摘要:

Consider a deterministic tournament amongNplayers in which the bestMare to be found and ranked. A tournament design is presented in which the ratio of the number of comparisons to the minimum number required asymptotically approaches one. At any given stage,n− 1 players have been considered. The rath is compared with the player with temporary rank min (M, [n/2]). If, as a result, thenth is determined to be possibly one of the firstM, then further comparisons are made by halving the set of temporarily ranked players within which thenth may be.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479967

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

If the reported data of an experiment have been subject to selection, then inference from such data should be modified accordingly. We investigate the modification required to the face-value likelihood. In particular, we derive conditions under which no modification is necessary and the data can be taken at face value.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479968

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

For tests of a single parameter in the binomial logit model, Wald's test is shown to behave in an aberrant manner. In particular, the test statistic decreases to zero as the distance between the parameter estimate and null value increases, and the power of the test, based on its large-sample distribution, decreases to the significance level for alternatives sufficiently far from the null value.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479969

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

The Kaplan-Meier estimator for the survival function in the censored data problem can be expressed for finite samples as an explicit function of two empirical subsurvival functions. This function is the natural one that expresses the survival function in terms of the sub-survival functions. As an illustration of the usefulness of expressing the Kaplan-Meier estimator in this way, the strong consistency of the Kaplan-Meier estimator is easily proved.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479970

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

Exact and approximate methods are given for counting the number ofr × ccontingency tables with fixed margins. The approximate methods are extended to estimate the number ofr × c × scontingency tables with given first-order margins.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479971

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

Many regression programs include a tolerance test that does not allow a variable to enter the regression if its correlation with the previously entered variables exceeds a specified level. This is done to achieve computational stability by assuring that the correlation matrixCof the independent variables is not nearly singular. However, for any specified tolerance level, there is an example in which the entering variables pass the tolerance test but the computation is extremely unstable. A bound for the condition ofCisptimes the trace ofC-1, which can be monitored instead of tolerance to assure stability.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479972

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

A matrix containing all information sufficient for the computation of MINQUE variance component estimates (Rao 1973) in random and mixed models is exhibited. The use of this matrix leads to an efficient computer algorithm which saves both computer time and memory usage.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479973

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

New Bayesian estimates are proposed for multinomial probabilities, when the prior distribution is a mixture of Dirichlet distributions. They are based upon a distributional approximation for the χ2statistic and may be contrasted with the frequentist approximations recommended by other authors. An alternative is also suggested to the χ2goodness-of-fit test, when it is employed as a preliminary test of significance. The new procedure possesses remarkably different properties; it is used to reanalyze some data from Mendel's pea breeding experiment. The results suggest that the χ2test may have no particular relevance in preliminary testing situations.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479974

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

Some justifications for the Roy-Tiku (1962) approximation to the distributions of sample variances by Laguerre polynomial series are provided. It is shown that if one approximates any nonnegative continuous random variable by a finite series of Laguerre polynomials up to thekth degree, then the firstkmoments of the approximated distribution are equal to the firstkmoments of the random variable. We also derive an alternative Laguerre series approximation, including the Box (1953) approximation as a special case.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479975

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

We consider distributions of quadratic forms of the typeQk= Σkj= 1cj(xj+aj)2, where thexj's are independent and identically distributed standard normal variables, and wherecjandajare nonnegative constants. Exact significance points ofQk, for selected values ofcjand allaj= 0, have been published fork= 2, 3, 4, and 5. We give significance points fork= 6, 8, and 10. We propose and assess two new approximations toQk: (1) fitting a Pearson curve with the same first four moments asQk; and (2) fittingQk=Awr, wherewhas the χ2pdistribution, and whereA, r, andpare determined by the first three moments ofQk.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479976

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor