Address:

MRC Biostatistics Unit,
Institute of Public Health,
University Forvie Site,
Robinson Way,
Cambridge. UK.
CB2 0SR

Telephone Number:

Email Address:

Research Interests:

I lead a programme of research on the analysis of randomised trials, observational studies and meta-analysis, with particular focus on missing data, departures from randomised treatment and measurement error.

I give courses on:

• "Practical use of multiple imputation to handle missing data"
  See http://www.mrc-bsu.cam.ac.uk/MIcourse/
• "Missing data in mental health research: a practical approach using Stata"
  See http://www.mrc-bsu.cam.ac.uk/misscourse/
• "Handling missing outcome data in randomised trials"
  See http://www.mrc-bsu.cam.ac.uk/HTMRmiss/

• Using multiple imputation in practice.
• Allowing for informatively missing data, especially in randomised trials.
• PHSRN-funded project on Maximizing Return from Cohort Studies.
• Correct Stata do-files for my paper Allowing for missing outcome data and incomplete uptake of randomised interventions, with application to an Internet-based alcohol trial are available via these weblinks:
  - For missing data please click here.
  - For incomplete uptake ("non-compliance") please click here.

• Randomisation-based methods to allow for departures from randomised treatment (non-compliance).
• Allowing for changes to non-trial treatments.
• Handling time-dependent changes.
• Handling survival outcomes.
• I have written various pieces of Stata software to implement these methods.

• Handling measurement error in biochemical and dietary factors.
• Prognostic models.
• Collaborating in and developing statistical methods for the Fibrinogen Studies Collaboration, the Emerging Risk Factors Collaboration and the Centre for Nutrition and Cancer.

• Multivariate random-effects meta-analysis: download my Stata program mvmeta.
• Meta-analysis with missing data: download my Stata program metamiss.

• Down your drink, a web-based RCT of a web-based intervention to help people reduce their alcohol consumption.
• Other trials and observational studies in psychiatry, obstetrics, and cardiovascular disease.

• Various Stata software that I have written is available at
  http://www.mrc-bsu.cam.ac.uk/Software/stata.html

Selected Recent Publications:

Rapsomaniki E, White IR, Wood AM, Thompson SG, the Emerging Risk Factors Collaboration. A framework for comparing prognostic models based on net health benefits. Statistics in Medicine. Article first published online: 9 SEP 2011.
Weblink http://onlinelibrary.wiley.com/doi/10.1002/sim.4362/abstract

White IR, Wood A, Royston P. Tutorial in biostatistics: Multiple imputation using chained equations: issues and guidance for practice. Statistics in Medicine 2011; 30: 377–399.

White IR. Multivariate random-effects meta-regression. Stata Journal 2011; 11: 255–270.

White IR, Horton N, Carpenter J, Pocock SJ. Strategy for intention to treat analysis in randomised trials with missing outcome data. British Medical Journal 2011; 342: d40.

White IR, Carlin JB. Bias and efficiency of multiple imputation compared with complete-case analysis for missing covariate values. Statistics in Medicine 2010; 28: 2920–2931.

White IR, Daniel R, Royston P. Avoiding bias due to perfect prediction in multiple imputation of incomplete categorical variables. Computational Statistics and Data Analysis 2010; 54: 2267–2275.

White IR. simsum: Analyses of simulation studies including Monte Carlo error. Stata Journal 2010; 10: 369–385