摘要:

AbstractBecause the evaluation of rodent carcinogenicity studies involves performing a statistical analysis at each tumor site encountered it is important to understand the extent to which this multiplicity affects the false positive rate. It is equally important to apply methods of accounting for this multiplicity in the analysis.In this paper we discuss one such method which involves calculating the overall significance level associated withP1, the most extreme isolated trendP‐value observed among the tumor sites encountered. The method constructs the distribution of trend scores simultaneously for each tumor site using a multiresponse randomization procedure. As such, it recognizes the discrete nature of the data and incorporates inherent dependencis that may exist between the tumor sites.For small studies it is possible to perform a complete rerandomization and compute an exact adjusted trendP‐value. However, for moderate or large studies the need exists for approximations based on efficient resampling plans. We report one such approximation proposed by Dr. John Tukey which involves correcting the exact Bonferroni upper bound. Also, we show that the independence assumption used in methods proposed by Mantel (1980) and Mantel et al. (1982) seems to be a reasonable approximation for the study discussed in the present report. This result needs to be supported further using additional stud

ISSN:0323-3847    

DOI:10.1002/bimj.4710300802

出版商:WILEY‐VCH Verlag    

年代:1988

数据来源: WILEY

摘要:

AbstractIn some clinical trials where the experimental treatment is found to be effective in increasing survival, an important question is how long should the patient remain under treatment. Although the trial may not be designed to specifically answer this question, comparisons of the hazard curves among the treatment groups can yield some useful information. The survival data may be modelled using a flexible set of hazard functions and specific models are then chosen for further examination. This paper illustrates the approach using data from the Beta‐Blocker Heart Attack Trial. Parametric and semi‐parametric models are fitted and likelihood methods are used to assess length of treatment effectiven

ISSN:0323-3847    

DOI:10.1002/bimj.4710300803

出版商:WILEY‐VCH Verlag    

年代:1988

数据来源: WILEY

ISSN:0323-3847    

DOI:10.1002/bimj.4710300804

出版商:WILEY‐VCH Verlag    

年代:1988

数据来源: WILEY

摘要:

AbstractThe distribution of the Hosmer‐Lemeshow chi‐square type goodness‐of‐fit tests (Čg,Ȟg) for the logistic regression model are examined via simulations designed to examine their behavior when most of the estimated probabilities are small or are expected to fall in a few deciles. The results of the simulations show statistic Čgshould be used when the two outcome groups (y= 0, 1) are not well separated, Δ≤2, where Δ2is the Mahalanobis distance. StatisticȞgshould be used when Δ ≥ 8. Either statistic may be used when 2 ≦ Δ ≦ 8. All tests should be used with caution when the proportion in the sample wi

ISSN:0323-3847    

DOI:10.1002/bimj.4710300805

出版商:WILEY‐VCH Verlag    

年代:1988

数据来源: WILEY

摘要:

AbstractA new modification of Berkson's minimum logit chi‐squared estimator in simple linear logistic regression is suggested in order to achieve reduction of first order bias of the estimator as well as in the model. Furthermore, unlike estimators currently available, our procedure is quite simple to apply in practice and is valid even in the presence of zero frequencies in the tabl

ISSN:0323-3847    

DOI:10.1002/bimj.4710300806

出版商:WILEY‐VCH Verlag    

年代:1988

数据来源: WILEY

ISSN:0323-3847    

DOI:10.1002/bimj.4710300807

出版商:WILEY‐VCH Verlag    

年代:1988

数据来源: WILEY

摘要:

AbstractSuppose we have two general populations π1, π2. Each object belonging to the population πi,i= 1, 2 is characterized by a random vectorX′ = (Z′,Y′), whereZis discrete andYis continuous. On a certain element which is a member of a one of the two populations a realization π′0=(z′0,y′0) of the random vectorXhas been observed and we want to classify that element. One of the possible methods of doing it is to estimate the density functions ofXin π1and π2and construct an estimated classification rule. In this paper the density estimates based on the orthogonal series (Hall, 1983) will be employed and the classification rule will be examined on a

ISSN:0323-3847    

DOI:10.1002/bimj.4710300808

出版商:WILEY‐VCH Verlag    

年代:1988

数据来源: WILEY

摘要:

AbstractThe use of the binomial distribution for the numerator and the negative binomial for the denominator in prospective studies leads to an unbiased estimate of relative risk and an unbiased estimate for combining experiments. Optimal sample sizes for groups are calculated and confidence intervals for the relative risk are presented. The efficiency of plans are evaluated by comparing variances and coefficients of variation.

ISSN:0323-3847    

DOI:10.1002/bimj.4710300809

出版商:WILEY‐VCH Verlag    

年代:1988

数据来源: WILEY

摘要:

AbstractThe concept of clustering of events within elements of a population is explored. Test statistics for testing the null hypothesis of a Poisson process versus the alternative of clustering are developed and their conditional null expectation and variance are derived. An application to an EEG registration of an epilepsy patient is presented.

ISSN:0323-3847    

DOI:10.1002/bimj.4710300810

出版商:WILEY‐VCH Verlag    

年代:1988

数据来源: WILEY

摘要:

AbstractEdge corrections are reported for the mean and variance of the average distance between a sampling point and the nearest event point in a spatial point pattern, for the case of a regular grid of sampling points. Using these corrections the point‐event analogue of the Clark‐Evans statistic is found to be a powerful detector of departures from randomness in the clustered direct

ISSN:0323-3847    

DOI:10.1002/bimj.4710300811

出版商:WILEY‐VCH Verlag    

年代:1988

数据来源: WILEY