Primary Research Areas

• Statistical analysis of genomic and genetic data
• The analysis of spatial data
• Statistical methods for early phase clinical trials
• The design and analysis of phase III clinical trials
• Statistical modelling of neurological diseases

Statistical analysis of genomic and genetic data

Yongxiang Fang, Thomas Jaki, Matt Sperrin, Helene Thygesen, Ting-Li Su, Thomas Jaki and John Whitehead

The Section has a close collaboration with the School of Biological Sciences at the University of Liverpool concerning the design and analysis of microarray studies. Currently, the principal application concerns gene expression data in roach and carp. This has led to a methodological interest in the interpretation of multiple (many thousands) analyses, and the use of gene ontologies to structure the conclusions. A related interest concerns the relationship between the human genome and the risk of adverse drug reactions. As in the analysis of microarray data, there are severe problems of multiplicity. Sequential methods can be used to identify such an association quickly from accumulating adverse event data, allowing an exclusion criterion applied in the treatment of future patients.

Some recent publications:

• Kelly, P., Zhou, Y., Whitehead, J. and Bowman, C. (2008). Sequential testing for a gene-drug interaction in a genomewide analysis. Statistics in Medicine 27, 2022-2034.
• Kelly, P., Stallard, N., Zhou, Y., Whitehead, J. and Bowman, C. (2006). Sequential genome-wide association studies for monitoring adverse events in the clinical evaluation of new drugs. Statistics in Medicine 25, 3081-3092.
• Fraser, J., Vieira de Mello, L., Ward, D., Rees, H., Williams, D. R., Fang, Y., Brass, A., Gracey, A. Y. and Cossins, A. R. (2006). Hypoxia-inducible myoglobin expression in nonmuscle tissues. Proceedings of the National Academy of Sciences 103, 2977-2981.
• Gracey, A. Y., Fraser, E. J., Li, W., Fang, Y., Taylor, R. R., Rogers, J., Brass, A. and Cossins, A. R. (2004). Coping with cold: an integrative, multi-tissue analysis of the transcripome of a poikilothermic vertebrate. Proceedings of the National Academy of Sciences 101, 16970-16975.

The analysis of spatial data

Debbie Costain, Chris Sherlock and Ting-Li Su

Spatial data arise in many areas of medical research. One interest concerns spatial variation in disease risk and the development of flexible methods which allow for spatial discontinuity. Such methods can be used to model data from case-control studies conducted over a wide geographical area. Other research has arisen from the work of the National Zoonosis Research Centre which is centred at the University of Liverpool and includes Lancaster University as a partner institute. Zoonosis is the transfer of disease from animals to humans, and projects include studying the potential transfer of antibiotic resistant bacteria from wild rodents such as bank voles and wood mice.

Some recent publications:

• Costain, D. (2009). Bayesian partitioning for modelling and mapping spatial case-control data. Biometrics (To appear).

Statistical methods for early phase clinical trials

John Whitehead, Anne Whitehead, Helene Thygesen, Gareth Ridall and Thomas Jaki

Part of our work concerns first-in-man studies of new drugs, both in the setting of oncology where subjects are patients and responses are toxicities, and more generally where subjects are healthy volunteers and responses are pharmacokinetic and pharmacodynamic assessments. Research has centred on the development of Bayesian procedures for dose-escalation and on the identification of the optimal doses in drug combination therapies. We are also interested in both Bayesian and frequentist approaches to the determination of sample size for phase II studies and in the inclusion of interim analyses within phase II designs. Collaborations include participation in the MRC North West Hub for Trial Methodology Research centred at the University of Liverpool, and work with numerous pharmaceutical companies.

Some recent publications:

• Zhou, Y., Whitehead, J. and Korhonen, P. (2008). Implementation of a Bayesian design in a dose-escalation study of an experimental agent in healthy volunteers. Biometrics 64, 299-308.
• Whitehead, J., Zhou, Y., Mander, A., Ritchie, S., Sabin, A. and Wright, A. (2006). An evaluation of Bayesian designs for dose-escalation studies in healthy volunteers. Statistics in Medicine 25, 433-445.
• Whitehead, J. and Valdés-Márquez, E. (2008). Bayesian sample size for exploratory clinical trials incorporating historical data. Statistics in Medicine 27, 2307-2327.
• Whitehead, A., Whitehead, J., Todd, S., Zhou, Y. and Smith, M.K. (2007). Fitting models for the joint action of two drugs using SAS®. Online: Pharmaceutical Statistics. DOI: 10.1002/pst.312.

The design and analysis of phase III clinical trials

John Whitehead, Anne Whitehead, Ting-Li Su, Thomas Hamborg, Zakiah Zain

Research interests include the development of adaptive designs, particularly group sequential designs and sample size reviews. Interim analyses conducted to detect an interaction between a biomarker and treatment that could lead to continuing the trial with all subjects or restricting recruitment to those who are bioassay positive are being explored. The interpretation of multiple outcomes per patient is being studied. These might be assessments made on different scales, such as the use of the Barthel index, the modified Rankin score and the NIH stroke scale to evaluate stroke patients, or repeated application of the same scale over time. The outcomes might be binary or ordinal, and we are also beginning to study how to interpret multiple survival endpoints such as time to death and time to disease progression, or time to loss of sight in the right eye and time to loss of sight in the left eye. A further interest is methodology for meta-analysis, particularly individual patient data approaches and the properties of cumulative meta-analyses.

Some recent publications:

• Whitehead, A., Sooriyarachchi, M. R., Whitehead, J. and Bolland, K. (2008). Incorporating intermediate binary responses into interim analyses of clinical trials: a comparison of four methods. Statistics in Medicine 27, 1646-1666.
• Sooriyarachchi, M. R., Whitehead, J., Whitehead, A., and Bolland, K. (2006). The sequential analysis of repeated binary responses. Statistics in Medicine 25, 2196-2214.
• Sooriyarachchi, M. R., Whitehead, J., Matsushita, T., Bolland, K. and Whitehead, A. (2003). Incorporating data received after a sequential trial has stopped into the final analysis: implementation and comparison of methods. Biometrics 59, 701-709.
• Whitehead, A. (2002). Meta-analysis of Controlled Clinical Trials. Wiley: Chichester.

Statistical modelling of neurological diseases

Gareth Ridall

Work in this area is proceeding in collaboration with investigators at the Royal Brisbane and Women's Hospital in Australia and the Erasmus Medical Centre, Rotterdam in the Netherlands. Specifically, interest centres on the problem of estimating the number of functioning neurological motor units in patients suffering from the degenerative disease amyotrophic lateral sclerosis. A Bayesian approach is being taken to analyse longitudinal data from multi-electrode probes allowing for correlations in time and in space. Estimation of the number of surviving motor units would enable early detection of the disease and provide a reliable and objective means of quantifying its progress. This would have potential for the clinical development of new therapies.

Some recent publications:

• Ridall, P. G., Pettitt, A. N., Friel, N., Henderson, R. D. and McCombe, P. A. (2007). Motor unit number estimation using reversible jump Markov chain Monte Carlo (with discussion). Journal of the Royal Statistical Society, Series C 56,1-26.
• Henderson, R. D., Ridall, P.G., Pettitt, A. N., McCombe, P. A. and Daube, J. R. (2006). The stimulus-response curve and motor unit variability in normal subjects and subjects with Amyotrophic Lateral Sclerosis. Muscle Nerve 33, 34-43
• Ridall, P. G., Pettitt, A. N., Henderson, R. D. and McCombe, P. A. (2006). Motor unit number estimation - a Bayesian approach. Biometrics 62, 1235-50.