Search

Pharmaceutical companies regularly need to make decisions about drug development programs based on the limited knowledge from early stage clinical trials. In this situation, eliciting the judgements of experts is an attractive approach for synthesising evidence on the unknown quantities of interest. When calculating the probability of success for a drug development program, multiple quantities of interest - such as the effect of a drug on different endpoints - should not be treated as unrelated. We discuss two approaches for establishing a multivariate distribution for several related quantities within the SHeffield ELicitation Framework (SHELF). The first approach elicits experts' judgements about a quantity of interest conditional on knowledge about another one. For the second approach, we first elicit marginal distributions for each quantity of interest. Then, for each pair of quantities, we elicit the concordance probability that both lie on the same side of their respective elicited medians. This allows us to specify a copula to obtain the joint distribution of the quantities of interest. We show how these approaches were used in an elicitation workshop that was performed to assess the probability of success of the registrational program of an asthma drug. The judgements of the experts, which were obtained prior to completion of the pivotal studies, were well aligned with the final trial results., Comment: 29 pages, 7 figures

Many methods for modelling spatial processes assume global smoothness properties; such assumptions are often violated in practice. We introduce a method for modelling spatial processes that display heterogeneity or contain discontinuities. The problem of non-stationarity is dealt with by using a combination of Voronoi tessellation to partition the input space, and a separate Gaussian process to model the data on each region of the partitioned space. Our method is highly flexible because we allow the Voronoi cells to form relationships with each other, which can enable non-convex and disconnected regions to be considered. In such problems, identifying the borders between regions is often of great importance and we propose an adaptive sampling method to gain extra information along such borders. The method is illustrated with simulation studies and application to real data.

Complete understanding of the mechanisms regulating the proliferation and differentiation that takes place during human immune CD8+ T cell responses is still lacking. Human clinical data is usually limited to blood cell counts, yet the initiation of these responses occurs in the draining lymph nodes; antigen-specific effector and memory CD8+ T cells generated in the lymph nodes migrate to those tissues where they are required. We use approximate Bayesian computation with deterministic mathematical models of CD8+ T cell populations (naive, central memory, effector memory and effector) and yellow fever virus vaccine data to infer the dynamics of these CD8+ T cell populations in three spatial compartments: draining lymph nodes, circulation and skin. We have made use of the literature to obtain rates of division and death for human CD8+ T cell population subsets and thymic export rates. Under the decreasing potential hypothesis for differentiation during an immune response, we find that, as the number of T cell clonotypes driven to an immune response increases, there is a reduction in the number of divisions required to differentiate from a naive to an effector CD8+ T cell, supporting the "division of labour" hypothesis observed in murine studies. We have also considered the reverse differentiation scenario, the increasing potential hypothesis. The decreasing potential model is better supported by the yellow fever virus vaccine data.

Conditional preference networks (CP-nets) are a graphical representation of a person's (conditional) preferences over a set of discrete variables. In this paper, we introduce a novel method of quantifying preference for any given outcome based on a CP-net representation of a user's preferences. We demonstrate that these values are useful for reasoning about user preferences. In particular, they allow us to order (any subset of) the possible outcomes in accordance with the user's preferences. Further, these values can be used to improve the efficiency of outcome dominance testing. That is, given a pair of outcomes, we can determine which the user prefers more efficiently. Through experimental results, we show that this method is more effective than existing techniques for improving dominance testing efficiency. We show that the above results also hold for CP-nets that express indifference between variable values., Comment: 58 pages, 8 figures

We harness the power of Bayesian emulation techniques, designed to aid the analysis of complex computer models, to examine the structure of complex Bayesian analyses themselves. These techniques facilitate robust Bayesian analyses and/or sensitivity analyses of complex problems, and hence allow global exploration of the impacts of choices made in both the likelihood and prior specification. We show how previously intractable problems in robustness studies can be overcome using emulation techniques, and how these methods allow other scientists to quickly extract approximations to posterior results corresponding to their own particular subjective specification. The utility and flexibility of our method is demonstrated on a reanalysis of a real application where Bayesian methods were employed to capture beliefs about river flow. We discuss the obvious extensions and directions of future research that such an approach opens up., Comment: 38 pages, 9 figures

When animals are transported and pass through customs, some of them may have dangerous infectious diseases. Typically, due to the cost of testing, not all animals are tested: a reasonable selection must be made. How to test effectively whilst avoiding costly disease outbreaks? First, we extend a model proposed in the literature for the detection of invasive species to suit our purpose. Secondly, we explore and compare three decision methodologies on the problem at hand, namely, Bayesian statistics, info-gap theory and imprecise probability theory, all of which are designed to handle severe uncertainty. We show that, under rather general conditions, every info-gap solution is maximal with respect to a suitably chosen imprecise probability model, and that therefore, perhaps surprisingly, the set of maximal options can be inferred at least partly---and sometimes entirely---from an info-gap analysis., Comment: 14 pages, 5 figures, 4 tables; v2: 15 pages, minor corrections, references added

In this brief note, we highlight some difficulties that can arise when fitting a continuous, symmetric, unimodal distribution to a set of expert's judgements. A simple analysis shows it is possible to fit a Cauchy distribution to an expert's beliefs when their beliefs actually follow a normal distribution. This example stresses the need for careful distribution fitting and for feedback to the expert about what the fitted distribution implies about their beliefs., Comment: Submitted to the Electronic Journal of Statistics (http://www.i-journals.org/ejs/) by the Institute of Mathematical Statistics (http://www.imstat.org)