Anthony C. Atkinson

Learn More
Three properties of interest in bioavailability studies using compartmental models are the area under the concentration curve, the maximum concentration, and the time to maximum concentration. Methods are described for finding designs that minimize the variance of the estimates of these quantities in such a model. These methods use prior information. Both(More)
Randomized optimum designs of biased-coin type are compared with other strategies for the sequential allocation of two or more treatments in a clinical trial. The emphasis is on the variance of estimated treatment contrasts. This variance, which depends on the design strategy employed, may be interpreted as the number of patients on whom information is(More)
Adaptive designs are used in phase III clinical trials for skewing the allocation pattern toward the better treatments. We use optimum design theory to derive a skewed Bayesian biased-coin procedure for sequential designs with continuous responses. The skewed designs are used to provide adaptive designs, the performance of which is studied numerically and(More)
Setting of process variables to meet a required specification of quality characteristic (or response variable) in a process, is one of the common problems in the process quality control. But generally there are more than one quality characteristics in the process and the experimenter attempts to optimize all of them simultaneously. Since response variables(More)
We use the forward search to provide robust Mahalanobis distances to detect the presence of outliers in a sample of multivariate normal data. Theoretical results on order statistics and on estimation in truncated samples provide the distribution of our test statistic. We also introduce several new robust distances with associated distributional results.(More)
The methods of very robust regression resist up to 50% of outliers. The algorithms for very robust regression rely on selecting numerous subsamples of the data. We describe new algorithms for LMS and LTS estimators that have increased efficiency due to improved combinatorial sampling. These and other publicly available algorithms are compared for outlier(More)
We combine the selection of a statistical model with the robust parameter estimation and diagnostic properties of the Forward Search. As a result we obtain procedures that select the best model in the presence of outliers. We derive distributional properties of our method and illustrate it on data on ozone concentration. The effect of outliers on the choice(More)
Response adaptive designs are used in phase III clinical trial for skewing the allocation pattern towards the better treatments. We use optimum design theory to derive adaptive designs when the responses are normally distributed. The performance of the designs is studied with respect to the loss and the proportion of allocation to different treatments. The(More)