Weighted cumulative correspondence analysis based on a particular cumulative power divergence family

Abstract The Pearson’s $$X^2$$ X 2 statistic and the likelihood ratio $$G^2$$ G are most frequently used for testing independence or homogeneity, in two-way contingency table. These indexes members of a continuous family Power Divergence (PD) statistics, but they perform badly studying association between ordinal categorical variables. Taguchi’s Nair’s statistics have been introduced literature as simple alternatives to index tables with ordered It’s possible show, using parameter, how link obtaining new class called Weighted Cumulative Chi-Squared (WCCS-type tests). Therefore, main aim this paper is introduce divergence based on cumulative frequencies Divergence. Moreover, an extension Correspondence Analysis WCCS further properties shown.