Showing papers in "Journal of Applied Statistics in 1990"
TL;DR: In this paper, the construction and selection of multiple dependent (deferred) state (MDS) sampling plans of type MDS-(c1,c2) is discussed.
Abstract: Tables have been prepared for the construction and selection of multiple dependent (deferred) state (MDS) sampling plans of type MDS-(c1,c2). These plans are compared with conventional sampling plans (such as single and double sampling) and it is shown that MDS-type plans require a smaller sample size. A special feature of the MDS-(0,1) plan is highlighted and its design procedure is indicated.
63 citations
TL;DR: In this article, the location and scale parameters of an exponential distribution based on singly and doubly censored samples are estimated using the maximum likelihood (ML) estimation method, which does not admit explicit solutions.
Abstract: The maximum likelihood (ML) estimation of the location and scale parameters of an exponential distribution based on singly and doubly censored samples is given When the sample is multiply censored (some middle observations being censored), however, the ML method does not admit explicit solutions In this case we present a simple approximation to the likelihood equation and derive explicit estimators which are linear functions of order statistics Finally, we present some examples to illustrate this method of estimation
53 citations
TL;DR: In this article, a mixture model with Laplace and normal components is fitted to wind shear data available in grouped form, and a set of equations is presented for iteratively estimating the parameters of the model using an application of the EM algorithm.
Abstract: A mixture model with Laplace and normal components is fitted to wind shear data available in grouped form. A set of equations is presented for iteratively estimating the parameters of the model using an application of the EM algorithm. Twenty-four sets of data are examined with this technique, and the model is found to give a good fit to the data. Some hypotheses about the parameters in the model are discussed in light of the estimates obtained.
36 citations
TL;DR: In this paper, the authors compared various methods for clustering mixed-mode data and found that a method based on a finite mixture model in which the observed categorical variables are generated from underlying continuous variables out-performed more conventional methods when applied to artificially generated data.
Abstract: Various methods for clustering mixed-mode data are compared. It is found that a method based on a finite mixture model in which the observed categorical variables are generated from underlying continuous variables out-performs more conventional methods when applied to artificially generated data. This method also performs best when applied to Fisher's iris data in which two of the variables are categorized by applying thresholds.
35 citations
TL;DR: The authors show that the various times series models, reported in the literature, for the Canadian lynx data form interesting clusters, and show that they form interesting clustering for different types of timeseries.
Abstract: We show that the various times series models, reported in the literature, for the Canadian lynx data form interesting clusters.
30 citations
TL;DR: Aitchison as mentioned in this paper proposed a method for principal component analysis of compositional data involving transformation of the raw data and showed how this can be approximated by a correspondence analysis of appropriately transformed data.
Abstract: Principal component and correspondence analysis can both be used as exploratory methods for representing multivariate data in two dimensions. Circumstances under which the, possibly inappropriate, application of principal components to untransformed compositional data approximates to a correspondence analysis of the raw data are noted. Aitchison (1986) has proposed a method for the principal component analysis of compositional data involving transformation of the raw data. It is shown how this can be approximated by a correspondence analysis of appropriately transformed data. The latter approach may be preferable when there are zeroes in the data.
30 citations
TL;DR: In this article, a table and a procedure are given for finding the multiple deferred state sampling plan of type MDS-1 involving minimum sum of risks for specified acceptable quality level and limiting quality level.
Abstract: A table and a procedure are given for finding the multiple deferred state sampling plan of type MDS-1 involving minimum sum of risks for specified acceptable quality level and limiting quality level.
25 citations
TL;DR: In this article, the effect of rounding normal data on the significance level of four test statistics was investigated and guidance on what is an appropriate degree of precision when using these tests on normal rounded data was given.
Abstract: A basic assumption of many statistical tests is that the samples are drawn from normal populations. However, in practice the data are often subject to rounding. Here we consider the effect of rounded normal data on the significance level of four test statistics. Guidance is given on what is an appropriate degree of precision when using these tests on normal rounded data. The results indicate that less precision is required of the recorded data than that which is usually given.
