Dr Heather Turner:
ht at heatherturner dot net
I am a statistical consultant with experience in supporting research in the life and social sciences. I have particular expertise in the areas of statistical modelling and statistical programming using the open source software R.
Services I can provide include
- data analysis
- methodology studies
- development of custom R packages
- conversion of code from other software to R
- training in R
Recent WorkThe following describes some of the projects I have worked on in the last year:
- Developing R package for EEG data analysis
- Co-developing the R package gslcca implementing a novel technique, Generalised Semi-linear Canonical Correlation Analysis, for the analysis of data from Electroencephalography (EEG) experiments. This work was carried out whilst working at Pfizer PharmaTherapeutics R&D and was presented at useR! 2011.
- Mediation analysis of an Intervention Study
- Applying the R package mediation to investigate the mediating effect of a individual's belief regarding treatment on the effect of treatment in a clinical trial for restless leg syndrome.
- Gene Set Enrichment Analysis Review
- Reviewing current methodology for gene set enrichment analysis and identifying methods that may provide some benefit over the method currently in use by the client. Applying selected methods to internal data sets to assess performance in practice and investigate differences between the methods.
- Modelling Results of the English Premier League
- Using Bradley-Terry models to model the ability of teams in the English Premier League and predict the outcomes of the 2011-12 season. This work is being carried out in my role of Senior Research Fellow at Warwick University.
Alongside my consultancy work, I have a part-time position as a Senior Research Fellow at the University of Warwick, UK. In this role, I am working with Professor David Firth on applications of generalized nonlinear models.
In 2011 I was Editor-in-chief of The R Journal as well as Program Chair and local organiser of the useR! 2011 conference. These roles pass on to others in 2012, however I will be involved as Associate Editor for The R Journal and Program Committee member for useR! 2012.
For the first nine months of 2011, I worked as a statistician at Pfizer PharmaTherapeutics R&D providing support to biologists and chemists working in early drug discovery. I had particular responsibility for the primary pharmacology and high throughput screening groups, providing expertise in areas such as dose response analysis and statistical process control. During this time I co-developed the gslcca package mentioned above.
Before moving to Pfizer I spent six years working as a researcher at the University of Warwick, again working with Professor David Firth. Our research activity focused on the development of methods and software for genealized nonlinear models, and we were awarded the 2007 John M. Chambers Statistical Software Award for the resultant package gnm. We also worked on models for paired comparisons, which we implemented in the BradleyTerry2 package.
I obtained my PhD in 2005 on the topic of biclustering microarray data, supervised by Professors Trevor Bailey and Wojtek Krzanowski at the University of Exeter. The plaid model algorithm of the biclust package, developed by Sebastian Kaiser and colleagues, is based on the algorithm and R code developed in this thesis.
My undergraduate degree is in Applied Statistics from the University of Reading, UK. During this time I spent a year working at the Institute of Arable Crop Research, University of Bristol, providing statistical support for scientists and developing a Genstat procedure for modelling seed germination.