinations of both rows and column levels that explain the deviation from expectation. Indeed, (28)28 LANCASTER HO. 1963. Canonical Correlations and Partitions of χ2. Quarterly Journal of Mathematics, 14(1): 220-224. proved that the first eigenvalue is larger than the corresponding chi-square and (29)29 LEBART L. 1976. The significance of Eigenvalues issued from Correspondence Analysis. COMPSTAT, Vienna, Physica Verlag: pp. 38-45. proved that the distribution of the eigenvalues is that of those of a Wishart matrix (W (m1 - 1) (m2 - 1), Min (m1 - m2 - 1), I). Nevertheless, (15)15 GHOMARI A. 1983. Analyse Canonique d'une table de contingence. Étude asymptotique par échantillonnage. Thèse de l'Université de Pau et des Pays de l'Adour (France). finds that the sum of the smallest eigenvalues may be used as a test for their nullity, that leads to the Malinvaud's (31)31 MALINVAUD E. 1987. Data analysis in applied socio-economic statistics with specialconsideration of correspondence analysis. Marketing Science Conference, Joy en Josas: HEC-ISA. stopping rule, to test the residuals of each reduced rank solution. Indeed, one may test for significance

asymptotically chi-square-distributed with (r - α - 1) × (c - α - 1) degrees of freedom.

2.3 Multiple Correspondence Analysis

Let us consider now a qualitative data table X with n observations, with Q as nominal characters and J as the total number of levels, that is J = ∑Qi=1li, where li is the number of levels of the i-th character. It is well-known that MCA of such a matrix is nothing but a generalization of SCA and it is based on SCA of either the indicator matrix Z, whose rows are the units and the columns are all the J levels of the Q considered variables, or the so-called Burt's table B = Z'Z that gathers all contingency tables obtained by cross-tabulating all the variables in Z, including the diagonal tables obtained by crossing each variable with itself. The idea is to adopt for both matrices the same optimized decomposition of SCA, namely the GSVD of either Q-1ZDr-1 or

(12)

Indeed, it is evident that the latter is the square of the previous, so that they share the eigenvectors, and the singular values in Burt's case are the squares of those of the indicator matrix case: vα = μ2α. The identity of the eigenvalues allows identical interpretation of the resulting factors. Thus, it makes no difference to perform MCA on either matrix. On the other side, whereas the total inertia of Z is Iz = B equals ∑vα = ∑ μ2α. In both cases, the chi-square metrics is adopted so that the interpretation of results ought to be done once again in terms of deviations from expectation. This point deserves some special attention, since the deviation refers to all contingency tables gathered in the Burt's table, including the diagonal ones. The problem is that such diagonal matrices, that "theoretically" would indicate maximum deviation, in this case are just the expected ones, as they cross each character with itself., the one of

As SCA, given a Burt matrix B, MCA may be defined as the weighted least-squares approximation of B by another matrix H of lower rank, minimizing

(13)

Notice how (13) derives from (10). In terms of the subtables, this may be rewritten as

where H is the supermatrix of the Hij. Introducing the norm notation

||A - B||2ij = trace(Di-1(A - B)Dj-1(A - B)')

the minimization can be written as

(14)

In MCA the identification of the true dimension is particularly difficult, despite the MCA is a SCA of a particular table, because the chi-square test has no sense. Indeed, for B a chi-squared statistic may again be calculated as if it were a contingency table, and this simplifies as

where χ2ij is the chi-squared statistic for the off-diagonal subtable Nij =Z'iZj crossing the i-th and the j-th characters, but without the possibility to make a test. Unfortunately neither Qα nor Z are chi-square distributed (5)5 BEN AMMOU S & SAPORTA G. 1998. Sur la normalité asymptotique des valeurs propres en ACM sous l'hypothèse d'indépendance des variables. Revue de Statistique Appliquée, 46(3): 21-35., since Z is composed by 0's and 1's, and it is dramatically inflated by the diagonal tables without any real meaning. computed on the indicator matrix

The high number of eigenvalues of the MCA, and their corresponding low values, were criticized by the same Benzécri (8)8 BENZÉCRI JP. 1979. Sur les calcul des taux d'inertie dans l'analyse d'un questionnaire. Les Cahiers de l'Analyse des Données, 4(3): 377-379. that suggests to reevaluate those larger than their average. Indeed, applying both SCA and MCA to the same two characters, by partitioning the Burt's table Z'Z into submatrices it can be shown (ibid.) the relation μα = α, the eigenvalues of Z, and λα, those of the SCA of the contingency table crossing the two characters. In this case, it is evident that to the eigenvalues λα = 0 of SCA correspond eigenvalues μα = 1/2 of Z and vα = 1/4 of B, whereas to the other two correspond, one of which larger and the other smaller than 1/2 and 1/4 respectively. To generalize this argument to several characters results in admitting to limit attention in MCA only to the eigenvalues larger than their mean, that is μ ≥ . that holds among μ

The argument is discussed in detail by both Benzécri (8)8 BENZÉCRI JP. 1979. Sur les calcul des taux d'inertie dans l'analyse d'un questionnaire. Les Cahiers de l'Analyse des Données, 4(3): 377-379. and Greenacre (20)20 GREENACRE MJ. 1988. Correspondence analysis of mutlivariate categorical data by weighted least squares. Biometrika, 75: 457-467., (21)21 GREENACRE MJ. 2006. From Simple to Multiple Correspondence Analysis. In: GREENACRE & BLASIUS (Eds.), pp. 41-76.. Both authors suggest, in order to get a measure of relative importance of each factor, to re-evaluate the eigenvalues larger than the mean (equal to 1/Q) according to the formula

Benzécri (8)8 BENZÉCRI JP. 1979. Sur les calcul des taux d'inertie dans l'analyse d'un questionnaire. Les Cahiers de l'Analyse des Données, 4(3): 377-379. suggests to consider as total inertia the sum of the re-evaluated eigenvalues and to take as percentage of explained inertia the ratio (20)20 GREENACRE MJ. 1988. Correspondence analysis of mutlivariate categorical data by weighted least squares. Biometrika, 75: 457-467. bases his arguments on the unusefulness to take into account the diagonal block matrices and the utility to limit attention only to the total off-diagonal inertia of the table, that is the sum of squared (non-re-evaluated) eigenvalues minus the diagonal inertia; represented as:. This results in a dramatic re-evaluation of the relative importance of the first eigenvalues. On the opposite, Greenacre

Experiments show that the Greenacre's reevaluation is always limited to a share of the total inertia of Burt's table even by taking into consideration all the eigenvalues larger than the mean. This does not affect the interpretation of the factors, that essentially depends upon the eigenvectors - and thus to the contributions of both levels and characters to them -, but affects more the quality of representation of these elements on the factor subspaces, that varies according to the percentage of inertia attributed to each one. Indeed, this is a point that would deserve some specific consideration, in particular in deciding which reevaluation may be better taken into account. In the following, we shall call adjusted MCA the one with re-evaluated inertia, therefore with the coordinates recalculated accordingly.

The reduction in number of the dimension, thanks to both Benzécri's and Greenacre's reevaluations, does not solve the problem of the true dimension of the table. To this question, an answer comes from Ben Ammou & Saporta (5)5 BEN AMMOU S & SAPORTA G. 1998. Sur la normalité asymptotique des valeurs propres en ACM sous l'hypothèse d'indépendance des variables. Revue de Statistique Appliquée, 46(3): 21-35., (6)6 BEN AMMOU S & SAPORTA G. 2003. On the connection between the distribution of eigenvalues in multiple correspondence analysis and log-linear models. REVSTAT-Statistical Journal, 1(0): 42-79.: they suggest to estimate the significance of the eigenvalues of MCA according to their distribution. If the characters are independent,

with n..ϕ2ij ≈ χ2(li - 1)(lj - 1), thus,

E[n..ϕ2ij] = E2ij] = (li - 1)(lj - 1)

so the expectation of the variance S2μ of the eigenvalues is

Roughly, one may assume that the interval 1/Q ± 2σ should contain about 95% of the eigenvalues. Indeed, since the kurtosis of the set of eigenvalues is lower than for a normal distribution, the actual proportion is larger than 95%.

2.4 Joint Correspondence Analysis

Greenacre (20)20 GREENACRE MJ. 1988. Correspondence analysis of mutlivariate categorical data by weighted least squares. Biometrika, 75: 457-467. criticizes the MCA approach, stating that it is not a natural generalization of SCA, and proposes as more natural his Joint Correspondence Analysis (JCA). With it, he overcomes the MCA's useless fitting of the diagonal subtables of B which contribute with the term n(J - Q) to the total inertia. Hence, he takes as more natural measure of total inertia the sum ∑∑q ≠ s χ2qs of the inertias of the off-diagonal tables. This suggests an alternative generalization of correspondence analysis which fits only the off-diagonal tables, analogous to factor analysis where values on the diagonal of the covariance or correlation matrix are of no direct interest.

Indeed, the proposed redefinition of the total inertia, by removing the diagonal block-matrices, would fix an important bias due to the application to the Burt's table of the chi-square metrics, since the diagonal structure of the diagonal block-matrices represents a very high fictitious deviation from the expected values, that MCA analyzes as if it were a true deviation. On this basis, opposite to the current use, this kind of analysis is not really suitable.

Greenacre (20)20 GREENACRE MJ. 1988. Correspondence analysis of mutlivariate categorical data by weighted least squares. Biometrika, 75: 457-467. proposes his Joint Correspondence Analysis (JCA) as a weighed least-squares approximation aiming at minimizing

(15)

instead of (14) with the corresponding χ2j = ∑Qi=1i-1j=1 χ2ij sum of the chi-squares of all off-diagonal tables, that unfortunately may not be checked for significance.

