Rhian Daniel MA MSc PhD

Research Fellow

I studied mathematics at Queens' College Cambridge for four years before coming to the LSHTM in 2004 to study for an MSc in Medical Statistics. From 2005 until 2008 I studied for my PhD (also at the School, in the Medical Statistics Unit) in missing data methods under the supervision of Mike Kenward. From October 2008 until September 2011, I was employed on an MRC-funded grant, entitled Quantitative methods for the assessment of systematic error in observational studies: improving causal research. In September 2011, I took up a Medical Research Council Career Development Award in Biostatistics, on the topic: Methods for addressing complex causal questions relating to health research in low- and middle-income countries. My sponsors at LSHTM are Bianca De Stavola, Simon Cousens and Mike Kenward. 

Affiliation

Teaching

I am the organiser and lecturer for the Robust Methods module on the MSc Medical Statistics course. I also give a lecture on time-varying confounding on the short course in Causal Inference in Epidemiology: Recent Methodological Developments, and assist with some of the practicals on this short course, as well as on the short course Advanced Course in Epdiemiological Analysis.

I have also been involved in external short course teaching, in Nairobi, Kenya and Bologna, Italy. In Autumn 2011, I will contribute to the teaching of short courses in Turin, Italy and Uppsala, Sweden.

Research

I work on methods for dealing with time-varying confounding in longitudinal observational studies, and also on the related problem of estimating direct and indirect causal effects.

In September 2011, I took up a Medical Research Council Career Development Award in Biostatistics, on the topic: Methods for addressing complex causal questions relating to health research in low- and middle-income countries. My sponsors at LSHTM are Bianca De Stavola, Simon Cousens and Mike Kenward. The fellowship will also involve a visit to North Carolina State University, where Butch Tsiatis will be my sponsor, and to Stijn Vansteelandt at Ghent University.

The project focuses on three situations in low- and middle-income countries in which epidemiologic data are used to address complex causal questions. The questions identified are complex as they face the problem of causal feedback. That is, interest lies in estimating the causal effect of a variable A on a variable B, but future values of A are also potentially affected by past values of B. For example, it is believed that high fertility leads to high child mortality and also that high child mortality can influence mothers' decisions to have more children. If the likely impact of family planning programmes on child mortality is to be estimated, then these two causal pathways – acting in opposing directions – must be teased apart.

Three methods (g-computation formula, inverse-probability-weighted-estimation of marginal structural models, g-estimation of structural nested models) have been developed by James Robins and colleagues to estimate causal effects in the presence of causal feedback, using longitudinal data.

We aim to apply these in settings where, hitherto, they have not been applied, extending them when the need arises. A strong focus is on making the methods more accessible to applied researchers by writing and extending software routines.

I am a member of the Centre for Statistical Methodology, and one of the co-ordinators of the Causal Inference theme.

Research areas

  • Statistical methods

Disciplines

  • Epidemiology
  • Statistics

Other interests

  • CSM
  • Causal Inference
  • Missing Data
Back to top