Project/Area Number |
05302064
|
Research Category |
Grant-in-Aid for Co-operative Research (A)
|
Allocation Type | Single-year Grants |
Research Field |
Statistical science
|
Research Institution | KYUSHU UNIVERSITY |
Principal Investigator |
YANAGAWA Takashi Kyushu Univ Graduate School of Math Professor, 大学院・数理学研究所, 教授 (80029488)
|
Co-Investigator(Kenkyū-buntansha) |
OHASHI Yasuo Univ of Tokyo Fac of Medicine Professor, 医学部, 教授 (00134461)
YOSHIMURA Isao Tokyo Univ of Science Fac of Engin Professor, 工学部, 教授 (30010797)
SATO Toshiya Inst of Statistical Math Associate Professor, 助教授 (50187217)
TANGO Toshiro National Inst of Health Epidemiology Head, 疫学部, 室長 (70124477)
HIROTSU Chihiro Univ of Tokyo Fac of Engineering Professor, 工学部, 教授 (60016730)
大瀧 恵 広島大学, 放射線医学研究所, 助教授 (20110463)
|
Project Period (FY) |
1993 – 1994
|
Project Status |
Completed (Fiscal Year 1994)
|
Budget Amount *help |
¥12,500,000 (Direct Cost: ¥12,500,000)
Fiscal Year 1994: ¥6,100,000 (Direct Cost: ¥6,100,000)
Fiscal Year 1993: ¥6,400,000 (Direct Cost: ¥6,400,000)
|
Keywords | Toxicological data / Epidemiological data / Clinicalcomparison / Mutagenecity assay / Spacial aggrigation / Summary hazard ratio / Growth curves / Multicenter clinical trials / 同等性の検定 / 最大カイニ乗検定 / 集積性の検定 / リスク評価 / 最大カイ二乗検定 |
Research Abstract |
[Analysis of Toxicological Data]. "Statistical Analysis of Toxicological Data" is published (Yoshimura, Ohashi) . This is the first book of this kind written in Japanese. Also published is the "Biostatistics in the Study of Toxicology" (Sakuma, Yanagawa, Yoshimura eds.) which is the proceedings of the first International Biostatistics Conference in the Toxicology. A new method for the determination the of the no-observed-adverse-effect level is developed. Statistical analysis of data in mutageneity assays in the case of rodent micronucleus assay is also explored. [Methodologies in Epidemiology]. "Biostatistics in Human Cancer" (Yanagawa, Ohashi, Tango, Yanagimoto eds.) which is the proceedings of the fourth Japan-US Biostatistics Conference in the Study of Human Cancer is published : also published is the "Statistics for medical Science" (Tango). These two publications have given an inmense effect to researchers in the field of medical science. Mantel-Haenszel estimators are generalized
… More
for 2xJ table (J>2) . A statistical test for spaciai aggrigation of disease is developed. Meanings of interaction and standardization are syudied in depth and clarified from the point of view of causality. Estimators of summary hazard ratio are developed when there exist effect modification. [Statistical Methods for Clinical Data]. A set of new statistical methods are developed based on accumulated chi-squares. These methods are anticipated to replace the classical analysis of variance. Statistical testing procedures which adjust for the inbalance of background factors and to detect the equivalence or more than equivalence of two drugs is developed. A method is explored on the Meta Analysis so that it enables researchers to treat multicenter clinical trials. [Basic thory]. A new analysis of growth curves is explored by introducing linear models among parameters in growth-curve, algorithm of the method is developed and computer program is explored which can be used on parsonal computer. As is seen, for example, in the invited special lecture "Goodness of statistical estimator, from Pitagorian point of view" delivered at the Mathematical Society of Japan, basic theory of biostatistics is also very much advanced. Less
|