In order to get the solution, he proposes an alternating least-squares algorithm, based on the reformulation of (15) as follows:

(16)

with ri the diagonal of the i-th block-diagonal matrix. Calling H and L the supermatrices gathering the Hij and Lij respectively, (20)20 GREENACRE MJ. 1988. Correspondence analysis of mutlivariate categorical data by weighted least squares. Biometrika, 75: 457-467. states the equivalence of the rank-K solution of L which satisfies the normal equations in the minimization of the second term of (16) with the rank-(K + 1) matrix H = rr' + L which satisfies minimizing (15), with r the supervector gathering the Q vectors ri.

The matrix approximation L of rank K is of the form L = nDXDβX'D, where the J × K matrix X is normalized as X'DX = QI, with D = diag(r). The matrix X of parameters has rows corresponding to the categories of the variables and columns corresponding to the dimensions of the solution, that must be chosen in advance. The diagonal matrix Dβ contains a scale parameter for each dimension. This form of L and the normalization conditions are chosen to generalize the bivariate case (8). The parameter matrix X is partitioned row-wise according to the variables as X1, ..., XQ, where Xq is Jq × K, so that the submatrices of L are Lqs = nDqXqDβX'sDs. There are also inherent centering constraints on X of the form X'r = 0 due to the orthogonality with the dimension defined by the trivial solution. It is evident that the dimension of the solution must be chosen in advance.

Thus (20)20 GREENACRE MJ. 1988. Correspondence analysis of mutlivariate categorical data by weighted least squares. Biometrika, 75: 457-467. proposes the approximate reconstruction of the whole matrix B - nrr', namely

B - nrr' ≈ nDXDβX'D + C,

where C is a block diagonal matrix with submatrices Cqq, q = 1, ..., Q down the diagonal and zeros elsewhere. Here, each Cqq is composed by dummy parameters which effectively allow perfect fitting of the submatrices on the diagonal of B - nrr', thereby eliminating their influence on the model of interest. The minimization of

(17)

is equivalent to minimizing (16) because the latter set of terms in (17) can always be made zero by setting Cii = Nii - n ri ri' - Lii.

The algorithm proposed by (20)20 GREENACRE MJ. 1988. Correspondence analysis of mutlivariate categorical data by weighted least squares. Biometrika, 75: 457-467. to minimize (17) can be performed iteratively by alternating between the variables in C and those in X and Dβ as follows:

  • 1. fix the dimension K of the solution.

  • 2. initiate the algorithm with an analysis of the full Burt matrix B, that is

(18)

  • 3. limiting attention to the first K dimensions, say the first K columns of X x(1), ..., x(K), (18) can be rewritten as

(19)

  • so that, if all quantities except the βk(k = 1, ..., K) are regarded as fixed, the problem reduces to a simple weighted least-squares regression (see (20)20 GREENACRE MJ. 1988. Correspondence analysis of mutlivariate categorical data by weighted least squares. Biometrika, 75: 457-467., for further details).

  • 4. Keeping X and Dβ fixed, set

Cii = Nii - nriri' - nDiXiDβX'iDi (i = 1, ..., Q).

  • 5. Keeping C fixed, minimize with respect to X and Dβ: this is achieved by performing a correspondence analysis on the table B* = B - C, that is the Burt's matrix with modified submatrices on its diagonal, setting X equal to the first K vectors of optimal row or column parameters and the diagonal of Dβ equal to the square roots of the first K principal inertias respectively.

  • 6. Iterate the last two steps until convergence.

In the special case Q = 2, the problem reduces to fitting the single off-diagonal submatrix N12. It is relevant to mention that the initial solution described above is optimal and provides the simple correspondence analysis of N = N12 exactly. It is also noteworthy to quote (22)22 GREENACRE MJ. 2007. Correspondence Analysis in Practice, 2nd Ed., London, Chapman and Hall., [pag. 148]'s alternative proposal to reevaluate the inertias along the axes by estimating them through a weighted least-squares regression. Indeed, it means to estimate only once the βks in (19), where the xks are the eigenvectors issued by MCA, once the dimension of the solution K is decided. We are not convinced by this solution, since the objections that concern the use of the chi-square metrics remain unaltered.

2.5 The Extended Matching Coefficient

JCA was introduced by (20)20 GREENACRE MJ. 1988. Correspondence analysis of mutlivariate categorical data by weighted least squares. Biometrika, 75: 457-467. as a way to drop the excessive attention given to the diagonal of the Burt's matrix by MCA, that indeed does not deserve any interest, but with a different optimization aim, that is to reconstruct at the best the off-diagonal subtables. In this case, the chi-square metrics is justified, whereas we have already stated that in classical MCA it has no theoretical justification. For this reason, we are not convinced that some inertia reevaluation of MCA, as the quoted ones, may be a solution. On the opposite, we find interesting to explore Gower & Hand's (18)18 GOWER JC & HAND DJ. 1006. Biplots. London, Chapman and Hall. proposal to drop the chi-square metrics in favor of a more simple one: the Extended Matching Coefficient. Indeed, for two units, they define it as the number of common levels across all characters. Therefore, given the indicator matrix Z, ZZ' would give us a similarity matrix to deal with; indeed, given its size, the Burt's table B as such is its corresponding in the dual space, so that it is sufficient to perform the SVD of the centered Burt's matrix, that is

