摘要:

Response surface methodology, an experimental strategy initially developed and described by Box and Wilson, has been employed with considerable success in a wide variety of situations, especially in the fields of chemistry and chemical engineering. It is the purpose of this paper to review the literature of response surface methodology, emphasizing especially the practical applications of the method. A comprehensive bibliography is included.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490404

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

This paper describes life test sampling plans which assume only that the life distribution has increasing or decreasing failure rate. Tables are presented showing the minimum number of items necessary to assure a specified mean life or percentile life when the experiment time is fixed in advance.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490405

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

This paper describes modifications of the sequential, two-sample, grouped, rank tests developed earlier. A modified, sequential, configural rank test is discussed in some detail and is a procedure based on rerankings of observations as new groups of observations are obtained sequentially. A numerical application is given.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490406

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490407

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

The binomial group-testing problem is extended to the case in which the common probabilitypof a unit being defective is unknown. A Bayes “non-mixing” procedureR(1)is derived and compared with other procedures, in particular with the corresponding procedureR1that requires the knowledge ofpand with another procedure based on continually revising the maximum likelihood estimate ofp; the latter is called an empirical Bayes solution. Finally, a Bayes procedure derived in the Appendix allows “mixing” and this is conjectured to be the unrestricted Bayes solution; the improvements due to “mixing” are shown to be small in Table III. Several applications of the general problem of group-testing are discussed in the introduction and this virtually constitutes a general review of the subject. After the procedureR(1)is defined a detailed illustration is given in section 2.1 showing how to carry out this procedure with the use of Tables I and II. Lower bounds for the Bayes risk associated with any group testing procedure for unknownpare given in Table III; one of these bounds, based on information theory, is derived in section 4.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490408

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

Discriminant functions are based on samples which are assumed to be correctly classified. If some members of the original samples are incorrectly classified the utility of the discriminant function may not be seriously affected.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490409

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

In short routine experiments involving small samples from a normal distribution, it is often found to be more convenient to use the sample mean absolute deviation (m) rather than the sample standard deviation (S) in forming confidence intervals. Approximate and exact methods for correctly usingmin confidence intervals are given. The expected lengths of the intervals usingmare then compared with the expected lengths of the intervals usingS. The results indicate that the increase in expected length usingmrather thanSis insignificant, whereas there is a decrease in expected length usingmwhen one can take an additional observation.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490410

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

In the analysis of experimental data one may seek to solve a system of equations which is inconsistent. If the means and variances for the observed data are used, a least squares estimate of the solution of the system may be so improbable as to lead to the conclusion that some of the data should be discounted or ignored. Aposterioriprobability provides a rational means of attaching different weighting factors to the various data. If one assumes an aprioriprobability that the observed means and variances are correct and also some a priori probability that the distribution of errors has some alternative form, one can make use of Bayes technique to obtain a weighting of the data. A general description of this method is given and the method is then applied to a well-known problem of the determination of physical constants.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490411

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

We tabulate percentage points of the beta distributionzIIsuch thatFβ(zII|r,n) = II. The percentage points are given to four decimal places for II = .01, .05(.05).95, .99,n= 2(1)30, 40, 50 andt= 1(1)[n/2]. The tables are primarily for use in Bayesian analysis of Bernoulli processes as treated in Raiffa and Schlaifer [7]. Numerical integration of a function with respect to the beta distribution is also discussed. An example is given.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490412

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

A randomisation procedure is given for making tests on the coefficients of regression equations developed from data which arise from a general multivariate distribution, not necessarily Normal. The procedure makes use of a six card computer subroutine which randomly permutes an array of numbers. This subroutine is extremely useful and can be employed in many other types of problems.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490413

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor