摘要:

A method of combining two separate regressions,YonxandYoonz, to yield confidence intervals forx's corresponding to given values ofz's, is illustrated in the following chemical calibration problem: A chemical indicatorz, (oxalacetic acid), called the standard, is used to estimate the average amount of serum glutamic oxalacetic transaminase (SGOT) enzymexpresent by in effect comparing the regressions ofYonxandYoonz, whereYandYoare their respective light absorbences. It is shown that single and joint contidence intervals for expected enzyme levels corresponding to indicator values are given by the solution of quartic equations when (as for this particular enzyme) the regression ofYonxis (approximately) quadratic and the regression ofYoonzis linear (and both are through the origin).

ISSN:0040-1706    

DOI:10.1080/00401706.1980.10486170

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

摘要:

The method of calculating the exact likelihood function of a stationary autoregressive moving average (ARMA) time series based on Akaike's Markovian representation and using Kalman recursive estimation is reviewed. This state space approach involves matrices and vectors with dimensions equal to Max (p,q+ 1) wherepis the order of the autoregression andqis the order of the moving average, rather than matrices with dimensions equal to the number of observations. A key to the calculation of the exact likelihood function is the proper calculation of the initial state covariance matrix. The inclusion of observational error into the model is discussed as is the extension to missing observations. The use of a nonlinear optimization program gives the maximum likelihood estimates of the parameters and allows for model identification based on Akaike's Information Criterion (AIC). An example is presented fitting models to western United States drought data.

ISSN:0040-1706    

DOI:10.1080/00401706.1980.10486171

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

摘要:

The effect of system size and shape on the theoretical space-time autocorrelation function is described for first order STARMA models. Figures and tables are presented to assist in identification considerations which include model interpretation, patterns of the theoretical spacetime autocorrelation and partial autocorrelation functions, and initial estimation for the STAR(11) and STMA(11) models.

ISSN:0040-1706    

DOI:10.1080/00401706.1980.10486172

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

摘要:

This paper is concerned with the problem of obtaining confidence intervals or tests of significance for the parameters or other characteristics of the generalized gamma distribution. Procedures are given whereby confidence intervals for the parameters, quantiles or the reliability (survivor) function of the distribution can be obtained, when the generalized gamma index parameter is known. Their application in studying robustness and model-dependence in lifetime distributions is also discussed.

ISSN:0040-1706    

DOI:10.1080/00401706.1980.10486173

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

摘要:

Conditional inference procedures are discussed for the shape parameter and for the current system reliability for a time truncated Weibull process. These tests are shown to be uniformly most powerful unbiased. Approximate confidence limits for the scale parameter are also developed.

ISSN:0040-1706    

DOI:10.1080/00401706.1980.10486174

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

摘要:

Tests are presented for comparing the scale parameters of Weibull process models when k independent series are available. The application of these tests, together with Crow's maximum likelihood ratio test for comparing shape parameters, is one way of testing that the k series have identical rates.

ISSN:0040-1706    

DOI:10.1080/00401706.1980.10486175

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

摘要:

Jonckheere (1954) proposed a test for ordered alternatives in a design withktreatments andblevels of another factor (blocks). In this paper tables are given for the null distribution of Jonckheere's statistic. Exact probabilities and critical values are given for α-levels near .2, .l, .05, .01 and .001, wherek= 2(1)6 andb= 2(1)5. Tables appear for designs in which there are an equal number of observations in treatments within a block, with cell sample sizes ranging from one to five.

ISSN:0040-1706    

DOI:10.1080/00401706.1980.10486176

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

摘要:

A table of percentage points of the asymptotic distribution of the one sample truncated K uiper statistic is provided. The table is useful for goodness of fit problems involving truncated or censored data, and in two sample testing problems.

ISSN:0040-1706    

DOI:10.1080/00401706.1980.10486177

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

摘要:

It is pointed out that the inferential theory of the segmented regression model depends strongly on whether or not continuity at the change-point is assumed. In particular, if it is not, the likelihood ratio test for the presence of two segments tends to infinity.

ISSN:0040-1706    

DOI:10.1080/00401706.1980.10486178

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

ISSN:0040-1706    

DOI:10.1080/00401706.1980.10486181

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor