Missing and imperfect data in clinical trials and observational studies

Lead Research Organisation: MRC Biostatistics Unit

Abstract

The statistical analysis of the ideal clinical trial is relatively straightforward, but in practice clinical trials usually run into two difficulties that complicate the analysis. Firstly, some participants may change from their allocated treatment. It is standard practice to estimate the benefit of allocation to an intervention, but we will develop ways to estimate the benefit of the intervention itself without resorting to a potentially deceptive comparison of those who do and do not receive the intervention. Secondly, some participants may not provide information about their final health state to the investigators. We will use some unusually rich data sets and some newly developed statistical methods to compare the health and other characteristics of participants who do and do not provide final health information. This will help researchers to know how to handle such missing information. Studies often attempt to relate health outcomes to dietary or biochemical factors that suffer from misreporting and day-to-day variation, and we will develop statistical methods to handle these difficulties in large, complex data sets. All of this work is informed by our collaborations on a variety of biomedical studies.

Technical Summary

This programme focuses on practical difficulties commonly encountered in randomised trials and observational studies. Much of the work is motivated by our collaborative research but seeks wide generalisability. We aim to provide feasible yet theoretically well-grounded solutions in three main areas: Missing data in RCTs and observational studies: We will use rich data structures and plausible assumptions to explore whether data are informatively missing. This work will extend existing models to the complexities of the QUATRO trial, the ALSPAC study, the CFAS study and a programme of smoking cessation trials. By estimating the missing data mechanisms in these and other studies, we will begin to establish an evidence base for the selection of suitable methods for dealing with missing data. Alongside this work we will identify and disseminate suitable methods in single studies and meta-analyses. Departures from randomised treatment in RCTs: We will extend existing methodology to handle the full complexity of departures typically found in RCTs. To handle switches to non-trial treatments, or cessation of all treatment in comparative trials, we will use information external to the trial about non-trial treatment contrasts. To handle time-dependent treatment changes with survival outcomes, we will develop a new potential outcomes model. We will also explore the implications of departures for health economic evaluations. Measurement error in observational studies: We will explore issues arising in the Fibrinogen Studies Collaboration, the Emerging Risk Factors Collaboration and the Centre for Nutrition and Cancer. Specifically, we will develop methods for practical adjustment for measurement error in exposure and confounders using replicate measurements of biochemical risk factors, taking account of possible non-linear associations, and methods for allowing for bias in dietary reports by using replicate measurements of different types. We will extend these methods to the meta-analysis situation, allowing for patterns of replicate measurements which differ between studies. These three areas are linked both practically, because studies rarely suffer from a single problem in isolation; theoretically, by common methods such as instrumental variables; and by a common formulation as missing data problems. They also all raise important design issues. In addition to the above, we will also maintain collaborations on randomised trials, including the evaluation of an internet intervention to reduce heavy drinking, and on observational studies, including development of new methods for the antenatal diagnosis of Downs syndrome, and we will pursue new methodological issues that arise from these collaborations.

Publications

10 25 50

publication icon
Baker R (2008) A new approach to outliers in meta-analysis. in Health care management science

publication icon
Baker R (2010) Inference for meta-analysis with a suspected temporal trend. in Biometrical journal. Biometrische Zeitschrift

publication icon
Baker R (2016) New models for describing outliers in meta-analysis. in Research synthesis methods

publication icon
Barrett JF (2014) Planned cesarean or vaginal delivery for twin pregnancy. in The New England journal of medicine

 
Description EMEA
Geographic Reach Europe 
Policy Influence Type Participation in a national consultation
 
Description Membership of ethics committee
Geographic Reach Local/Municipal/Regional 
Policy Influence Type Participation in a advisory committee
 
Description Multiple Imputation paper cited as one of twenty top papers to mark The BMJ's two digital decades
Geographic Reach National 
Policy Influence Type Citation in systematic reviews
URL http://www.bmj.com/content/351/bmj.h3660
 
Description NICE
Geographic Reach National 
Policy Influence Type Participation in advisory committee
 
Description Research Paper selected as Thorax Editor's Choice (October 2015 issue)
Geographic Reach National 
Policy Influence Type Influenced training of practitioners or researchers
URL http://thorax.bmj.com/content/70/10/930.abstract
 
Description Department for Children, Schools and Families
Amount £20,000 (GBP)
Organisation Department for Education 
Department Department for Children, Schools and Families (DCSF)
Sector Public
Country United Kingdom
Start  
 
Description MRC Population Health Sciences Research Network Grant
Amount £254,188 (GBP)
Funding ID PHSRN17 
Organisation Medical Research Council (MRC) 
Sector Academic/University
Country United Kingdom
Start 09/2006 
End 04/2014
 
Description Multiple imputation by chained equations for data that are missing not at random: methods development for randomised trials and observational studies (NARMICE)
Amount £145,164 (GBP)
Funding ID MC_EX_MR/M025012/1 
Organisation Medical Research Council (MRC) 
Department MRC/NIHR Methodology Research Programme
Sector Academic/University
Country United Kingdom
Start 01/2016 
End 12/2018
 
Title MNAR analysis methods 
Description We have developed methods for moving beyond missing-at-random analysis in clinical trials and observational studies in two ways. 1. Using ease-of-contact data to estimate the extent of departure from the missing-at-random analysis 2. Using investigator beliefs about the extent of departure from the missing-at-random analysis 
Type Of Material Improvements to research infrastructure 
Year Produced 2006 
Provided To Others? Yes  
Impact The method has been used in collaborations with Swedish researchers in randomised trials evaluating interventions to reduce hazardous drinking and to help smokers to quit. 
 