(20)

to be compared with (12). Now, the reconstruction formula (3) holds, but this time the layers may not be interpreted in terms of deviations from expectation, that is not taken into account by the method, but merely as contribution to the reconstruction, that is in this case the frequencies in the Burt's cells. Unfortunately, no stopping rule is available for this method so far, thus we considered both Cattel's (12)12 CATTELL RB. 1966. The scree test for the number of factors. Multivariate Behavioural Research, 1: 245-276. and brokenstick (3)3 BARTON DE & DAVID FN. 1956. Some Notes on Ordered Random Intervals. Journal of the Royal Statistical Society, Series B, 18(1): 79-94. tests.

3 AN APPLICATION TO THE KIND OF WORDS

To show in detail the different behavior of the different analyses in practice, we refer first to a data set taken from (32)32 NARDY MNS. 2007. A sintaxe no interior das palavras - efeitos de gênero na lingua escrita contemporânea. PhD Thesis in Linguistics. Rio de Janeiro, Facultade de Leteras da Universidade Federal de Rio de Janeiro., consisting in 2000 words taken from four different kind of periodic reviews (Childish (TC), Review (TR), Dissemination (TD), and Scientific Summary (TS)), classified according to their grammatical kind (Verb (WV), Noun (WN), and Adjective (WA)) and the number of internal layers (Two- (L2), Three- (L3), and Four and more layers (L4)), as a measure of the word complexity. In Table 1 the Burt's table that results by crossing the three characters is reported.

Table 1
Burt's table of the words' type example.

In Table 2 are reported the eigenvalues of the three SCAs of the contingency data tables that cross the three characters two by two: the eigenvalues, the percentage of corresponding inertia, and the p-value associated to the chi-square calculated for the corresponding one-dimensional reconstruction, that, in this case, is identical to the Malinvaud's test, since each solution is 2-dimensional.

Table 2
SCA of the three contingency data tables of the three characters two by two. In the columns, the eigenvalues, the percentage of inertia, and the p-value of the chi-square associated to the factors.

In two cases, the tests do not attribute to the second factors any real meaning, since the p-value is larger than 5%, whereas in the case of the table type of publication - kind of words the second factor is also significant.

In Figure 1 the results of the three SCAs are represented too: it must be pointed out that the vertical position of the items is significant only for the second graphic. Indeed, the inspection of this factor plane shows an arch pattern due to a Guttman effect (9)9 CAMIZ S. 2005. The Guttman Effect: its Interpretation and a New Redressing Method. Τετραδία Αναλύσης Δεδομένων (Data Analysis Bulletin), 5: 7-34., (24)24 GUTTMAN L. 1941. The Quantification of a Class of Attributes: a Theory and Method of Scale Construction. In: HORST P (Ed.) The Prediction of Personal Adjustment. New York, Social Science Research Council.; the same, the interpretation is straightforward: for the first table, both verbs and nouns seem to have in general less syllables than the adjectives; for the second, the variation in use of the words according to the higher complexity of the publication: verbs for the childish, nouns for reviews and disseminations, adjectives for scientific summaries; for the third, the more complicated words (3 and more syllables) in scientific summaries than in all others. It is noteworthy in the second table the opposite pattern of verbs and adjectives, the first reducing while the publication is of higher level and the second raising; this explains clearly the observed Guttman effect. The position of long words very elongated on the second axis of both the first and the third analyses, in the latter case also with review is explained by the shortness of the verbs and its scarce presence in childish publications, but it is not significant. We may ground our comparisons on this interpretation of the data. Running MCA, the pattern of eigenvalues is represented in Table 3, in which are reported the singular values of Z, their percentage to their total (that equals = 2.33), the cumulate percentage, the eigenvalues of the Burt's matrix, corresponding to the explained inertia, and the cumulate inertia.

Figure 1
Words' type example: The pair of characters levels on the three two-way SCAs: (a) Words vs. Levels; (b) Publications vs. Words; (c) Publications vs. Levels.

Table 3
MCA singular values, percentage to the total and cumulate percentage, eigenvalues, and cumulate inertia of the Burt's table of words' type example. Then re-evaluated inertia and percentages according to both (8)8 BENZÉCRI JP. 1979. Sur les calcul des taux d'inertie dans l'analyse d'un questionnaire. Les Cahiers de l'Analyse des Données, 4(3): 377-379. and (20)20 GREENACRE MJ. 1988. Correspondence analysis of mutlivariate categorical data by weighted least squares. Biometrika, 75: 457-467..

