Towards a Comprehensive Approach to the Analysis of Categorical Data.
Published 1 June 1983
Stephen E. Fienberg
Citations1
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper surveys the evolution of this comprehensive approach to categorical data problems and classes of problems for which it has proven useful and some speculation on unsolved methodological problems of current interest and on future developments.
Abstract
Abstract : Current methodology for the analysis of categorical data can be traced to two papers published in 1900, one by Pearson and one by Yule. The keys to the linking of their ideas have been the use of linear models and inferential tools due to Fisher. After 50 years of research, statisticians have come close to developing a comprehensive approach to categorical data problems that stresses three basic themes; interpretability, flexibility, and computability. This paper surveys the evolution of this comprehensive approach and classes of problems for which it has proven useful. A concluding section contains some speculation on unsolved methodological problems of current interest and on future developments. (Author)
Keywords
Computer ScienceMathematicsAgricultural and Biological Sciences
Contemporary Sociology A Journal of ReviewsDiscrete Multivariate Analysis: Theory and Practice.
5,160 Citations1975James R. Beniger, Yvonne Bishop +4 more
The London Edinburgh and Dublin Philosophical Magazine and Journal of ScienceX. <i>On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling</i>
3,978 Citations1900Karl Pearson
TechnometricsThe Analysis of Cross-Classified Categorical Data
1,957 Citations1979J. Wanzer Drane, Stephen E. Fienberg
BiometrikaExploratory latent structure analysis using both identifiable and unidentifiable models
1,585 Citations1974Leo A. Goodman
Journal of the American Statistical AssociationAn Exponential Family of Probability Distributions for Directed Graphs
1,143 Citations1981Paul W. Holland, Samuel Leinhardt
An exponential family of distributions that can be used for analyzing directed graph data is described, and several special cases are discussed along with some possible substantive interpretations.
International Statistical ReviewKarl Pearson and the Chi-Squared Test
660 Citations1983R. L. Plackett
Journal of the American Statistical AssociationCovariance Analysis of Censored Survival Data Using Log-Linear Analysis Techniques
532 Citations1981Nan M. Laird, Donald Olivier
It is demonstrated that many currently popular approaches to modeling survival data can be handled by using existing computer packages developed for the log-linear analysis of contingency table data, including the approaches of Glasser, Cox, Breslow, and Holford.
The Annals of Mathematical StatisticsMaximum Entropy for Hypothesis Formulation, Especially for Multidimensional Contingency Tables
401 Citations1963I. J. Good
Philosophical Transactions of the Royal Society of London Series A Containing Papers of a Mathematical or Physical CharacterVII. On the association of attributes in statistics: with illustrations from the material of the childhood society, &c
400 Citations1900George Yule
In the ordinary theory of statistical correlation, normal or otherwise, material susceptible of continuous variation, or at least of variation by a considerable number of discontinuous steps, certain practical cases arise, where either no variation is thinkable at all, or else is not measured or possibly measurable.
BiometricsThe Analysis of Rates and of Survivorship Using Log-Linear Models
378 Citations1980Theodore R. Holford
It is shown that the estimation of parameters involves the solution of identical systems of equations for data from either a Poisson process, an exponential distribution, a survival model or a generalized log-linear model that enables one to use algorithms for fitting log- linear models, such as iterative proportional fitting (IPF), for the analysis of rates or survivorship.
Journal of the American Statistical AssociationDiscrete Statistical Models With Social Science Applications.
323 Citations1983Clifford C. Clogg, Erling B. Andersen
Journal of the Royal Statistical Society Series C (Applied Statistics)The Fitting of Exponential, Weibull and Extreme Value Distributions to Complex Censored Survival Data Using GLIM
311 Citations1980Murray Aitkin, David Clayton
The purpose of the present paper is to describe the use of GLIM (Baker and Nelder, 1978) to fit exponential, Weibull or extreme value distributions, by expressing the likelihood in each case as a Poisson likelihood, with a log-linear model for the Poisson mean corresponding to the log- linear models for the hazard function.
The Annals of StatisticsMaximum Likelihood Estimates in Exponential Response Models
270 Citations1977Shelby J. Haberman
Springer series in statisticsMaximum Likelihood in Three-Way Contingency Tables
259 Citations1992M. W. Birch
Sociological MethodologyCategorical Data Analysis of Single Sociometric Relations
232 Citations1981Stephen E. Fienberg, Stanley Wasserman
BiometricsLife Tables with Concomitant Information
210 Citations1976Theodore R. Holford
A regression model for the analysis of survival data adjusting for concomitant information is developed and can lead to the log linear exponential model (Glasser [1967]) and the life table regression model of Cox [1972].
Journal of the American Statistical AssociationA New Model for Scaling Response Patterns: An Application of the Quasi-Independence Concept
156 Citations1975Leo A. Goodman
This model, using methods already developed for the study of quasi-independence in contingency tables, is shown how to test whether the model fits the observed data, estimate the proportion of intrinsically scalable (and unscalable) individuals, and estimate the distribution of the intrinsically scalable individuals among the d different scale types.
Journal of the American Statistical AssociationA Survey of Strategies for Modeling Cross-Classifications Having Ordinal Variables
80 Citations1983Alan Agresti
Journal of Multivariate AnalysisAn overview of multivariate data analysis
72 Citations1971A. P. Dempster
A cross section of basic yet rapidly developing topics in multivariate data analysis is surveyed, emphasizing concepts required in facing problems of practical data analysis while de-emphasizing technical and mathematical detail.
International Statistical ReviewCategorical Data Analysis: Some Reflections on the Log Linear Model and Logistic Regression. Part II: Data Analysis
57 Citations1982Peter B. Imrey, Gary G. Koch +4 more
Mathematical BiosciencesEstimating malaria incidence and recovery rates from panel surveys
48 Citations1980Burton H. Singer, Joel E. Cohen
This work presents a strategy for deciding whether two-state, two-wave panel data could have been generated by continuous-time Markov chains or certain mixtures of such chains, and test estimated conditional probabilities for membership in the set of conditional probabilities that can be generated by specific classes of models.
Journal of the American Statistical AssociationAn Incomplete Contingency Table Approach to Paired-Comparison Experiments
37 Citations1976Peter B. Imrey, William D. Johnson +1 more
Journal of EconometricsLoglinear models and categorical data analysis with psychometric and econometric applications
35 Citations1983Stephen E. Fienberg, Michael M. Meyer
Sociological MethodologyEstimation of Nonstationary Markov Chains from Panel Data
25 Citations1981Burton H. Singer
With a few exceptions (see Tuma, 1976; Littman and Mode, 1977; Pickens and Soyka, 1980), most attempts to model individual choice behavior with Markov and related models have interpreted "Markov" to mean time-homogeneous Markov.
Defense Technical Information Center (DTIC)USING INFORMATION ON ORDERING FOR LOGLINEAR MODEL ANALYSIS OF MULTIDIMENSIONAL CONTINGENCY TABLES*
4 Citations1982Stephen L Fienberg, Stephen E. Fienberg
Defense Technical Information Center (DTIC)Recent Advances in Theory and Methods for the Analysis of Categorical Data: Making the Link to Statistical Practice.
3 Citations1981Alan F. Karr