Title Inf cens 
Description This is a statistical method for handling censored time-to-event data when the censoring is believed to be informative. We proposed and validated a method for using multiple imputation to impute the censored event times. The method is intended to be used in a sensitivity analysis. 
Type Of Material Data analysis technique 
Year Produced 2015 
Provided To Others? Yes  
Impact The method was proposed to GSK researchers as a way of performing a sensitivity analysis that was being requested by the FDA. GSK used our method, by modifying our software code, and included it in their FDA submission. 
URL http://doi.wiley.com/10.1002/sim.6274
 
Title Using mvmeta for NMA 
Description Network meta-analysis models can be regarded as multivariate meta-regression. This means that software that we have written for multivariate meta-regression can be used to fit network meta-analysis models in a way that is much more easy to implement than the previous (WinBUGS) approach. 
Type Of Material Data analysis technique 
Year Produced 2011 
Provided To Others? Yes  
Impact The paper has more than 100 citations at March 2016. Roughly half of these are papers reporting network meta-analyses which have used our method. The other half are methodological developments. 
 
Title perfect prediction and augment 
Description Software for multiple imputation by chained equations can fail when perfect prediction occurs; further, perfect prediction is surprisingly common in complex data analyses. We explained the problem and proposed a simple "data augmentation" method to fix the problem. 
Type Of Material Data analysis technique 
Year Produced 2010 
Provided To Others? Yes  
Impact Our proposed solution has been implemented in three software packages: in Stata (both in our own implementation of multiple imputation and in the "official" implementation); in the MICE package for R; and in SAS, where our method was implemented (after consultation between us and the SAS programmers) in version 14.1 of PROC MI. 
 
Description Addenbrookes Hospital - Dan & vascular surgery 
Organisation University of Sydney
Department Faculty of Veterinary Science
Country Australia 
Sector Academic/University 
PI Contribution Statistical methods
Collaborator Contribution Medical research for joint papers
Impact PMID: 20122853; PMID: 21560121 Two papers submitted and currently under review (Nov 2011)
Start Year 2009
 
Description Astra Zeneca consulting 
Organisation AstraZeneca
Country United Kingdom 
Sector Private 
PI Contribution In thsi consultation, I advised on analyses of overall survival in the presence of treatment switching in the Iressa IPASS study.
Collaborator Contribution Astra Zeneca provided the draft report and asked the questions.
Impact None at present.
Start Year 2014
 
Description Astrazeneca informative censoring collaboration 
Organisation AstraZeneca
Country United Kingdom 
Sector Private 
PI Contribution We contributed codes and our expertise to develop an R package with Astrazeneca . A statistical software paper is to follow.
Collaborator Contribution AZ provided the person power to implement the R package using our methods.
Impact R package https://cran.r-project.org/web/packages/InformativeCensoring/index.html
Start Year 2016
 
Description BRC Rebecca Turner- BRC Evaluation and Implementation Theme 
Organisation National Institute for Health Research
Department NIHR Cambridge Biomedical Research Centre
Country United Kingdom 
Sector Public 
PI Contribution tbc
Collaborator Contribution tbc
Impact tbc
Start Year 2015
 
Description CNC 
Organisation Medical Research Council (MRC)
Department MRC Centre for Nutritional Epidemiology in Cancer Prevention and Survival (CNC)
Country United Kingdom 
Sector Public 
PI Contribution Provided statistical leadership and advised on design
Collaborator Contribution Provided data and encouraged particular lines of methodological research
Impact PMID: 20407088; PMID: 20648013; PMID: 20437091; PMID: 20702156; PMID: 20407088; PMID: 20648013 2 papers accepted for publication 3 papers in preparation
Start Year 2006
 
Description Case control book 
Organisation University of Oxford
Country United Kingdom 
Sector Academic/University 
PI Contribution Jointly writing a manuscript in case control studies
Collaborator Contribution Jointly writing a manuscript in case control studies
Impact Book to be finished in early 2012
Start Year 2009
 
Description DYD 
Organisation University College London
Department Research Department of Primary Care & Population Health
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical advice and discussion on design, conduct and analysis of RCT
Collaborator Contribution Data provision, particpated in ellicitacion exercise leading to development of methods for handling missing data
Impact PMID: 21948462; PMID: 21371988; doi:10.1371/journal.pone.0014740 Co-authors presented the results at Society for Academic Primary Care 1 paper in press 1 paper accepted for publication: McCambridge J, Kalaitzaki E, White IR, Khadjesari Z, Murray E, Linke S, Thompson SG, Godfrey C, Wallace P. Can differences in the length or relevance of questionnaires impact upon attrition in trials? A randomised controlled trial. Journal of Medical Internet Research
Start Year 2006
 
Description Dan & Salford 
Organisation University of Salford
Department Salford Business School
Country United Kingdom 
Sector Academic/University 
PI Contribution Joint research
Collaborator Contribution Joint research
Impact Papers published- PMID: 20740482; doi:10.1016/j.jspi.2009.09.017 One paper currently in preparation (Nov 2011)
 
Description ERFC 
Organisation University of Cambridge
Department Department of Public Health and Primary Care
Country United Kingdom 
Sector Academic/University 
PI Contribution Provided statistical leadership
Collaborator Contribution Provided inspiration for much methodological research and provided data
Impact PMID: 19622820; PMID: 21905066; PMID: 20439481
 
Description Exelixis consulting 
Organisation Exelixis
Country United States 
Sector Private 
PI Contribution This was a consultancy. I advised Exelixis on the analysis of 2 randomised trials with treatment switching, and performed some of the complex analyses.
Collaborator Contribution They provided data which I hope to use (with their permission) ina future publication.
Impact None
Start Year 2014
 
Description Finbarr to PhD day at GSK 
Organisation GlaxoSmithKline (GSK)
Country Global 
Sector Private 
PI Contribution PhD student presented poster at a research day for PhD students hosted by GSK
Collaborator Contribution Hosted the day.
Impact None as yet.
Start Year 2014
 
Description GSK/Royes 
Organisation GlaxoSmithKline (GSK)
Country Global 
Sector Private 
PI Contribution Supervising post-doc
Collaborator Contribution Supervising post-doc and providing clinical trial data for methodological re-analysis
Impact Multi-disciplinary - biostatistics and clinical trials/drug development. This project tackles multiple imputation of data after treatment discontinuation. Presentation to GSK's annual UK biostatistics meeting about the results.
Start Year 2015
 
Description ICE 
Organisation Medical Research Council (MRC)
Department MRC Clinical Trials Unit
Country United Kingdom 
Sector Public 
PI Contribution Joint research
Collaborator Contribution ADD PUBS LISTED AS ICE
Impact PMID: 21225900; doi:10.1016/j.csda.2010.04.005 One paper accepted for publication: Royston P, White IR. Multiple imputation by chained equations (MICE): implementation in Stata. Journal of Statistical Software Short courses on multiple imputation since 2008
Start Year 2006
 
Description ITT Group 
Organisation London School of Hygiene and Tropical Medicine (LSHTM)
Department Faculty of Epidemiology and Population Health
Country United Kingdom 
Sector Academic/University 
PI Contribution In depth discussions leading to development of new concepts
Collaborator Contribution In depth discussions leading to development of new conceptsIn depth discussions leading to development of new concepts
Impact PMID: 21300711 1 paper submitted
Start Year 2008
 
Description ITT Group 
Organisation Smith College
Department Department of Mathematics and Statistics
Country United States 
Sector Academic/University 
PI Contribution In depth discussions leading to development of new concepts
Collaborator Contribution In depth discussions leading to development of new conceptsIn depth discussions leading to development of new concepts
Impact PMID: 21300711 1 paper submitted
Start Year 2008
 
Description Ian - smoking cessation trials 
Organisation University of Cambridge
Department Cambridge Institute of Public Health
Country United Kingdom 
Sector Academic/University 
PI Contribution Working on the development of statistical methodology for smoking cessation trials
Collaborator Contribution Working on the development of statistical methodology for smoking cessation trials
Impact Two papers: Jackson D, Mason D, White IR, Sutton S (2012) An exploration of the missing data mechanism in an Internet based smoking cessation trial. BMC Medical Research Methodology 12: 157. Jackson D, White IR, Mason D, Sutton S (2014) A general method for handling missing binary outcome data in randomised controlled trials. Addiction 109: 1986-1993. Multi-disciplinary: biostatistics with behavioural research.
Start Year 2009
 
Description Informative censoring with astrazeneca and the university of Cambridge 
Organisation AstraZeneca
Country United Kingdom 
Sector Private 
PI Contribution We are jointly developing an R package to implement multiple imputation methodology when time-to-event data are informatively censored.
Collaborator Contribution We developed the methods and provided basic code. Astrazeneca are developing the code and the R package.
Impact None yet, but we anticipate an R package and a corresponding paper about it. We expect the package to be widely used in sensitivity analyses in the pharmaceutical industry and outside.
Start Year 2015
 
Description Informative censoring with astrazeneca and the university of Cambridge 
Organisation University of Cambridge
Department Department of Public Health and Primary Care
Country United Kingdom 
Sector Academic/University 
PI Contribution We are jointly developing an R package to implement multiple imputation methodology when time-to-event data are informatively censored.
Collaborator Contribution We developed the methods and provided basic code. Astrazeneca are developing the code and the R package.
Impact None yet, but we anticipate an R package and a corresponding paper about it. We expect the package to be widely used in sensitivity analyses in the pharmaceutical industry and outside.
Start Year 2015
 
Description IoP 
Organisation King's College London
Department Institute of Psychiatry, Psychology & Neuroscience
Country United Kingdom 
Sector Academic/University 
PI Contribution Detailed discussions about complex intervention trials and about missing data
Collaborator Contribution Detailed discussions about complex intervention trials and about missing data
Impact Course on missing data in mental health research (2010-2011)
Start Year 2009
 
Description Jane Walker - University of Oxford 
Organisation University of Oxford
Department Blavatnik School of Government
Country United Kingdom 
Sector Academic/University 
PI Contribution Contribute to the design, conduct and analysis of a pragmatic multicentre randomised controlled trial to compare the effectiveness and cost-effectiveness of Proactive Liaison Psychiatry with usual care.
Collaborator Contribution Lead on the design, conduct and analysis of a pragmatic multicentre randomised controlled trial to compare the effectiveness and cost-effectiveness of Proactive Liaison Psychiatry with usual care.
Impact None as yet
Start Year 2016
 
Description LSHTM- Shaun Seaman- Missing data in propensity score analyses using Electronic Health Record data 
Organisation London School of Hygiene and Tropical Medicine (LSHTM)
Country United Kingdom 
Sector Academic/University 
PI Contribution Providing PI and Co-PI input into the project
Collaborator Contribution tbc
Impact ttbc
Start Year 2014
 
Description Lupus 
Organisation Dalhousie University
Department Faculty of Medicine
Country Canada 
Sector Academic/University 
PI Contribution Statistical methods
Collaborator Contribution Medical research for one joint paper
Impact PMID: 21342917
Start Year 2010
 
Description MHRN 
Organisation King's College London
Department Institute of Psychiatry, Psychology & Neuroscience
Country United Kingdom 
Sector Academic/University 
PI Contribution Exchange of ideas
Collaborator Contribution Exchange of ideasexchange of ideas exchange of ideas
Impact Course preceding MHRN conference Planned workshop for 2012
Start Year 2006
 
Description MHRN 
Organisation University of Bristol
Department School of Social and Community Medicine
Country United Kingdom 
Sector Academic/University 
PI Contribution Exchange of ideas
Collaborator Contribution Exchange of ideasexchange of ideas exchange of ideas
Impact Course preceding MHRN conference Planned workshop for 2012
Start Year 2006
 
Description MHRN 
Organisation University of Manchester
Department School of Medicine Manchester
Country United Kingdom 
Sector Academic/University 
PI Contribution Exchange of ideas
Collaborator Contribution Exchange of ideasexchange of ideas exchange of ideas
Impact Course preceding MHRN conference Planned workshop for 2012
Start Year 2006
 
Description MIDIA 
Organisation London School of Hygiene and Tropical Medicine (LSHTM)
Department Faculty of Epidemiology and Population Health
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical analysis
Collaborator Contribution Data provision and expertiseData provisionStatistical expertiseExpertise in Medical StatisticsStatistical expertise
Impact One paper submitted; several papers in preparation (5 in total; with different collaborators) Members of staff gave talks at MIDEA (Missing Data and Exploratory Analysis Meeting)
Start Year 2007
 
Description MIDIA 
Organisation Medical Research Council (MRC)
Department MRC Clinical Trials Unit
Country United Kingdom 
Sector Public 
PI Contribution Statistical analysis
Collaborator Contribution Data provision and expertiseData provisionStatistical expertiseExpertise in Medical StatisticsStatistical expertise
Impact One paper submitted; several papers in preparation (5 in total; with different collaborators) Members of staff gave talks at MIDEA (Missing Data and Exploratory Analysis Meeting)
Start Year 2007
 
Description MIDIA 
Organisation Medical Research Council (MRC)
Department MRC Social & Public Health Sciences Unit
Country United Kingdom 
Sector Public 
PI Contribution Statistical analysis
Collaborator Contribution Data provision and expertiseData provisionStatistical expertiseExpertise in Medical StatisticsStatistical expertise
Impact One paper submitted; several papers in preparation (5 in total; with different collaborators) Members of staff gave talks at MIDEA (Missing Data and Exploratory Analysis Meeting)
Start Year 2007
 
Description MIDIA 
Organisation University College London
Department Institute of Child Health
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical analysis
Collaborator Contribution Data provision and expertiseData provisionStatistical expertiseExpertise in Medical StatisticsStatistical expertise
Impact One paper submitted; several papers in preparation (5 in total; with different collaborators) Members of staff gave talks at MIDEA (Missing Data and Exploratory Analysis Meeting)
Start Year 2007
 
Description MIDIA 
Organisation University of Bristol
Department School of Social and Community Medicine
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical analysis
Collaborator Contribution Data provision and expertiseData provisionStatistical expertiseExpertise in Medical StatisticsStatistical expertise
Impact One paper submitted; several papers in preparation (5 in total; with different collaborators) Members of staff gave talks at MIDEA (Missing Data and Exploratory Analysis Meeting)
Start Year 2007
 
Description MRC SPHSU 
Organisation Medical Research Council (MRC)
Department MRC Social & Public Health Sciences Unit
Country United Kingdom 
Sector Public 
PI Contribution Statistical expertise
Collaborator Contribution Joint research
Impact MRC SPHSU Technical report published- PMID: 21220355
Start Year 2007
 
Description NATSAL 
Organisation University College London
Department Department of Statistical Science
Country United Kingdom 
Sector Academic/University 
PI Contribution Supervising PhD student on missing data in NATSAL
Collaborator Contribution Co-supervising of PhD student
Impact None yet
Start Year 2009
 
Description NCI 
Organisation National Cancer Institute (NCI)
Country United States 
Sector Public 
PI Contribution Conduction joint research and writing joint papers
Collaborator Contribution Statistical expertise in measurement error in nutritional epidemiology
Impact Paper in preparation
Start Year 2010
 
Description Psychometrics 
Organisation University of Cambridge
Department School of the Humanities and Social Sciences
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical methods and data analysis
Collaborator Contribution Expertise in the subject area
Impact Two papers submitted and under review (2011)
Start Year 2010
 
Description Reading 
Organisation University of Reading
Department Department of Food and Nutritional Sciences
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical methods for estimating error in self-reported dietary measurements.
Collaborator Contribution Investigation into association between self-reported dietary intake and biomarkers for dietary intake.
Impact 1 paper submitted; 1 conference abstract submitted and another paper on preparation
Start Year 2009
 
Description Ruth polyps 
Organisation MRC-Technology
Country United Kingdom 
Sector Academic/University 
PI Contribution Advised on design of study to compare a new diagnostic tool for colorectal polyps with existing methods
Collaborator Contribution Working on joint grant called Development Gap Fund: Diagnosis of colorectal polyps using Optical Projection Tomography (OPT)
Impact N/A since the study is currently undergoing and statistical analysis will start in 2012
Start Year 2010
 
Description Shaun-UCL-prog models 
Organisation University College London
Department Department of Statistical Science
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical analysis
Collaborator Contribution Statistical expertise. Joint research
Impact DOI: 10.1002/sim.4371 One MRC Methodology grant application made
Start Year 2008
 
Description South Africa 
Organisation University of Cape Town
Department Statistical Sciences Cape Town
Country South Africa 
Sector Academic/University 
PI Contribution Research for one joint paper
Collaborator Contribution Research for one joint paper
Impact PMID: 21324180
Start Year 2010
 
Description THIN MI 
Organisation University College London
Department Research Department of Primary Care & Population Health
Country United Kingdom 
Sector Academic/University 
PI Contribution Helped prepare grant application. Contributing to statistical methods for imputing missing data in GP databases. Currently developing method for making best use of GP databases in general
Collaborator Contribution Proposed problems and facilitated discussions about missing data
Impact One paper published- PMID: 22052713 Publications in preparation.
Start Year 2009
 
Description Tim Morris PhD 
Organisation Medical Research Council (MRC)
Department MRC Clinical Trials Unit
Country United Kingdom 
Sector Public 
PI Contribution Supervising PhD student
Collaborator Contribution Hosting PhD student working on multiple imputation
Impact Presented poster at ISCB Confererence (2011). 3 methodological papers published. Not multi-disciplinary.
Start Year 2010
 
Description Tim Morris PhD 
Organisation University College London
Department Department of Statistical Science
Country United Kingdom 
Sector Academic/University 
PI Contribution Supervising PhD student
Collaborator Contribution Hosting PhD student working on multiple imputation
Impact Presented poster at ISCB Confererence (2011). 3 methodological papers published. Not multi-disciplinary.
Start Year 2010
 
Description University of Birmingham 
Organisation University of Birmingham
Department College of Life and Environmental Sciences
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical methodology
Collaborator Contribution Working on the methodology Grant application submitted
Impact PMID: 21268052 One paper submitted and one paper currently in preparation
Start Year 2009
 
Description University of Manchester 
Organisation University of Manchester
Department School of Medicine Manchester
Country United Kingdom 
Sector Academic/University 
PI Contribution Joint research and other expertise
Collaborator Contribution Provided data and inspired joint research
Impact PMID:19608601; PMID: 19608601 Workshop
Start Year 2006
 
Description Utah-biomarkers for disease progression in cystic fibrosis patients 
Organisation University of Utah
Department School of Medicine Utah
Country United States 
Sector Academic/University 
PI Contribution Providing statistical advice on methods for investigating biomarkers for disease progression in cystic fibrosis patients
Collaborator Contribution Leading research work
Impact Paper submitted and more data collection is under way
Start Year 2009
 
Title Predicting adverse outcomes in pregnancy 
Description Observational studies to predict adverse outcomes in pregnancy with a view to identifying women with high-risk pregnancies that would benefit from intervention 
Type Diagnostic Tool - Non-Imaging
Current Stage Of Development Initial development
Year Development Stage Completed 2010
Development Status Under active development/distribution
Impact Not known 
 
Title Randomised trials in community psychiatry 
Description Trials of improvements to service provision in community psychiatry: intensive case management, keyworker training in dual diagnosis work, crisis resolution team, adherence therapy. 
Type Health and Social Care Services
Current Stage Of Development Late clinical evaluation
Year Development Stage Completed 2010
Development Status On hold
Impact Informing practice in community psychiatry 
 
Title ehealth trials 
Description We have participated in a series of randomised controlled trials in e-health, evaluating online and mobile-phone interventions to help people reduce their alcohol consumption or (in different trials) to quit smoking. 
Type Preventative Intervention - Behavioural risk modification
Current Stage Of Development Late clinical evaluation
Year Development Stage Completed 2016
Development Status Under active development/distribution
Clinical Trial? Yes
Impact Our main achievements as methodologists have been demonstrating good methodology that can be used to design and analyse e-health trials, in particular allowing for high levels of non-compliance and missing data. See for example the paper at http://doi.wiley.com/10.1002/sim.4360. 
URL http://doi.wiley.com/10.1002/sim.4360
 
Title ABSORB software 
Description Software for conducting sensitivity analysis to publication bias in meta-analysis 
Type Of Technology Software 
Year Produced 2010 
Impact Not known yet 
 
Title RCTmiss module for Stata 
Description The -rctmiss- module for the statistical package Stata allows users to perform sensitivity analyses over a range of possible assumptions about the missing data mechanism. It was first realeased in 2010 and updated in 2017. 
Type Of Technology Software 
Year Produced 2017 
Open Source License? Yes  
Impact The software has been used in our course, "Handling missing outcome data in randomised trials". It has been cited in 13 protocols or reports of randomised trials (as at 16/02/2017). 
URL https://ideas.repec.org/c/boc/bocode/s458304.html
 
Title UVIS/ICE/MIM 
Description This was the first software for multiple imputation in the statistical package Stata. It was initially written by Patrick Royston (MRC CTU) and then developed and improved by him in collaboration with Ian White (MRC BSU). 
Type Of Technology Software 
Open Source License? Yes  
Impact The software was very widely used, with thousands of citations; the authors responded to hundreds of email queries about the software. Subsequently Stata Corporation, the author of Stata, decided to make their own implementation of multiple imputation. They drew heavily on our experience with our software, including our experience of what functionality users want and what methods are most practicable and most useful. The Stata manual (mi, page 21) acknowledges Patrick Royston and Ian White "for their comments and assistance in the development of mi" and "for their past and current contributions". 
URL https://ideas.repec.org/c/boc/bocode/s446602.html
 
Title metamiss module for Stata 
Description The -metamiss- module for the statistical package Stata provides a range of methods for handling incomplete binary data in meta-analysis. 
Type Of Technology Software 
Year Produced 2008 
Open Source License? Yes  
Impact Colleagues at the University of Ioannina have extended the methodology to handle incomplete quantitative data. We have now also collaborated to extend the software. We have given workshops on the methodology and software at Cochrane Colloquia. 
URL http://www.stata-journal.com/article.html?article=st0157
 
Title mvmeta software for Stata 
Description User-written -mvmeta- module for the Stata statistical package. The module performs multivariate meta-analysis and meta-regression. 
Type Of Technology Software 
Year Produced 2009 
Open Source License? Yes  
Impact 1. It led to a method for performing network meta-analysis that has proved to be easy to implement and widely used. As a result I have developed a dedicated network meta-analysis package for Stata, but the -mvmeta- module is the workhorse. 2. A similar package for the statistical package R has been written by Antonio Gasparrini (LSHTM). 3. Two papers describing this software have been cited approximately 300 times as at 16/02/2017. Of these, we estimate that approximately 100 are applied network meta-analyses which used this software. 
URL http://www.stata-journal.com/article.html?article=st0156_1
 
Title network software for Stata 
Description The -network- module for the statistical package Stata is an easy-to-use package to handle data for network meta-analysis and to fit consistency and inconsistency models (via calls to the -mvmeta- module). 
Type Of Technology Software 
Year Produced 2014 
Open Source License? Yes  
Impact Starting to be widely used, as judged from the number of emails I receive about it. Has featured in various publications including two in Chinese: http://www.cjebm.org.cn/Upload/PaperUpLoad/b24bfc39-bb0d-41b9-9f0f-93c3ba90353b.pdf and http://www.cjebm.org.cn/oa/DArticle.aspx?type=view&id=20150818. At 16/02/2017 its use had been explicitly reported in 6 applied network meta-analyses, and we believe it has been used more widely without explicit citation. 
URL http://www.stata-journal.com/article.html?article=st0410
 
Title simsum module for Stata 
Description The "simsum" module for Stata allows the user to quickly summarise the results of simulation studies, including calculationn of Monte Carlo standard errors which are frequently omitted. 
Type Of Technology Software 
Year Produced 2009 
Open Source License? Yes  
Impact Staff member gave a talk to the 2011 UK Stata Users Meeting. 
 