24 citations
TL;DR: The authors investigated the effect of rounding normal data on the significance level of four test statistics and found that the power of these tests is adversely affected for the degree of precision recommended in Tricker's paper.
Abstract: A basic assumption of many statistical tests is that the samples are drawn from normal distributions. However, if the data are rounded, the question arises of how this affects the usual tests. Tricker (1990) considered the effect of rounded normal data on the significance level of four test statistics. Here the power of these tests is investigated and whether this power is adversely affected for the degree of precision recommended in Tricker's paper.
18 citations
TL;DR: A set of master tables is presented which can be used to select a Modified Quick Switching System indexed by different sets of parameters.
Abstract: A set of master tables is presented which can be used to select a Modified Quick Switching System. Selection of Modified Quick Switching System indexed by different sets of parameters is discussed.
13 citations
TL;DR: In this paper, modified maximum likelihood estimators of the parameters of a multivariate normal distribution are developed when the smallest or largest observations on one of the components are censored, and these estimators are used to construct tests for means and correlation coefficients.
Abstract: Modified maximum likelihood estimators of the parameters of a multivariate normal distribution are developed when the smallest or largest observations on one of the components are censored. These estimators are used to construct tests for means and correlation coefficients. The robustness of these tests to deviations from normality is investigated.
TL;DR: The authors used n-ary block designs in the evaluation of balanced incomplete block (BIB) designs for all the four Griffing's (1956) complete dialled crosses (CDC) systems.
Abstract: To fill the gap between theory and practice of modern statistical designs, this paper presents the use of n-ary block designs in the evaluation of balanced incomplete block (BIB) designs for all the four Griffing's (1956) complete dialled crosses (CDC) systems, the construction of which is proposed here by adopting a suitable BIB design and associating its treatments with the crosses under a CDC system.
TL;DR: In this article, the mean direction and the concentration parameters of the von Mises distribution were estimated from a Bayesian point of view when k(k < n/2) of the n observations are spurious.
Abstract: This paper discusses inference regarding the mean direction and the concentration parameters based on data from the von Mises distribution from a Bayesian point of view, when k(k < n/2) of the n observations are spurious, that is, are from a von Mises population with a shifted mean direction. The Bayesian analysis for this spuriosity case provides both detection, identification, and estimation for the mean direction and the concentration parameter when indeed spurious observations are present, possibly giving rise to outliers.
TL;DR: In this paper, two graphical displays for the off-diagonal as well as the diagonal elements of PZ are proposed to detect outliers in multivariate data where the rows of Z are usually regarded as a random sample from a multivariate population.
Abstract: In the context of the general linear model Y=Xβ+e, the matrix Pz =Z(ZTZ)−1 ZT , where Z=(X: Y), plays an important role in determining least squares results. In this article we propose two graphical displays for the off-diagonal as well as the diagonal elements of PZ . The two graphs are based on simple ideas and are useful in the detection of potentially influential subsets of observations in regression. Since PZ is invariant with respect to permutations of the columns of Z, an added advantage of these graphs is that they can be used to detect outliers in multivariate data where the rows of Z are usually regarded as a random sample from a multivariate population. We also suggest two calibration points, one for the diagonal elements of PZ and the other for the off-diagonal elements. The advantage of these calibration points is that they take into consideration the variability of the off-diagonal as well as the diagonal elements of PZ . They also do not suffer from masking.
TL;DR: In this paper, the use of single group skewness and kurtosis critical values for the assessment of residual normality in the ANOVA model is examined, using single group critical values gives a conservative test of residual norms in multiple group designs.
Abstract: The use of single group skewness and kurtosis critical values for the assessment of residual normality in the ANOVA model is examined. Using single group critical values gives a conservative test of residual normality in multiple group designs. As the sample size per group increases, the empirical Type I error rates for the skewness and kurtosis tests of residual normality approach a. These results supplement previous work which has focused on testing residual normality in the linear regression model.
TL;DR: In this article, an algorithm for generating von Mises variates using Forsythe's method was described, with respect to speed, and compactness, and the performance was analyzed with respect of speed, compactness and efficiency.
Abstract: An algorithm is described for generating von Mises variates using Forsythe's method. The performance is analysed with respect to speed, and compactness. Conclusions are drawn as to when it is preferred to Best and Fisher's envelope rejection method.
TL;DR: Sampling from infinite and finite populations with overlapping classifications, stratified sampling, optimum allocation to strata, etc., are considered and results concerning the significance of sample leads are presented.
Abstract: This article presents results concerning the significance of sample leads and illustrates their uses. They enable the analysis of one party over another in political polls, one product over another in market research surveys, market share in industrial studies, etc. They enable the calculation of confidence intervals and required sample size, testing of hypotheses, etc. Sampling from infinite and finite populations with overlapping classifications, stratified sampling, optimum allocation to strata, etc., are considered. Derivation of the results is given in a set of Appendices. Some of these are rather complicated, but their uses are straightforward.
TL;DR: In this article, an estimation of a single equation in which the coefficients of certain exogenous variables are fixed and those of other exogenous variable are random is presented, and the model is analyzed.
Abstract: With the recent accent on varying parameter models, theoretical studies have concentrated on estimating equations where all the coefficients are stochastic. This paper analyses an estimation of a single equation in which the coefficients of certain exogenous variables are fixed and those of other exogenous variables are random.
TL;DR: In this paper, the effects of rounding on the significance and power of four test statistics were investigated for rounding non-normal data and guidelines were given on how the degree of precision recommended for normal populations can be applied when the population is nonnormal.
Abstract: In a previously published study, the effects of rounding on the significance and power of four test statistics were considered when the parent population was normal. Here we investigate how these tests will perform for rounded non-normal data. Guidelines are given on how the degree of precision recommended for normal populations can be applied when the population is non-normal.
TL;DR: In this article, the potential application of the characterization theory to the mixture model is discussed and successful application of this theory can be made in order to choose the appropriate mixture model and the mixing parameter.
Abstract: This paper indicates the potential application of the characterization theory to the mixture model. It discusses a particular example of a mixture model and concludes that successful application of this theory can be made in order to choose the appropriate mixture model and the mixing parameter.
TL;DR: In this article, the problem of constructing simultaneous confidence intervals for various measures of association is considered, and alternative bootstrap algorithms are given for approximating the sampling distributions of the quantities generating the confidence sets.
Abstract: The problem of constructing simultaneous confidence intervals for various measures of association is considered. Alternative bootstrap algorithms are given for approximating the sampling distributions of the quantities generating the confidence sets. The small sample performance of the procedures is illustrated using simulated data from 3- and 6-variate normal populations. The results are applied to a large multidimensional longitudinal data set from a study of the relationship between drug use and several behavioral attributes.
Journal Article•
TL;DR: In this article, a model of the transition probabilities in a finite state stochastic process in discrete time is introduced to describe the ordinal features of the responses to this experiment.
Abstract: In psychology, the free-recall experiment is used to investigate the organization of items in memory. A model is introduced to describe the ordinal features of the responses to this experiment. This is essentially a model of the transition probabilities in a finite state stochastic process in discrete time. A matrix regression model is introduced to investigate the effects on various factors on organization. Simulation techniques are used to assess the goodness of fit of the model and to test hypothesis about the model parameters. Finally components of the log-likelihood are used as diagnostic tools to check that there are no outliers. An example involving the recall of personalities' names is considered.
TL;DR: Newrick et al. (1990) have claimed from 100 consecutive autopsies that there is a significant association between life-line and longevity, and this work re-examines their claim.
Abstract: Newrick et al. (1990) have claimed from 100 consecutive autopsies that there is a significant association between life-line and longevity. This study has received wide publicity in the popular press and in the T.V. media, and we re-examine their claim.
TL;DR: Incomplete variance functions may be used to explain the unreliability of variance estimates when the distribution is long-tailed as mentioned in this paper, which may also explain the importance of extreme values in variance estimates.
Abstract: Estimates of variance from samples depend strongly on extreme values. Incomplete variance functions may be used to explain the unreliability of variance estimates when the distribution is long-tailed.
TL;DR: In this paper, the problem of constructing the prediction intervals for future observations using the growth curve model is considered and approximate intervals assuming different structures on σ are derived, and the results are illustrated with several data sets.
Abstract: The growth curve model Yn×p = An×p ξ mtimes;kBk×p+ Enxp, where Y is an observation matrix, &sigma is a matrix of unknown parameters, A is a known matrix of rank m, B is a known matrix of rank k with 1'= (1, …, 1) as its first row, and the rows of E are independent each distributed as Np(0,Σ,) is considered. The problem of constructing the prediction intervals for future observations using the above model is considered and approximate intervals assuming different structures on σ are derived. The results are illustrated with several data sets.
TL;DR: In this article, a bi-weight approach is proposed for the estimation of a realistic exchange rate for the Nigerian currency, naira, which is essentially a critic of the methods being used by the Central Bank of Nigeria (CBN) to derive its estimate.
Abstract: In this article, we propose a biweight approach to a real-life location problem, namely, the estimation of a realistic exchange rate for the Nigerian currency, naira (for easy reference, we denote the exchange rate parameter byθ). Our proposal is essentially a critic of the methods being used by the Central Bank of Nigeria (CBN) to derive its estimate θCBN of θ. The CBN generates the necessary data by periodically organizing a foreign exchange market (FEM) where it sells a certain amount of US dollars to authorized foreign exchange dealers. (The amount of dollars available for sale is usually inadequate to meet aggregate demand, so there is literally a ‘scramble’ among dealers for a ‘slice of the cake’.) During each session of FEM, each dealer quotes: (a) how much naira (variable Y) it will pay for US$1, and (b) the amount of US dollars (variable X) it wants to buy. The CBN estimates, based on observations of Y, have been found to be unstable and part of the problem seems to lie with the fact that a few a...
TL;DR: The origins of words in current use often hold surprises as mentioned in this paper, and some of the more interesting etymologies are considered, such as coined words, "hi-jacks" from other disciplines, and words which have gradually evolved meanings quite different from the original ideas they expressed.
Abstract: The origins of words in current use often hold surprises. Statistical terminology is no exception, and some of the more interesting etymologies are considered. They include coined words, ‘hi-jacks' from other disciplines, and words which have gradually evolved meanings quite different from the original ideas they expressed (as witness the title).
TL;DR: In this paper, the authors developed non-parametric, parametric and network models to describe the distribution of stay in "limbo" and estimate the probability of return to service.
Abstract: It is of particular importance to nurse manpower planners to determine the likelihood and time-scale of return to service of nurses who have temporarily withdrawn from the labour force. Such behaviour is common in female dominated professions and is referred to in the nursing literature as being in ‘limbo’. In this paper we develop non-parametric, parametric and network models to describe the distribution of stay in ‘limbo’ and estimate the probability of return to service. These models are fitted to data from the Northern Ireland nursing service. It is inherent in the problem that the data are statistically incomplete. This must be taken into account in the statistical methods used to estimate the various model parameters.
TL;DR: In this article, a class of aligned rank order tests for interaction in two-way layouts is considered, based on application of the existing nonparametric techniques for one-way layout to the transformed observations.
Abstract: A class of aligned rank order tests for interaction in two-way layouts is considered. The technique is based on application of the existing nonparametric techniques for one-way layouts to the transformed observations. It is shown that the asymptotic properties of these techniques are preserved after alignment. Furthermore, asymptotic relative efficiency comparisons are made with some of the competing tests. Finally, we demonstrate that our technique can be used to test for higher-order interactions in general multi-factor layouts.