ANALYSIS OF DISCRETE-DATA - RERANDOMIZATION METHODS AND COMPLEXITY

被引:7
作者
BAGLIVO, J
OLIVIER, D
PAGANO, M
机构
[1] BOSTON COLL, DEPT MATH, CHESTNUT HILL, MA 02167 USA
[2] HARVARD UNIV, SCH PUBL HLTH, BOSTON, MA 02115 USA
[3] HARVARD UNIV, SCH MED, DANA FARBER CANC INST, BOSTON, MA 02115 USA
关键词
GOODNESS-OF-FIT TESTS; LOG-LINEAR MODELS; MAX TEST; MULTINOMIAL MODELS; CONTINGENCY TABLES; CHI-SQUARED TEST; LIKELIHOOD RATIO TEST; POWER DIVERGENCE STATISTIC;
D O I
10.1016/0167-9473(93)90112-7
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Analysis of discrete data, and especially contingency table data, plays a central role in biostatistics. Traditional methods rely on approximations based on asymptotic results which are very powerful but not always appropriate. In this article we show that efficient rerandomization methods may be developed for many commonly used models and tests: multinomial testing, specifically goodness-of-fit and max tests; and goodness-of-fit of log-linear models for contingency tables. The feasibility (complexity) of these algorithms is a function of the sufficient statistics for the models. By contrast, algorithms which require the explicit enumeration of all outcomes in the sample space are exponential in the degrees of freedom, and are usually not feasible except when sample sizes are unrealistically small. The algorithms we present are different from recently proposed methods since we show how to calculate permutation distributions of commonly used statistics rather than calculating p-values for exact tests, and we emphasize underlying probability formulas rather than implementation details.
引用
收藏
页码:175 / 184
页数:10
相关论文
共 19 条
[1]  
Aho Alfred V., 1974, DESIGN ANAL COMPUTER
[2]   METHODS FOR EXACT GOODNESS-OF-FIT TESTS [J].
BAGLIVO, J ;
OLIVIER, D ;
PAGANO, M .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1992, 87 (418) :464-469
[3]  
BERKSON J, 1978, J STAT PLAN INFER, V2, P27, DOI 10.1016/0378-3758(78)90019-8
[4]  
Bishop Y., 1975, DISCRETE MULTIVARIAT
[5]   STATISTICAL-ANALYSIS OF CYTOGENETIC ABNORMALITIES IN HUMAN CANCER-CELLS [J].
BRODEUR, GM ;
TSIATIS, AA ;
WILLIAMS, DL ;
LUTHARDT, FW ;
GREEN, AA .
CANCER GENETICS AND CYTOGENETICS, 1982, 7 (02) :137-152
[6]  
CRESSIE N, 1984, J ROY STAT SOC B MET, V46, P440
[7]   PEARSONS-X2 AND THE LOGLIKELIHOOD RATIO STATISTIC-G2 - A COMPARATIVE REVIEW [J].
CRESSIE, N ;
READ, TRC .
INTERNATIONAL STATISTICAL REVIEW, 1989, 57 (01) :19-43
[8]  
Freeman PR, 1979, J APPL STAT, V28, P333
[9]  
Haberman S. J., 1974, ANAL FREQUENCY DATA, VIV
[10]   IN DISPRAISE OF THE EXACT TEST - REACTIONS [J].
KEMPTHORNE, O .
JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1979, 3 (03) :199-213