摘要:

AbstractThe paper deals with the problem of sampling error of genotypic correlation estimated from a randomised block design. The Bootstrap method is used and two different procedures are studied. Both standard deviations and confidence intervals for the genotypic correlations are calculated in a real experiment. The results show that the estimates might be very unstable. Theoretical considerations indicate that large experiments are needed in order to obtain reliable estimates.

ISSN:0323-3847    

DOI:10.1002/bimj.4710320502

出版商:WILEY‐VCH Verlag    

年代:1990

数据来源: WILEY

ISSN:0323-3847    

DOI:10.1002/bimj.4710320503

出版商:WILEY‐VCH Verlag    

年代:1990

数据来源: WILEY

摘要:

AbstractParametric bootstrap methods for the construction of confidence intervals for the effective dose at level α(EDα) under the probit model for the dose‐response relationship are investigated. The standard maximum likelihood confidence intervals and percentile, centered percentile, studentized, bias corrected and better bias corrected bootstrap methods are compared in a simulation with 1000 Monte Carlo runs and 1000 bootstrap samples. Among the bootstrap methods, studentized and centered percentile methods are found to behave unfavorably with respect to observed coverage probability, whereas the bias corrected and better bias corrected bootstrap sometimes improve on the maximum likelihood method. The maximum likelihood method yielded very mixed results, but in our simulation none of the currently available bootstrap methods improved uniformly on this standard method. The methods are illustrated by an application to a bioas

ISSN:0323-3847    

DOI:10.1002/bimj.4710320504

出版商:WILEY‐VCH Verlag    

年代:1990

数据来源: WILEY

摘要:

AbstractA method of analysing regression data is presented for a model in which the dependent variable has a binomial distribution and the regression contains both fixed and random components. The method is then used to analyse treatment success data for a multicentre clinical trial study.

ISSN:0323-3847    

DOI:10.1002/bimj.4710320505

出版商:WILEY‐VCH Verlag    

年代:1990

数据来源: WILEY

摘要:

AbstractAssuming normality of observations an almost unbiased estimator of heritability (h2) for half‐sib data design has been obtained. Results of bias in the conventional estimator for several combinations of sire/dam number andh2are discussed for the balanced situatio

ISSN:0323-3847    

DOI:10.1002/bimj.4710320506

出版商:WILEY‐VCH Verlag    

年代:1990

数据来源: WILEY

摘要:

AbstractA table of Bonferroni Chi‐square limits is given forRsimultaneous tests, whereR= 1(1) 30(5) 150 at the level of α = 0.05 for 1 to 100 degrees of freedom. At the level α = 0.01 the limits are given forR= 1(1) 30, correspondingly. Additionally, a table of Bonferroni Chi‐square limits for 1 degree of freedom is given at both levels up toR(5%) = 300 andR(1 %) = 60 allowing for one‐sided as well as two‐sided testing. Reading of both tables is illustrated by biomedical examples. Methodological problems and clinical applications are discussed with special reference to configural frequency analy

ISSN:0323-3847    

DOI:10.1002/bimj.4710320507

出版商:WILEY‐VCH Verlag    

年代:1990

数据来源: WILEY

摘要:

AbstractRandom distributions ofNpoints in a square were simulated by computer, interpoint and nearest neighbour distances were calculated and corresponding distribution functions found. The results of 1000 repetitions of this process were used to find approximate 90, 95 and 99 % confidence bounds for the distribution functions. Calculations were performed in the rangeN= 10 toN= 350. Results are given in tabular form.

ISSN:0323-3847    

DOI:10.1002/bimj.4710320508

出版商:WILEY‐VCH Verlag    

年代:1990

数据来源: WILEY

摘要:

AbstractLet X1, X2,…, Xndenote a random sample from an unknown symmetric population distribution with mean, θ. The observations are subject to right censorship. The parameter, θ, is estimated using the Kaplan‐Meier median and various trimmed mean estimators (at α = .2, .3, and .4). A comparison is made between the Kaplan‐Meier median and the various trimmed means based on the estimated mean square errors. Ten underlying population distributions and two censoring distributions are co

ISSN:0323-3847    

DOI:10.1002/bimj.4710320509

出版商:WILEY‐VCH Verlag    

年代:1990

数据来源: WILEY

摘要:

AbstractIn the present paper, a multiple logistic model has been proposed to estimate the exposure‐specific incidence rates of several dichotomous etiologic factors from case‐control data. The relative probability of falling in a given exposure level with respect to the unexposed population for cases is expressed as a logistic function of the exposure levels (1 if exposed, 0 if not) of these factors. The odds ratio of the exposure category of cases relative to the controls comes out to be an exponential function of the exposure levels. It is shown how the maximum likelihood estimates of the logistic parameters can be obtained. The term ‘marginal effect’ of a factor is introduced. This is the effect of a factorAin the presence of one or more of other factors. The differenceSAbetween the marginal effect and the individual effect of a factorAis the increase in the effect ofAwhen it interacts with other factors. A simple relationship has been established between the Hogan et al. measure and the increasesSA,SB, … of two or more factors. Several numerical examples illustrate th

ISSN:0323-3847    

DOI:10.1002/bimj.4710320510

出版商:WILEY‐VCH Verlag    

年代:1990

数据来源: WILEY

摘要:

AbstractThe problem of characterizing the intrasubject variability in bioavailability/bioequivalence studies when the intrasubject variability differs from subject to subject is considered. To account for the heterogeneity of the intrasubject variability, a conditional random effects model that assumes a common coefficient of variation (CV) for each subject is proposed. This common CV is used to assess the intrasubject variability. Several procedures are developed for estimating the common CV. The proposed estimators are compared asymptotically. An extensive simulation study is conducted to study their finite sample performances.

ISSN:0323-3847    

DOI:10.1002/bimj.4710320511

出版商:WILEY‐VCH Verlag    

年代:1990

数据来源: WILEY