COMPUTER-PROGRAM FOR GENERALIZED CHI-SQUARE ANALYSIS OF CATEGORICAL DATA USING WEIGHTED LEAST-SQUARES (GENCAT)

被引:107
作者
LANDIS, JR
STANISH, WM
FREEMAN, JL
KOCH, GG
机构
[1] UNIV MICHIGAN, DEPT BIOSTAT, ANN ARBOR, MI 48109 USA
[2] UNIV N CAROLINA, DEPT BIOSTAT, CHAPEL HILL, NC 27514 USA
[3] YALE UNIV, SCH MED, NEW HAVEN, CT 06510 USA
来源
COMPUTER PROGRAMS IN BIOMEDICINE | 1976年 / 6卷 / 04期
关键词
D O I
10.1016/0010-468X(76)90037-4
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
GENCAT is a computer program which implements an extremely general methodology for the analysis of multivariate categorical data. This approach essentially involves the construction of test statistics for hypotheses involving functions of the observed proportions which are directed at the relationships under investigation and the estimation of corresponding model parameters via weighted least squares computations. Any compounded function of the observed proportions which can be formulated as a sequence of the following transformations of the data vector.sbd.linear, logarithmic, exponential or the addition of a vector of constants.sbd.can be analyzed within this general framework. This algorithm produces minimum modified chi-square statistics which are obtained by partitioning the sums of squares as in ANOVA. The input data can be either: frequencies from a multidimensional contingency table; a vector of functions with its estimated covariance matrix; or raw data in the form of integer-valued variables associated with each subject. The input format is completely flexible for the data and the matrices.
引用
收藏
页码:196 / 231
页数:36
相关论文
共 38 条
[1]   ON HYPOTHESES OF NO INTERACTION IN CONTINGENCY TABLES [J].
BHAPKAR, VP ;
KOCH, GG .
BIOMETRICS, 1968, 24 (03) :567-&
[3]   HYPOTHESES OF NO INTERACTION IN MULTIDIMENSIONAL CONTINGENCY TABLES [J].
BHAPKER, VP ;
KOCH, GG .
TECHNOMETRICS, 1968, 10 (01) :107-&
[4]  
Bishop Y. M. M., 1975, DISCRETE MULTIVARIAT
[5]   HOW TO USE RIDIT ANALYSIS [J].
BROSS, IDJ .
BIOMETRICS, 1958, 14 (01) :18-38
[6]   ON COMPARING CORRELATIONS WITHIN 2 PAIRS OF VARIABLES [J].
DAVIS, CE ;
QUADE, D .
BIOMETRICS, 1968, 24 (04) :987-&
[7]  
ELKHORAZATY N, 1975, THESIS U N CAROLINA
[8]  
Forthofer R N, 1974, Comput Programs Biomed, V3, P237, DOI 10.1016/0010-468X(74)90014-2
[9]   ANALYSIS FOR COMPOUNDED FUNCTIONS OF CATEGORICAL DATA [J].
FORTHOFER, RN ;
KOCH, GG .
BIOMETRICS, 1973, 29 (01) :143-157
[10]  
FORTHOFER RN, 1971, J BIOMEDICAL SYSTEMS, V2, P3