摘要:

One question which often arises in feedback systems is how often should one sample to know the options with which control adjustments may be made. In an optimal control scheme. we suppose that a control arrangement will be employed in which the sampling interval ishunits long wherehis an unknown integer. The equations describing both the dynamics and the noise process now depend on this intervalh. Now considering the noise process and the cost and frequency of sampling, a reasonable cost function is formulated as a function ofh. The optimum time interval at which surveillance should be conducted, i.e. observations taken and control adjustment action taken, is obtained by minimizing the above cost function.

ISSN:0040-1706    

DOI:10.1080/00401706.1979.10489717

出版商:Taylor & Francis Group    

年代:1979

数据来源: Taylor

摘要:

The switching characteristics among normal, reduced and tightened inspection in MIL-STD-105D. the most widely used sampling standard, are studied with Markov chain theory and signal flow graph theory. These studies will also contribute to the design of new switching rules providing desired characteristics.

ISSN:0040-1706    

DOI:10.1080/00401706.1979.10489718

出版商:Taylor & Francis Group    

年代:1979

数据来源: Taylor

摘要:

Five acceptance sampling plans in which the flow of items produced by a continuous process is regarded as a flow of groups of items are considered in terms of the amount of inspection and the average outgoing quality. Some general results and nomograms to aid in the choice of a plan are given.

ISSN:0040-1706    

DOI:10.1080/00401706.1979.10489719

出版商:Taylor & Francis Group    

年代:1979

数据来源: Taylor

摘要:

This paper presents tables for confidence limits on the MTBF of an exponentiadl istribution using observationsfr om sequential tests of MIL-STD 781. An example shows the use of the tables. The theory and calculation of the tables are explained in the Appendices.

ISSN:0040-1706    

DOI:10.1080/00401706.1979.10489720

出版商:Taylor & Francis Group    

年代:1979

数据来源: Taylor

摘要:

This paper presents tables for confidence limits for the parameters, percentiles. and reliabtlities of normal and lognormal life distributions using best linear unbiased estimates (BLUES) from singlyfailurecensored data. These tables also provide approximate confidence limits for singlytimecensored data. The tables covern= 2(1)10,r= 2(1)n, and various conlidence levels.

ISSN:0040-1706    

DOI:10.1080/00401706.1979.10489721

出版商:Taylor & Francis Group    

年代:1979

数据来源: Taylor

摘要:

Prediction equations constructed from multiple linear regression analyses are often intended for use in predicting response values throughout a region of the space of the predictor variables. Criteria for evaluating prediction equations, however, have generally concentrated attention on mean squared error properties of the estimated regression coefficients or on mean squared error properties of the predictor at the design points. If adequate prediction throughout a region of the space of predictor variables is the goal, neither of these criteria may be satisfactory in assessing the predictor. In this paper integrated mean squared error is used as a criterion to determine when the least squares, principal component, and ridge regression estimators of regression coefficients can produce satisfactory prediction equations in the presence of a multicollinear design matrix.

ISSN:0040-1706    

DOI:10.1080/00401706.1979.10489722

出版商:Taylor & Francis Group    

年代:1979

数据来源: Taylor

摘要:

The critical values for testing for a two-phase regression are given by simulation methods. The dependence of the test on the values of the independent variable is investigated. and a comparison is made between the critical values of the simulation and those given by using Bonferroni's inequality.

ISSN:0040-1706    

DOI:10.1080/00401706.1979.10489723

出版商:Taylor & Francis Group    

年代:1979

数据来源: Taylor

摘要:

Maximum likelihood estimates of the parameters for logistic discrimination show considerable bias in small samples, Adjustment by a bias correction using higher derivatives of the log likelihood is shown to be effective in a simulation study. The procedure is illustrated in a medical diagnosis problem.

ISSN:0040-1706    

DOI:10.1080/00401706.1979.10489724

出版商:Taylor & Francis Group    

年代:1979

数据来源: Taylor

摘要:

A procedure is described for screening using a variableXwhich will guarantee that 100δ% ofYvalues for screened items will be betweenLandU(two specification limits). The random variables (X,Y) are assumed to have a joint bivariate normal distribution. Tables for implementing the procedure are also given. The procedure is then extended to the case where all the parameters are unknown.

ISSN:0040-1706    

DOI:10.1080/00401706.1979.10489725

出版商:Taylor & Francis Group    

年代:1979

数据来源: Taylor

摘要:

Tables of the upper α-pointsmα;k*,vof the studentized maximum modulus distribution with parameterk* andvdegrees of freedom are given for α = .01, .05, 10, and .20, twelve values 01V, andk* =k(k− 1)/2 fork= 3(1)20. The tables are of use in applying Hochberg's GT2-Method [6] of multiple comparison and extend the use of this method to cases withk≤ 20 means. As conjectured in [15]. the GT2-Method is in almost all cases the strongest of several competitors of Spodtvoll and Stoline'sT′-Method [11] for carrying out the set ofk* pairwise comparisons between the means ofkgroups with arbitrary sample sizes. The auxiliary tables of [15], in which theT′-Method and other procedures are compared, are extended here. These tables should aid the user in choosing between theT′ and GT2-Methods. The results of the comparisons continue to support the fact that theT-Method is preferred if the unbalance of the sample sizes is slight and thatTbecomes a stronger competitor as α increases.

ISSN:0040-1706    

DOI:10.1080/00401706.1979.10489726

出版商:Taylor & Francis Group    

年代:1979

数据来源: Taylor