Research Interests:
Research Interests:
ABSTRACT We consider the construction and properties of influence functions in the context of functional measurement error models with replicated data. In these models estimates of the parameters can be affected both by the individual... more
ABSTRACT We consider the construction and properties of influence functions in the context of functional measurement error models with replicated data. In these models estimates of the parameters can be affected both by the individual observations and the means of replicated observations. We show that influence function of the means of replicates on the estimate of regression coefficients can be only derived under the assumption that the variances of the errors are known, while one for the individual observations can be only derived simultaneously with their influence function on the estimators of the variances of the errors.
Research Interests:
Research Interests:
Research Interests:
ABSTRACT This paper discusses a recent evaluation of bone assemblage quantification methods based in large part upon a critique of our own published work. We aim to show that the critique reveals a misunderstanding of our proposals and of... more
ABSTRACT This paper discusses a recent evaluation of bone assemblage quantification methods based in large part upon a critique of our own published work. We aim to show that the critique reveals a misunderstanding of our proposals and of the aims of quantification techniques in this field.
Research Interests:
ABSTRACT Methods of quantifying bone samples are discussed and the minimum numbers approach criticized. A technique based upon number estimation of game populations is put forward, and some of the practical difficulties of this method are... more
ABSTRACT Methods of quantifying bone samples are discussed and the minimum numbers approach criticized. A technique based upon number estimation of game populations is put forward, and some of the practical difficulties of this method are examined. Consideration is given to the underlying statistical assumptions involved in quantified analysis of bone samples, and a method of calculating confidence limits for death population numbers proposed.
Research Interests:
Research Interests: Echocardiography, Humans, Hemodynamics, Female, Male, and 6 moreHeart, Adult, Cardiomyopathies, Heart Ventricles, JAMA, and Nitroglycerin
Research Interests:
Research Interests:
Research Interests:
Research Interests:
A statistical comparison is made of various tests for the randomness or otherwise of second-phase particles in composite materials. Quadrat, nearest-neighbour, Ripley's K function and Dirichlet tessellation-based tests are... more
A statistical comparison is made of various tests for the randomness or otherwise of second-phase particles in composite materials. Quadrat, nearest-neighbour, Ripley's K function and Dirichlet tessellation-based tests are compared. It is found that a test based on Ripley's K function performs well in detecting both clustered and regular alternatives to randomness. Additionally these tests have the benefit of providing
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
... obvi-(32b) ous. A useful statistic in the testing of a pair of upper outliers in a gammasample is T(,, + T(,,_-= Zn, say, whose density function hn( ) can be found in prin-ciple from the above joint density. Even without the exact ...
Research Interests:
ABSTRACT The nature of “mixed” grain size populations modelled by log skew Laplace (and other) mixture distributions may be displayed and analysed by using the simple convention of plotting the parameter scores of the component... more
ABSTRACT The nature of “mixed” grain size populations modelled by log skew Laplace (and other) mixture distributions may be displayed and analysed by using the simple convention of plotting the parameter scores of the component populations as “dumb-bells” on three-dimensional and two-dimensional displays. An example is given using particle size data from dune ridge crest and pan sands from the Kalahari desert of central southern Africa.
Research Interests:
The differentiation between psoriatic arthritis and rheumatoid arthritis can be clinically difficult if there is no manifest psoriasis of skin or nail. In order to clarify this diagnostic problem, the amino acid patterns in seventy-five... more
The differentiation between psoriatic arthritis and rheumatoid arthritis can be clinically difficult if there is no manifest psoriasis of skin or nail. In order to clarify this diagnostic problem, the amino acid patterns in seventy-five psoriatic and non-psoriatic nails have been studied. Using gas--liquid chromatographic techniques and discriminant analysis, a high degree of differentiation (96%) has been established between the normal looking nails of patients with psoriatic arthritis and those with rheumatoid arthritis. This biochemical/statistical approach to the fingernail enhances diagnosis in difficult clinical problems, particularly where there are no overt manifestations of psoriasis.
Research Interests:
Research Interests:
Research Interests:
ABSTRACT The study of particle size distributions is commonly used to investigate sedimentary processes and environments. Originally such work concentrated on typifying these distributions by their sample moments, while more recent... more
ABSTRACT The study of particle size distributions is commonly used to investigate sedimentary processes and environments. Originally such work concentrated on typifying these distributions by their sample moments, while more recent statistical studies have proposed fitting parametric models to sample data and then using the resulting parameter estimates. We have investigated the use of log-hyperbolic and skew log-Laplace models to distinguish between beach and dune sands, with the aim of classifying the depositional environment of some mesolithic middens. We found that the former models were unsatisfactory for various numerical and physical reasons, while the latter provide a simple and robust method which is useful for the classification of sand sediments.
Research Interests:
Research Interests:
Research Interests:
ABSTRACT This paper identifies various statistical problems in the measurement and analysis of particle sizes. The log-skew-Laplace distribution is proposed as a simple but effective model for particle sizes which can be readily extended... more
ABSTRACT This paper identifies various statistical problems in the measurement and analysis of particle sizes. The log-skew-Laplace distribution is proposed as a simple but effective model for particle sizes which can be readily extended to handle more complex situations such as mixtures and the marrying of measurements of different aspects of size. The model is compared with other contenders, the log-normal and log-hyperbolic distributions, in the analysis of sand grain data from the Hebrides.
Research Interests:
Research Interests:
... distributionsinclude the Weibull density (Rosin Rammler,1933), the lognormal(Krumbein Pettijohn, 1938)the GramCharlierseries and Pearsoncurves (Otto,1939; Tanner,1958; LeRoy,1981). ... BarndorffNielsen,O., Dalsgaard,K., Halgreen,C.,... more
... distributionsinclude the Weibull density (Rosin Rammler,1933), the lognormal(Krumbein Pettijohn, 1938)the GramCharlierseries and Pearsoncurves (Otto,1939; Tanner,1958; LeRoy,1981). ... BarndorffNielsen,O., Dalsgaard,K., Halgreen,C., Kulhman,H., Moller,JT Schou, G. (1980 ...
Research Interests:
ABSTRACT The current paradigm for the identification of candidate drugs within the pharmaceutical industry typically involves the use of high-throughput screens. High-content screening (HCS) is the term given to the process of using an... more
ABSTRACT The current paradigm for the identification of candidate drugs within the pharmaceutical industry typically involves the use of high-throughput screens. High-content screening (HCS) is the term given to the process of using an imaging platform to screen large numbers of compounds for some desirable biological activity. Classification methods have important applications in HCS experiments, where they are used to predict which compounds have the potential to be developed into new drugs. In this paper, a new classification method is proposed for batches of compounds where the rule is updated sequentially using information from the classification of previous batches. This methodology accounts for the possibility that the training data are not a representative sample of the test data and that the underlying group distributions may change as new compounds are analysed. This technique is illustrated on an example data set using linear discriminant analysis, k-nearest neighbour and random forest classifiers. Random forests are shown to be superior to the other classifiers and are further improved by the additional updating algorithm in terms of an increase in the number of true positives as well as a decrease in the number of false positives.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
ABSTRACT A bioassay has been developed, using the crawling and attachment behaviour of plantigrades of the common mussel, Mytilus edulis, for copper-impaired sea water. Potentiometric stripping analysis has been used to quantify the total... more
ABSTRACT A bioassay has been developed, using the crawling and attachment behaviour of plantigrades of the common mussel, Mytilus edulis, for copper-impaired sea water. Potentiometric stripping analysis has been used to quantify the total and electrochemically labile species of copper. The threshold of sensitivity for the bioresponse lies between 13 ppb total, 8 ppb labile and 25 ppb total, 15 ppb labile copper, for a bioassay of 1 h duration. There is an example of hormesis for the bioresponse of the number of plantigrades that crawl for levels of copper at and below 13 ppb total, 8 ppb labile metal. The effects of light and gravity as directional cues and the effect of animal size and density in the bioassay have also been considered.
Research Interests:
A problem receiving increasing interest is whether it is possible to quantify in a statistical sense the quality of match of two images of a face, for example of an image captured on a surveillance monitor to an image held in a database.... more
A problem receiving increasing interest is whether it is possible to quantify in a statistical sense the quality of match of two images of a face, for example of an image captured on a surveillance monitor to an image held in a database. Such a quantitative measure is a prerequisite for ...