摘要:

AbstractConsider the model yijk=u ± ai± bi± cij± eijki=1, 2,…, t; j=1, 2,…b; k=1, 2,…,nijwhere μ is a constant and ai, bi, cijare distributed independently and normally with zero means and variances Δ2Δ2/bdijand δ2respectively. It is assumed that di's, and dij's are known (positive) constants (for alliandj). In this paper procedures for estimating the variance components (Δ2, Δ2band Δ2a) and for testing the hypothesis Hoc:Δ2c/Δ2= y3and Hoa:Δ2b/Δ2= y4(where y2, y3, and y4, are specified constants) are presented. A generalization for the mixed model case is discussed

ISSN:0323-3847    

DOI:10.1002/bimj.4710200302

出版商:WILEY‐VCH Verlag    

年代:1978

数据来源: WILEY

摘要:

AbstractA mathematical formula for determining the sampling frequency on the basis of the coefficients of variation of the various parameters of interest of water quality is developed.The uncertainty or the variability of each sampling program is expressed as a function of the sampling design variable in order to construct a performance index which will enable one to select the best sampling program. The notion of information content is used as a basis for the performance index.Under certain circumstances, the information content of a single composite is more than that of a single grab sample. However, the average of a series of grab samples provides more information than the average of a series of composite samples. This happens because the individual information content (entropy) of discrete portions of the composite sample are confounded in the average.It is shown that if the variability of the proportions is greater than the upper limit (provided in Table 2), the information content of the composite, where the volume of each discrete portion is collected in proportion to the rate of flow (or discharge) at the time it is collected, is much smaller than that of the same number of grab samples or composite samples collected at constant volume‐constant time intervals.Time constant, volume proportional‐to‐flow since last sample composites have the same disadvan

ISSN:0323-3847    

DOI:10.1002/bimj.4710200303

出版商:WILEY‐VCH Verlag    

年代:1978

数据来源: WILEY

摘要:

AbstractIncomplete contingency tables, i.e. tables with structurally caused empty cells, are analysed by means of so‐called quasilog‐linear models. In general the expected values can be calculated by means of iterative cyclic adaption to corresponding marginals of the empirical contingency tables (in the same way as in complete tables) under different hierarchical hypotheses concerning the parameters of the models.For important cases of 2‐dimensional contingency tables it is possible to demonstrate that expected values and test statistics are to find in a closed form.If all 2‐dimensional sub or partial tables of a 3‐dimensional table can be assigned to such cases then the hypotheses of classes (AB×C) (

ISSN:0323-3847    

DOI:10.1002/bimj.4710200304

出版商:WILEY‐VCH Verlag    

年代:1978

数据来源: WILEY

摘要:

AbstractThis paper considers the probability distribution of the volume of a certain substance (e.g. river discharge, rainfall, deposites of clay, organism, etc.) that flows into a semi‐infinite reservoir before its first emptiness for continuous and homogeneous input process when the substance is released at unit rate per unit of time. A few moments of the distribution have been computed. A generalized gamma, and a generalized exponential distributions as particular cases are also discussed. Some possible applications of the generalized negative exponential distribution have been mentioned. These distributions are in fact the continuous analogues of the discrete LAGRANGE distributions recently considered by JAIN and other

ISSN:0323-3847    

DOI:10.1002/bimj.4710200305

出版商:WILEY‐VCH Verlag    

年代:1978

数据来源: WILEY

摘要:

AbstractA new class of phase‐confounded designs is suggested. The class possesses the property that if in a year one of the rotations carries the test crop all other rotations also do. It also leads to equal block sizes when the rotations are structured in specified ways. Conditions under which designs of this class exist as well as method of constructing them are discusse

ISSN:0323-3847    

DOI:10.1002/bimj.4710200306

出版商:WILEY‐VCH Verlag    

年代:1978

数据来源: WILEY

摘要:

AbstractTwo simultaneous distribution free test procedures to test the homogeneity ofKsamples of response curves measured atTpoints of time each are proposed which react upon the shape of the response curve. One procedure is based on the comparison ofK T‐tupels of FRIEDMAN‐rank sums, the other on the comparison ofK T × T‐incidence tables, which first were introduced by KANNEMANN (1976). The application of the two procedures is illustrated by a numerical example. In the discussion the tests are compared with each other and with concurring

ISSN:0323-3847    

DOI:10.1002/bimj.4710200307

出版商:WILEY‐VCH Verlag    

年代:1978

数据来源: WILEY

摘要:

AbstractIf we have independent random variables the solution of BECHHOFER's selection problem in special cases is easily applied because we can use tables of a standardized multivariate normal distribution. The aim of this note is to show how such tables are also applicable in a case of correlated random variables like the estimates of treatment effects in BIB and BCB. Formulae for a choice of minimal sample sizes are also given.

ISSN:0323-3847    

DOI:10.1002/bimj.4710200308

出版商:WILEY‐VCH Verlag    

年代:1978

数据来源: WILEY

摘要:

AbstractAnalysis of partial diallel cross repeated over environments is discussed. Formulae are given to estimate the general combining ability effects and their interaction effects with environments. Analysis of variance table along with expected mean squares is given.

ISSN:0323-3847    

DOI:10.1002/bimj.4710200309

出版商:WILEY‐VCH Verlag    

年代:1978

数据来源: WILEY

摘要:

AbstractTwo sequential charts designed by I. BROSS, used to analyze serial data for two treatment groups, are studied in this paper. Simulation techniques, rather than theoretical calculations, have been used to determine more complete characteristics of these designs. Of particular interest are the estimates of percentiles of the distribution function of “sample size required to reach a statistical decision”. The distribution parameters of the one‐sided tests, not studied by BROSS, are also given.Es werden 2 sequentielle Pläne von I. BROSS untersucht, die zur Analyse von seriellen Daten für 2 Behandlungsgruppen verwendet werden können. Um diese Pläne umfassender zu charakterisieren, wurde die Simulationstechnik eingesetzt. Von besonderem Interesse waren Abschätzungen von Perzentilen der Verteilungsfunktion der “erforderlichen Stichprobengröße, um eine statistische Entscheidung zu treffen”. Es werden Verteilungsparameter von einseitigen

ISSN:0323-3847    

DOI:10.1002/bimj.4710200310

出版商:WILEY‐VCH Verlag    

年代:1978

数据来源: WILEY

摘要:

AbstractA new method of rotation in factor analysis is introduced, the Signimaxrotation. By this tool the number of the significant factor‐values can be maximated. The basis of its criterion of rotation are the distances between the nonsignificant factor‐values and the nearest limitation of significance and also the number of non‐significant factor‐values. In some examples it is shown that the Signimaxrotation yields results, better than these one of a Varimaxrotation or the visual rotation.Es wird ein neues Rotationsverfahren der Faktoranalyse vorgestellt, die Signimaxrotation. Mit ihr soll die Anzahl der signifikanten Ladungen einer Faktorenstruktur maximiert werden. Grundlagen ihres Rotationskriteriums sind die Abstände der nichtsiguifikanten Ladungen von der nächstgelegenen Signifikanzgrenze sowie die Anzahl der nichtsiguifikanten Ladungen. In Beispielen wird gezeigt, daß die Signimaxrotation bessere Ergebnisse liefert als die Varimaxrotation oder die visuell

ISSN:0323-3847    

DOI:10.1002/bimj.4710200311

出版商:WILEY‐VCH Verlag    

年代:1978

数据来源: WILEY