Description Alcohol and the media 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Media (as a channel to the public)
Results and Impact Presented a talk on 'Alcohol and the media' at an RSS meeting in London to Statisticians and Media representatives

Not known
Year(s) Of Engagement Activity 2007
 
Description An introduction to multivariate meta-analysis (course) 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? Yes
Type Of Presentation workshop facilitator
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Course entiotled "Introduction to multivariate meta-analysis" sparked very interesting questions and discussion afterwards

BSU strengthened its reputation as a major centre for knowledge transfer
Year(s) Of Engagement Activity 2014,2015
URL http://www.statslife.org.uk/events/eventdetail/241/-/-
 
Description Armitage Lectures 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Annual workshop and lecture created and hosted by the MRC Biostatistics Unit, to honour the immense contributions of Professor Peter Armitage who was at the unit from 1947 to 1961, and whose work is recognised throughout the world as achieving a successful balance between methodological rigour and applied commonsense, to which all statisticians aspire. An eminent medical statistician visits for a week and works with members of the unit. The highlight is the Armitage Lecture, where more than 100 delegates attend. This event raises the unit research profile and creates new collaborations.
Year(s) Of Engagement Activity Pre-2006,2006,2007,2008,
URL https://www.mrc-bsu.cam.ac.uk/news-and-events/armitage-lectureships-and-workshops/
 
Description Article for CMAJ Blogs 
Form Of Engagement Activity Engagement focused website, blog or social media channel
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact PhD student (SC) wrote article for CMAJ Blogs on 'On Reach, Engagement and Dissemination - Shouldn't People Read the Paper?'.
Blog about Domhnall MacAuley's Bradford Hill Seminar on 'The Future of Medical Publishing' - discussing widening the reach and spread of published articles.
Blog has ben well received and provoked readers to consider how they communicate research messages in their papers.
Blog was also published on MRC BSU website.
Year(s) Of Engagement Activity 2015
URL http://cmajblogs.com/on-reach-dissemination-and-engagement-shouldnt-people-read-the-paper/
 
Description BBC News - Statistical analysis of Stricly Come Dancing winners 
Form Of Engagement Activity A magazine, newsletter or online publication
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Media (as a channel to the public)
Results and Impact PhD student, Susan Connolly, assisted with statistical analysis for BBC News article about predicting the winner of Stricly Come Dancing 2017 (http://www.bbc.co.uk/news/entertainment-arts-41280119 ). Susan's analyis and predictions were mentioned and praised in a subsequent article in Significance magazine (https://www.significancemagazine.com/culture/576-statistical-analysis-strictly-on-request)
Year(s) Of Engagement Activity 2017,2018
URL https://www.significancemagazine.com/culture/576-statistical-analysis-strictly-on-request
 
Description BSA Science Discussion Panel 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Professional Practitioners
Results and Impact PhD student, Susan Connolly, took part in BSA Science Discussion Panel in Edinburgh, debating science, statistics and the media
Year(s) Of Engagement Activity 2017
 
Description BSU Open Day 
Form Of Engagement Activity Participation in an open day or visit at my research institution
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Schools
Results and Impact Unit held open day as part of MRC Festival of Medical Research.

The aim of the open day was to welcome secondary school students and members of the general public to come to the unit, find out about the research the unit does, and to take part in activities that illustrate BSU research, with the overall theme being 'Fun with statistics'. An open day of this format was a first for the unit and overall it was a very successful event. There were 40 attendees over a 4 hour event. All attendees pre-booked and were split into 4 groups for a 1 hour session comprising of an introduction, participation in hands-on activities, and a brief careers talk. The small groups and length of session allowed for quality engagement between the scientists and the audience.

Feedback from the attendees was very positive, and the wider MRC Festival activities that took place in Cambridge demonstrated the benefits in delivering these types of events.
Year(s) Of Engagement Activity 2016
URL http://www.mrc-bsu.cam.ac.uk/bsu-open-day-2016-why-are-statistics-important/
 
Description Big Biology Day 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact Participation in Big Biology Day, organised by Hills Road Sixth Form College in Cambridge - a one day annual 'science festival' event open to memebers of the general public to participate in a range of biology based hands-on activities for all ages.