In addition, on the table are reported the re-evaluated inertia and its percentages and cumulated ones according to both (8)8 BENZÉCRI JP. 1979. Sur les calcul des taux d'inertie dans l'analyse d'un questionnaire. Les Cahiers de l'Analyse des Données, 4(3): 377-379. and (20)20 GREENACRE MJ. 1988. Correspondence analysis of mutlivariate categorical data by weighted least squares. Biometrika, 75: 457-467., limited to the only three singular values larger than 1/Q = 1/3, with the totals in the following row. In both cases, the first dimension's re-evaluated inertia is by far larger than the others. If we apply the Ben Ammou & Saporta's (5)5 BEN AMMOU S & SAPORTA G. 1998. Sur la normalité asymptotique des valeurs propres en ACM sous l'hypothèse d'indépendance des variables. Revue de Statistique Appliquée, 46(3): 21-35., (6)6 BEN AMMOU S & SAPORTA G. 2003. On the connection between the distribution of eigenvalues in multiple correspondence analysis and log-linear models. REVSTAT-Statistical Journal, 1(0): 42-79. estimation of the average singular value distribution under independence, we find that the standard deviation is σ = 0.0159364, so that the confidence interval at 95% level is (0.30146 < λ < 0.36521). As a consequence, only the first singular value is outside the confidence interval and should be considered significant. As a matter of facts, the second one is very close to the threshold (0.3640): this is consistent with the fact that only one of the 2-dimensional tables has a significant second eigenvalue.

In Figure 2a the distribution of all character levels on the plane spanned by the first two factors of MCA is represented. Indeed, the patterns of all the characters' levels repeat fairy well the same in the three two-way tables: thus it may be taken as a sign of coherence between the individual SCAs and MCA.

Figure 2
Words' type example: representation of the three-character levels on the plane spanned by the first two factors: (a) MCA; (b) JCA.

It may be observed that the similarity is good even on the second dimension, albeit not significant, whereas on the plane the Guttman effect appears again in good evidence. This may also depend upon the magnitude of the first two eigenvalues, that is sufficiently high to state that the three characters share around either 48% or 36% of the first and second factor respectively. Concerning the inertia reevaluation, this does not affect the interpretation of the single factors but in case of the spaces, since it acts as different multiplicative constants on the factors.

Let us now discuss the results of the JCA carried out on the same example. In the 2-dimensional solution1 1 The R package ca, that we used, gave a diagnostic when asked of running the 1-dimensional solution. the axes inertias are 0.2488 and 0.0272, with a proportion of 90.15% and 9.85%, respectively: considering only the first axis as significant, we may observe in Figure 2b´ a pattern of levels nearly identical to the one of MCA. Some differences appear on the second axis, in which are noticeable the very different positions of verbs and childish publications on the negative side and of long words and summaries on the positive one, but, once again, this may not be considered significant.

Eventually, we got the results of EMC. The seven (J - Q) non-zero eigenvalues and the corresponding percentages of explained and cumulate inertia are reported on Table 4. They are reported also in the figure nearby, where the average (166.66) corresponds to the dotted line. Thus, one may identify two major eigenvalues that summarize 44% of the total inertia, three others around the mean and two minor ones. Here, the Cattel test would suggest two factors, whereas the brokenstick considers random even the first one, since the threshold to consider it non-random would be 37.04%. These contradictory results lead us to compare them with the previous ones, therefore considering the first dimension as the "true" one, but also taking into account the second, at least for the graphical representation. In Figure 3 all levels are plotted on the plane spanned by the first two factors: indeed, the pattern of levels along the first axis is somehow similar to the ones resulting from both MCA and JCA but not so much: both L4 and L3 and even more WA and WN are exchanged, slightly modifying the interpretation of the results. On the opposite, the pattern along the second factor is so different that no agreement seems to be possible. In both cases, differences may result from the fact that here rare levels are found close to the centroid and the frequent ones are far away, whereas in the chi-square-based methods the opposite occurs. Indeed, this is the case of both L2 and WN that have the highest marginal values, whereas L4, with the lowest ones, is set toward the center.

Table 4
Eigenvalues, percentages of explained and cumulate inertia of the analysis of EMC on Words' type example. On the right, the pattern of the eigenvalues. The dotted line represents their average (166.66).

Figure 3
Words' type example: representation of the three-character levels on the plane spanned by the first two factors of the centered PCA on the Burt's table, corresponding to the Extended Matching Coefficient.

Let us look now at the one-dimensional reconstruction, as resulting by the SCAs of the three individual tables, by the MCA, and by Greenacre's JCA as reported in Table 5. The comparison of the SCA one-dimensional solutions with the original tables shows that the amount of the cumulate absolute residuals is in good agreement with the quality of the solution, as represented by the corresponding chi-square. For this reason, the low quality of the reconstruction of the table crossing kind of words with the type of publications depends on the significance of the second dimension of the SCA of this table, that here is not taken into account. At first glance, it is evident the high difference in the cumulate absolute residuals of MCA in respect to the other solutions, that is an important sign of the limits of MCA in respect to JCA.

Table 5
Original two-way contingency tables of words' type example and their reconstruction according to the first dimension of SCAs, MCA, adjusted MCA, JCA, and EMC with the corresponding cumulate absolute residuals.

Indeed, the quality of JCA one-dimensional reconstruction is in all cases acceptable, so that it is possible to observe a synthetic graphical representation of the three tables that is realistic. Finally, looking at the first layer obtained by EMC we find a behavior somehow comparable with the first layer of MCA: much worst for the first table, much better for the second and relatively equal for the third. This may also depend on the different way that this method uses to reconstruct the data table, as each layer does not represent a deviation from expectation but rebuilds the table anew. Thus, a better reconstruction must be expected through a larger number of factors. We did it by comparing the sum of the absolute differences in the partial reconstructions obtained by increasing the solution dimension: this could be done for the whole 7 factors of both MCA and EMC and only for the first 3 above the mean for both adjusted MCA and JCA. The results are given in Table 6.

Table 6
Absolute residuals of the reduced dimensional reconstructions of both the Burt's table and the two-way off-diagonal ones according to MCA, adjusted MCA and JCA respectively: to 0 correspond the deviations from independence.

In Table 6 are reported the cumulate absolute residuals of reconstructions of MCAs, both normal and adjusted, JCA, and EMC: they are both total and partitioned according to the diagonal matrices and the off-diagonal ones. In this latter case, the residuals are divided by two, that is the sum of the residuals of the individual 2 × 2 contingency tables, that form either triangular off-diagonal sub-matrix. The residuals for 0-dimension are the deviations from independence and the following are reported for all the allowed dimensions: 7 = J - Q for both MCA and EMC and 3 for both adjusted MCA and JCA, that corresponds to the number of singular values of the Burt's table larger than the average.

The first row reports the deviations in respect to the independence, that for EMC does not make any sense. For each method, the first column represents the inertia of the whole Burt's tablereconstruction: it is always descendant, as it should be expected, although with different slope: in this respect, EMC performs best by far. Indeed, the same occurs for what concerns the reconstruction of the diagonal tables: once again the EMC's performance is the best, albeit not as for the total table. Both MCA and EMC eventually rebuild totally the Burt's table, as expected. The surprises arise looking at the off-diagonal tables reconstruction: here, the MCA reconstruction is dramatically bad and problematic: indeed, all partial reconstructions are worst than the independence, that is the estimated frequencies are further from the observed than those due the independence, but the last one. That is, the first 5 dimensions, instead of improving the estimation, get it even worse! In this respect, EMC performs much better, as it is constantly decreasing.

If we look now at both adjusted MCA and JCA, we notice that, for what concerns the diagonal submatrices, they perform very badly, even worst than MCA, but this ought to be expected, specifically for JCA, in which the diagonal submatrices are intentionally neglected. On the other side, the improvement in the reconstruction of the off-diagonal ones is incredibly better, even in respect to EMC, with an excellent performance of JCA.

4 CONCLUSION

This study started with the aim to understand to what extent the JCA(20)20 GREENACRE MJ. 1988. Correspondence analysis of mutlivariate categorical data by weighted least squares. Biometrika, 75: 457-467. could be of help in identifying the true dimension of an analysis concerning a set of qualitative data. In this sense, the confidence interval proposed by Ben Ammou & Saporta (5)5 BEN AMMOU S & SAPORTA G. 1998. Sur la normalité asymptotique des valeurs propres en ACM sous l'hypothèse d'indépendance des variables. Revue de Statistique Appliquée, 46(3): 21-35., (6)6 BEN AMMOU S & SAPORTA G. 2003. On the connection between the distribution of eigenvalues in multiple correspondence analysis and log-linear models. REVSTAT-Statistical Journal, 1(0): 42-79. seems a better answer to this problem, that in the proposed example resulted in agreement with the most one-dimensional solution of the SCAs applied to the two-way tables.

During the study, the problem of the data reconstruction not only showed that MCA is bad in reconstructing the whole data table, in respect to EMC, even in what concerns the diagonal submatrices, but mostly concerning the off-diagonal ones, that are even more biased: thereconstruction of the two-way off-diagonal tables is for the most reduced-dimensional solutions worst than the independence table. Indeed, only redefining the inertia according to the adjusted MCA, a suitable reconstruction may be performed, albeit far from optimality, that is much better approached by JCA. It is interesting to note that, concerning the off-diagonal tables the adjusted MCA seems to perform better than EMC, a result that should be further studied. Eventually, the performance of JCA, as expected, is by no means the most suitable to deal with the off-diagonal tables, that is on the study of the relations between pairs of characters. As for the interpretation of the factors, JCA is not very different from MCA, whereas the method's differences of EMC impose a different interpretation that may be further studied. Thus, JCAseems the most promising development of MCA and its properties deserve some further deepening, including the three available programs (21)21 GREENACRE MJ. 2006. From Simple to Multiple Correspondence Analysis. In: GREENACRE & BLASIUS (Eds.), pp. 41-76., (41)41 TATENENI K & BROWNE MW. 2000. A Noniterative Method of Joint Correspondence Analysis. Psychometrika, 65(2): 157-165., (43)43 VERMUNT JK & ANDERSON C. 2005. Joint Correspondence Analysis (JCA) by Maximum Likelihood, European Journal of Research Methods for the Behavioral and Social Sciences, 1(1): 18-26.: indeed, a direct comparison of these results with those obtained through Greenacre's (22)22 GREENACRE MJ. 2007. Correspondence Analysis in Practice, 2nd Ed., London, Chapman and Hall. inertia evaluation through regression, may provide further insights on both methods, albeit our critics on the use of chi-square metrics for the whole Burt's table remain.

Indeed, no direct comparison of the results is strictly correct, since the methods considered in this work use different metrics, either chi-square or EMC, and/or optimize different criteria, as described. In addition, JCA solutions are not nested. These aspects deserve being taken into account while interpreting the results obtained by the different methods. Eventually, address the study in a different framework such as maximum-likelihood estimation, may be a fruitful alternative.

ACKNOWLEDGEMENTS

We want to thank the anonymous referees that significantly helped in improving our paper. This work was mostly carried out during the reciprocal visits of both authors in the framework of the bilateral agreement between Sapienza Universitá di Roma and Universidade Federal do Rio de Janeiro, of which both authors are the scientific responsible. The first author was also granted by his Faculty of belonging, the Facoltà d'Architettura ValleGiulia of Sapienza and FAPERJ of Rio de Janeiro. All institutions grants are gratefully acknowledged.

REFERENCES

  • 1
    ABDI H. 2007. Singular Value Decomposition (SVD) and Generalized Singular ValueDecomposition (GSVD). In: SALKIND N (Ed.), Encyclopedia of Measurement and Statistics. Thousand Oaks, CA: Sage: pp. 940-945.
  • 2
    ABDI H & VALENTIN D. 2007. Multiple Correspondence Analysis. In: SALKIND N (Ed.), Encyclopedia of Measurement and Statistics. Thousand Oaks, CA: Sage: pp. 651-657.
  • 3
    BARTON DE & DAVID FN. 1956. Some Notes on Ordered Random Intervals. Journal of the Royal Statistical Society, Series B, 18(1): 79-94.
  • 4
    BELTON V & STEWART T. 2002. Multiple Criteria Decision Analysis. Boston, Kluwer Academic Publishers.
  • 5
    BEN AMMOU S & SAPORTA G. 1998. Sur la normalité asymptotique des valeurs propres en ACM sous l'hypothèse d'indépendance des variables. Revue de Statistique Appliquée, 46(3): 21-35.
  • 6
    BEN AMMOU S & SAPORTA G. 2003. On the connection between the distribution of eigenvalues in multiple correspondence analysis and log-linear models. REVSTAT-Statistical Journal, 1(0): 42-79.
  • 7
    BENZÉCRI JP ET AL. 1973-82. L'Analyse des données, Tome 2. Paris: Dunod.
  • 8
    BENZÉCRI JP. 1979. Sur les calcul des taux d'inertie dans l'analyse d'un questionnaire. Les Cahiers de l'Analyse des Données, 4(3): 377-379.
  • 9
    CAMIZ S. 2005. The Guttman Effect: its Interpretation and a New Redressing Method. Τετραδία Αναλύσης Δεδομένων (Data Analysis Bulletin), 5: 7-34.
  • 10
    CAMIZ S & GOMES GC. 2013. Joint Correspondence Analysis Versus Multiple Correspondence Analysis: A Solution to an Undetected Problem. In: GIUSTI A et al. (eds.), Classification and Data Mining, Studies in Classification, Data Analysis, and Knowledge Organization, Berlin, Springer: pp. 11-18.
  • 11
    CAMIZ S & PILLAR VD. (In press). Identifying the True Dimension in Principal Component Analysis. Submitted to Community Ecology.
  • 12
    CATTELL RB. 1966. The scree test for the number of factors. Multivariate Behavioural Research, 1: 245-276.
  • 13
    ECKART C & YOUNG G. 1936. The approximation of one matrix by another of lower rank. Psychometrika, 1: 211-218.
  • 14
    FRAWLEY WJ, PIATETSKY-SHAPIRO G & MATHEUS CJ. 1992. Knowledge Discovery in Databases: An Overview, Artificial Intelligence Magazine, 13(3): 57-70.
  • 15
    GHOMARI A. 1983. Analyse Canonique d'une table de contingence. Étude asymptotique par échantillonnage. Thèse de l'Université de Pau et des Pays de l'Adour (France).
  • 16
    GÓES ART, STEINER MTA & PENICHE RA. 2015. Classification of Power Quality Considering Voltage Sags in Distribution Systems Using KDD Process. Pesquisa Operacional, 35(2): 329-352.
  • 17
    GOMES LFAM & DE ANDRADE RM. 2012. Performance evaluation in assets management with the AHP. Pesquisa Operacional, 32(1): 31-53.
  • 18
    GOWER JC & HAND DJ. 1006. Biplots. London, Chapman and Hall.
  • 19
    GREENACRE MJ. 1983. Theory and Application of Correspondence Analysis. London: Academic Press.
  • 20
    GREENACRE MJ. 1988. Correspondence analysis of mutlivariate categorical data by weighted least squares. Biometrika, 75: 457-467.
