On parameter orthogonality and proper modelling of dispersion in Poisson-inverse Gaussian regression

Thursday, 24 September 2015
9.30am - 10.30am
Seminar Room 1, Level 6, The Alfred Centre
Commercial Rd
Prahran 3004

In clinical trials one traditionally models the effect of treatment on the mean response. The underlying assumption is that treatment affects the response distribution through a mean location shift on a suitable scale, with other aspects of the distribution (shape/dispersion/variance) remaining the same. This work is motivated by a trial in Parkinson’s disease patients where the primary endpoint is the number of falls during 10 weeks. Inspection of the data reveals that the Poisson-inverse Gaussian (PIG) distribution is appropriate, and that the experimental treatment reduces not only the mean, but also the variability, substantially. The conventional analysis assumes a treatment effect on the mean, either adjusted or unadjusted for covariates, and a constant dispersion parameter. On our data, this analysis yields a non-significant treatment effect. However, if we model a treatment effect on both the mean and dispersion parameters, both effects are highly significant. A simulation study shows that if a treatment effect exists on the dispersion parameter and is ignored in the modelling, estimation of the treatment effect on the mean can be severely biased. We show further that if we use an orthogonal parametrisation of the PIG distribution, estimates of the mean model are robust to misspecification of the dispersion model. We will also discuss inferential aspects that are more difficult than anticipated in this setting. These findings have implications in the planning of statistical analyses for count data in clinical trials.

Joint work with Gillian Heller (Macquarie University) and Dominique Couturier (Cambridge University)


Associate Professor Stephane Heritier

Assoc. Prof. Stephane Heritier

Dept of Epidemiology and Preventive Medicine
Monash University

Stephane Heritier is Associate Professor of Biostatistics at Monash University. His previous appointment was Head of Statistical Research at the George Institute for Global Health, Sydney University. He has been involved in the design and analysis of large-scale studies for 17+ years, mainly in cardiovascular and renal diseases, neurological and mental health, critical care and injury prevention. His research interests include adaptive designs, cluster randomised trials, survival analysis and robust statistics. Stephane is a chief investigator on several NHMRC grants and is involved in statistical consulting within the Faculty of Medicine and for the pharmaceutical industry.


PDF icon Presentation slides.pdf557.45 KB