Luigi D'Ambra

Catanova for two-way contingency tables with ordinal variables using orthogonal polynomials

ABSTRACT The analysis of variance of cross-classified (categorical) data (CATANOVA) is a technique designed to identify the variation between treatments of interest to the researcher. There are well-established links between CATANOVA and the Goodman and Kruskal tau statistic as well as the Light and Margolin R 2 for the purposes of the graphical identification of this variation. The aim of this article is to present a partition of the numerator of the tau statistic, or equivalently, the BSS measure in the CATANOVA framework, into location, dispersion, and higher order components. Even if a CATANOVA identifies an overall lack of variation, by considering this partition and calculations derived from them, it is possible to identify hidden, but statistically significant, sources of variation.

Non-symmetric correspondence analysis with ordinal variables using orthogonal polynomials

Non-symmetrical correspondence analysis (NSCA) is a useful tool for graphically detecting the asymmetric relationship between two categorical variables. Most of the theory associated with NSCA does not distinguish between a two-way contingency table of ordinal variables and a two-way one of nominal variables. Typically, singular value decomposition (SVD) is used in classical NSCA for dimension reduction. A bivariate moment decomposition (BMD) for ordinal variables in contingency tables using orthogonal polynomials and generalized correlations is proposed. This method not only takes into account the ordinal nature of the two categorical variables, but also permits for the detection of significant association in terms of location, dispersion and higher order components.

Correspondence Analysis of Cumulative Frequencies Using a Decomposition of Taguchi's Statistic

Taguchis statistic has long been known to be a more appropriate measure of association for ordinal variables than the Pearson chi-squared statistic. Therefore, there is some advantage in using Taguchis statistic for performing correspondence analysis when a two-way contingency table consists of one ordinal categorical variable. This article will explore the development of correspondence analysis using a decomposition of Taguchis statistic.

Some Interpretative Tools for Non-Symmetrical Correspondence Analysis

Non-symmetrical correspondence analysis (NSCA) is a very practical statistical technique for the identification of the structure of association between asymmetrically related categorical variables forming a contingency table. This paper considers some tools that can be used to numerically and graphically explore in detail the association between these variables and include the use of confidence regions, the establishment of the link between NSCA and the analysis of variance of categorical variables, and the effect of imposing linear constraints on a variable.

Cumulative Correspondence Analysis of Two-Way Ordinal Contingency Tables

A suitable measure of association for two ordered variables is the doubly cumulative chi-squared statistic (Hirotsu, 1994). This statistic is obtained by considering the cumulative sum of cell frequencies across the variables. In this article, we explore the development of correspondence analysis which takes into account the presence of two ordered variables by partitioning the doubly cumulative chi-squared statistic.

Cumulative correspondence analysis of ordered categorical data from industrial experiments

Most studies of quality improvement deal with ordered categorical data from industrial experiments. Accounting for the ordering of such data plays an important role in effectively determining the optimal factor level of combination. This paper utilizes the correspondence analysis to develop a procedure to improve the ordered categorical response in a multifactor state system based on Taguchis statistic. Users may find the proposed procedure in this paper to be attractive because we suggest a simple and also popular statistical tool for graphically identifying the really important factors and determining the levels to improve process quality. A case study for optimizing the polysilicon deposition process in a very large-scale integrated circuit is provided to demonstrate the effectiveness of the proposed procedure.

Visualizing main effects and interaction in multiple non-symmetric correspondence analysis

Non-symmetric correspondence analysis (NSCA) is a useful technique for analysing a two-way contingency table. Frequently, the predictor variables are more than one; in this paper, we consider two categorical variables as predictor variables and one response variable. Interaction represents the joint effects of predictor variables on the response variable. When interaction is present, the interpretation of the main effects is incomplete or misleading. To separate the main effects and the interaction term, we introduce a method that, starting from the coordinates of multiple NSCA and using a two-way analysis of variance without interaction, allows a better interpretation of the impact of the predictor variable on the response variable. The proposed method has been applied on a well-known three-way contingency table proposed by Bockenholt and Bockenholt in which they cross-classify subjects by persons attitude towards abortion, number of years of education and religion. We analyse the case where the variables education and religion influence a persons attitude towards abortion.

The analysis of dependence for three ways contingency tables with ordinal variables: A case study of patient satisfaction data

For many questionnaires and surveys in the marketing, business, and health disciplines, items often involve ordinal scales (such as the Likert scale and rating scale) that are associated in sometimes complex ways. Techniques such as classical correspondence analysis provide a simple graphical means of describing the nature of the association. However, the procedure does not allow the researcher to specify how one item may be associated with another, nor does the analysis allow for the ordinal structure of the scales to be reflected. This article presents a graphical approach that can help the researcher to study in depth the complex association of the items and reflect the structure of the items. We will demonstrate the applicability of this approach using data collected from a study that involves identifying major factors that influence the level of patient satisfaction in a Neapolitan hospital.

A dimensional reduction method for ordinal three-way contingency table

For the study of association in three-way, and more generally multi-way, contingency tables the literature offers a large number of techniques that can be considered. When there is an asymmetric dependence structure between the variables the Marcotorchino index [Mar84] (as apposed to the Pearson chi-squared statistic) can be used to measure the strength of their association. When the variables have an ordinal structure, this information is often not take into account. In this paper we introduce a partition of the Marcotorchino index for three ordered categorical variables using a special class of orthogonal polynomials. A graphical procedure is also considered to obtain a visual summary of the asymmetrical relationship between the variables.

Hausman Principal Component Analysis

The aim of this paper is to obtain discrete-valued weights of the variables by constraining them to Hausman weights (−1, 0, 1) in principal component analysis. And this is done in two steps: First, we start with the centroid method, which produces the most restricted optimal weights −1 and 1; then extend the weights to −1,0 or 1.