  • 21
    GREENACRE MJ. 2006. From Simple to Multiple Correspondence Analysis. In: GREENACRE & BLASIUS (Eds.), pp. 41-76.
  • 22
    GREENACRE MJ. 2007. Correspondence Analysis in Practice, 2nd Ed., London, Chapman and Hall.
  • 23
    GREENACRE MJ & BLASIUS J. (Eds.) 2006. Multiple Correspondence Analysis and Related Methods. Dordrecht (The Netherlands): Chapman and Hall (Kluwer).
  • 24
    GUTTMAN L. 1941. The Quantification of a Class of Attributes: a Theory and Method of Scale Construction. In: HORST P (Ed.) The Prediction of Personal Adjustment. New York, Social Science Research Council.
  • 25
    JACKSON DA. 1993. Stopping rules in principal component analysis: a comparison of heuristical and statistical approaches. Ecology, 74: 2204-2214.
  • 26
    JOLLIFFE IT. 2002. Principal Components Analysis. Berlin, Springer.
  • 27
    LANCASTER HO. 1949. The derivation and partition of χ2 in certain discrete distributions. Biometrika, 36: 117-129.
  • 28
    LANCASTER HO. 1963. Canonical Correlations and Partitions of χ2. Quarterly Journal of Mathematics, 14(1): 220-224.
  • 29
    LEBART L. 1976. The significance of Eigenvalues issued from Correspondence Analysis. COMPSTAT, Vienna, Physica Verlag: pp. 38-45.
  • 30
    LOPES YG & DE ALMEIDA AT. 2013. A multicriteria decision model for selecting a portfolio of oil and gas exploration projects. Pesquisa Operacional, 33(3): 417-441.
  • 31
    MALINVAUD E. 1987. Data analysis in applied socio-economic statistics with specialconsideration of correspondence analysis. Marketing Science Conference, Joy en Josas: HEC-ISA.
  • 32
    NARDY MNS. 2007. A sintaxe no interior das palavras - efeitos de gênero na lingua escrita contemporânea. PhD Thesis in Linguistics. Rio de Janeiro, Facultade de Leteras da Universidade Federal de Rio de Janeiro.
  • 33
    NENADIC O & GREENACRE M. 2006. Computation of multiple correspondence analysis, with code in R. In: GREENACRE AND BLASIUS (Eds), (2006), pp. 523-551.
  • 34
    NENADIC O & GREENACRE M. 2007. Correspondence analysis in R, with two- and three-dimensional graphics: the ca package. Journal of Statistical Software, 20(3): 1-13.
  • 35
    ORLÓCI L. 1978. Multivariate Analysis in Vegetation Research, 2nd ed. Den Haag: Junk.
  • 36
    PERES-NETO PR, JACKSON DA & SOMERS KM. 2005. How Many Principal Components? Stopping Rules for Determining the Number of Non-trivial Axes Revisited. Computational Statistics and Data Analysis, 49: 974-997.
  • 37
    ROY B & BOUYSSOU D. 1985. Aide à la décision: méthodes et cas. Paris, Economica.
  • 38
    R-PROJECT. 2009. http://www.r-project.org/
    » http://www.r-project.org/
  • 39
    SAPORTA G. 1975. Liaison entre plusieurs ensembles de variables et codage de données qualitatives. Thèse de troisième cycle, Paris VI, Université Pierre et Marie Curie.
  • 40
    SASSI RJ. 2012. An Hybrid Architecture for Clusters Analysis: Rough Sets Theory and Self-Organizing Map Artificial Neural Network. Pesquisa Operacional, 32(1): 139-163.
  • 41
    TATENENI K & BROWNE MW. 2000. A Noniterative Method of Joint Correspondence Analysis. Psychometrika, 65(2): 157-165.
  • 42
    THOMSON GH. 1934. Hotelling's method modified to give Spearman's g. Journal of Educational Psychology, 25: 366-374.
  • 43
    VERMUNT JK & ANDERSON C. 2005. Joint Correspondence Analysis (JCA) by Maximum Likelihood, European Journal of Research Methods for the Behavioral and Social Sciences, 1(1): 18-26.
  • 44
    WILLIAMS EJ. 1952. Use of scores for the analysis of association in contingency tables. Biometrika, 39: 274-289.
  • 1
    The R package ca, that we used, gave a diagnostic when asked of running the 1-dimensional solution.

Publication Dates

  • Publication in this collection
    Jan-Apr 2016

History

  • Received
    11 Sept 2015
  • Accepted
    20 Feb 2016
Sociedade Brasileira de Pesquisa Operacional Rua Mayrink Veiga, 32 - sala 601 - Centro, 20090-050 Rio de Janeiro RJ - Brasil, Tel.: +55 21 2263-0499, Fax: +55 21 2263-0501 - Rio de Janeiro - RJ - Brazil
E-mail: sobrapo@sobrapo.org.br