摘要:

For life testing from the exponential distribution the sequential probability ratio test is used to test hypotheses in which the exponential parameter and its alternatives change value a finite number of times during the test. Applications to nonexponential life distributions are indicated.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490343

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

A method is presented for reducing a curvilinear response to a set of numbers which describe the curve. An analysis of such numbers including reconstruction of the curves is presented. A numerical example is used to illustrate the entire procedure.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490344

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

The magnitudeSof a certain signal is to be measured in the presence of a noiseN. In order to improve the accuracy of the measurement, it will be repeated and essentially averaged by summing all the measurements. Consider a measuring device which at each stage of measurement adds or subtracm exactly one bit at the low end of a counter. Assume that the signalStogether with an additive noiseNis essentially restricted to some interval say −1 ≤S≤ 1. The interval [−1, 1] is divided by a mesh of reference values

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490345

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

When the substrate of a 2n–qfactorial or fractional factorial experiment may be expected to show trends representable by linear and quadratic terms in time, then certain orderings spaced at equal time-intervals permit better estimation of the effects than do others. Some of these ordered plans are given forp–q= 2, 3, 4, 5. Simple methods are given for computing effects, trends, and efficiencies.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490346

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

Methods are proposed for specifying additional runs to be included with the data of a non-orthogonal, undesigned experiment, in such a way as to increase the statistical power of the total experiment and to decrease the statistical dependence among the controllable variables. The methods are illustrated.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490347

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

In previous work [1] I have presented an interval estimation procedure applicable to singly censored samples from any univariate population depending only on a scale parameter and location parameter; the procedure applies to several censoring criteria. For any parametric function, the procedure gives an interval estimate based on two confidence statements each at the 1 – 2α level; these estimates were shown to be at least at the (1 – 2α)2level for any size sample and converge, for large samples, to population values. The present work concerns itself specifically with censored samples fromN(μ, σ) and studies the possibility of reducing the conservatism of the procedure. It is shown that, asymptotically, the procedure is at least at the 1 – 2α level. For some special parametric functions, theoretical considerations and fairly extensive computations strongly suggest that the procedure is at least at the 1 1 – 2α level even for small samples. It is conjectured that this property carries over to other functions and other distributions involving only a location and a scale parameter.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490348

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

Classical problems associated with paths composed of straight line segments with independent orientations, which have a continuous distribution, are discussed. Moment formulas are obtained for the distance between initial and terminal points, and a new approximation discussed. The Rayleigh approximation is used to derive approximations to other characteristics of the random path.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490349

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

An iterative procedure is given for the estimation of a vector of parameters some of which may be common to more than one of a set of nonlinear regression equations in the model presented. The procedure is given for the situation when the covariance matrix in the model is known and is extended to include the model when the covariance matrix is unknown. The covariance matrix allows for correlation between observations made on different regression equations but for the same value of the independent vector of variables. Under certain assumptions the procedure is shown to converge to a consistent estimator of the vector of parameters with probability one. The procedure is illustrated with data from a compartmental tracer experiment.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490350

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

An “index of discrepancy” is introduced to measure the deviation of an actual population from the population stated as null-hypothesis. The index is estimated by a statistic proportional to the familiar expression Σ(o–e)2/e, used in chi-square tests, with a subsequent correction for bias. The index can be used for any simple hypothesis and also as a measure of heterogeneity or of association in contingency tables. Asymptotic confidence limits (for large samples) are established on the basis that (under suitable conditions) Σ(o–e)2/eapproaches a non-central chi-square distribution. Nomograms are provided to facilitate the computation of the confidence limits.

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490351

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor

摘要:

In this paper an attempt has been made to calculate the producer's and the consumer's risks for non-normal populations. The effect of the peakedness parameter (kurtosis: λ4= β2– 3) only has been taken into consideration. In cases of platykurtic populations (λ4< 0), if the specification limits are set near the mean, then both the producer's and the consumer's risks will be greater than their respective normal theory values; and if the specification limits are set far from the mean, then both the risks will be smaller than their corresponding normal theory values. The situations will be the other way round in cases of leptokurtic populations (λ, > 0).

ISSN:0040-1706    

DOI:10.1080/00401706.1966.10490352

出版商:Taylor & Francis Group    

年代:1966

数据来源: Taylor