Analysis of Rank Measures of Association for Ordinal Data from Longitudinal Studies

Abstract Consideration is given to longitudinal data settings in which an ordinal response variable is observed at two or more visits for each subject in two or more ordered groups with at least moderately large sample sizes (e.g., overall n ≥ 40). Rank measures of association between group and response are constructed at each time, and the covariance matrix of these measures is also estimated. Variation among the rank measures of association is then analyzed through weighted least squares methods with weights based on the estimated covariance matrix. Such methods permit evaluation of group × visit interaction as well as other effects of interest. Extensions of this type of analysis to situations with stratification, or concomitant variables, or missing data are also considered. Examples are provided for illustrative purposes.

[1]  Daniel O. Stram,et al.  Analysis of Repeated Ordered Categorical Outcomes with Possibly Missing Observations and Time-Dependent Covariates , 1988 .

[2]  Pranab Kumar Sen,et al.  On Some Convergence Properties of UStatistics , 1960 .

[3]  Dana Quade,et al.  Nonparametric Partial Correlation , 1967 .

[4]  D. Quade,et al.  On Comparing the Correlations within Two Pairs of Variables , 1968 .

[5]  L. A. Goodman,et al.  Measures of Association for Cross Classifications III: Approximate Sampling Theory , 1963 .

[6]  D. Quade,et al.  Nonparametric analysis of covariance by matching. , 1982, Biometrics.

[7]  M. Friedman.  The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance , 1937 .

[8]  G G Koch,et al.  A general methodology for the analysis of experiments with repeated measurement of categorical data. , 1977, Biometrics.

[9]  G G Koch,et al.  An application of multivariate ratio methods for the analysis of a longitudinal clinical trial with missing data. , 1978, Biometrics.

[10]  P. McCullagh.  Regression Models for Ordinal Data , 1980 .

[11]  M. Kendall.  Rank Correlation Methods , 1949 .

[12]  J. K. Benedetti,et al.  Sampling Behavior of Tests for Correlation in Two-Way Contingency Tables , 1977 .

[13]  E. Rödel,et al.  Fisher, R. A.: Statistical Methods for Research Workers, 14. Aufl., Oliver & Boyd, Edinburgh, London 1970. XIII, 362 S., 12 Abb., 74 Tab., 40 s , 1971 .

[14]  G G Koch,et al.  Some general methods for the analysis of categorical data in longitudinal studies. , 1988, Statistics in medicine.

[15]  C. Hardison.  Small-sample properties of a family of nonparametric partial correlation measures , 1981 .

[16]  H. B. Mann,et al.  On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other , 1947 .

[17]  G. Koch.  The use of non-parametric methods in the statistical analysis of a complex split plot experiment. , 1970, Biometrics.

[18]  D. F. Morrison,et al.  Multivariate Statistical Methods , 1968 .

[19]  L. A. Goodman,et al.  Measures of Association for Cross Classifications, IV: Simplification of Asymptotic Variances , 1972 .

[20]  Gary G. Koch,et al.  Analysis of categorical data , 1985 .

[21]  G G Koch,et al.  An analysis for compounded functions of categorical data. , 1973, Biometrics.

[22]  Donald A. Berry,et al.  Statistical Methodology in the Pharmaceutical Sciences , 1989 .

[23]  Gary G. Koch,et al.  Some Aspects of the Statistical Analysis of “Split Plot” Experiments in Completely Randomized Layouts , 1969 .

[24]  G. Koch,et al.  A review of some statistical methods for covariance analysis of categorical data. , 1982, Biometrics.

[25]  J. L. Gill,et al.  Design and analysis of experiments in the animal and medical sciences , 1980 .

[26]  W. Hoeffding.  A Class of Statistics with Asymptotically Normal Distribution , 1948 .

[27]  G. Koch,et al.  Some Views on Parametric and Non-Parametric Analysis for Repeated Measurements and Selected Bibliography , 1980 .

[28]  W. Kruskal,et al.  Use of Ranks in One-Criterion Variance Analysis , 1952 .