BSU presented a stand with three hands-on, interactive activities, each communicating a simple statistical method or idea, linked to the unit's research themes.
Year(s) Of Engagement Activity 2016
URL http://www.hillsroad.ac.uk/college-life/events/2016/10/15/default-calendar/big-biology-day
 
Description Cambridge Science Festival 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? Yes
Type Of Presentation Workshop Facilitator
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact Families, schools and general public from all around the Cambridge region attend Cambridge Science Festival interactive displays, exhibist, talks and other related events.
For the 2015 edition, the Festival welcomed over 30,000 visitors to over 200 events and received extensive national and local media coverage. The BSU stand was presented at two separate venues over two dates reaching out to hundreds of children and adults and communicating basic statistical methods, based on BSU research.

Raised awareness of the Unit's work in the local schools community.
Very good feedback from festival attendants.
Year(s) Of Engagement Activity 2007,2008,2009,2011,2012
URL http://www.cam.ac.uk/science-festival
 
Description Cambridge Science Festival 
Form Of Engagement Activity Participation in an open day or visit at my research institution
Part Of Official Scheme? Yes
Geographic Reach Regional
Primary Audience Schools
Results and Impact As well as being entertaining and educational, this activity may encourage school children to consider a career in Statistics or medical research. It also helps adults to understand what medical researchers paid for by their taxpayers' money are doing.

N/A
Year(s) Of Engagement Activity 2012,2014,2015
 
Description Contributed talk at Bayes Pharma (CDI) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Industry/Business
Results and Impact Talk given and useful discussion followed.
Year(s) Of Engagement Activity 2016
 
Description Contributed talk at Cochrane Colloquium 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Approximately 80 researchers were in the audience. There were some interesting questions and discussion, which continued later into the lunchbreak. Several people came to discuss how the work I presented could help with their own research problems.
Year(s) Of Engagement Activity 2015
 
Description Contributed talk at International Society for Clinical Biostatistics conference 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Talk was attended by approximately 25 people. There was useful discussion afterwards and ideas were exchanged with researchers working in similar areas.
Year(s) Of Engagement Activity 2016
 
Description Contributed talk at International Society for Clinical Biostatistics conference (CDI) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Talk presented and useful discussion followed.
Year(s) Of Engagement Activity 2016
 
Description Contributed talk at International Society for Clinical Biostatistics conference (KR) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Useful discussion after the talk.
Year(s) Of Engagement Activity 2016
 
Description Contributed talk at Royal Statistical Society conference 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Other academic audiences (collaborators, peers etc.)
Results and Impact Plenty of discussion during the session, and talked to several people about the research later in the conference.

Received some useful feedback which will help with the next stage of this research.
Year(s) Of Engagement Activity 2014
 
Description Contributed talk at Royal Statistical Society conference (KR) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Other academic audiences (collaborators, peers etc.)
Results and Impact Good questions and interesting discussion after the session.

Useful feedback from several researchers working in related areas.
Year(s) Of Engagement Activity 2014
 
Description Contributed talk at Society for Research Synthesis Methodology (CDI) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Talk given and useful discussion and feedback followed.
Year(s) Of Engagement Activity 2016
 
Description Contributed talk at Society for Research Synthesis Methodology conference (KR) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Other academic audiences (collaborators, peers etc.)
Results and Impact Useful discussion and feedback from the audience.

Good feedback and requests for paper presenting this work.
Year(s) Of Engagement Activity 2014
 
Description Course on "Use of historical control data" 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Industry/Business
Results and Impact 20 industry statisticians attended a course on use of historical control data (including meta-analysis methods). There was very positive feedback and we have been asked to rerun the course soon for those who were on the waiting list and didn't get a place.
Year(s) Of Engagement Activity 2016
 
Description Eliciting and using expert opinions about non-response bias in RCTs 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Type Of Presentation Keynote/Invited Speaker
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact Presented a talk on 'Eliciting and using expert opinions about non-response bias in RCTs' in Chester to Statisticians at the PSI conference

Raised awareness of the Unit's work
Year(s) Of Engagement Activity 2007
URL http://ctj.sagepub.com/content/4/2/125.refs
 
Description FameLab 2016 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact PhD student (SC) participated in FameLab 2016 and successfully reached the regional finals.
FameLab is a science communications competition for scientists, mathematicians and engineers across the globe to take part in.
Contestants have just 3 minutes to convey a scientific concept of their choice. They are judged by leading researchers, media personalities and science policy makers on the content, clarity and charisma of their presentation.
Year(s) Of Engagement Activity 2016
URL http://www.cheltenhamfestivals.com/about/famelab/
 
Description German Region of the International Biometric Society conference, Dortmund: invited speaker. 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact German Region of the International Biometric Society conference, Dortmund: invited speaker. I gave an invited talk on network meta-analysis.
Year(s) Of Engagement Activity 2015
 
Description How multiple imputation hit the mainstream 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Health professionals
Results and Impact Feedback from participants was very good.
The MRC Clinical Trials Unit at UCL (MRC CTU) celebrated the work of three of its most eminent scientists with a one-day seminar on 08 April. Professors Abdel Babiker, Andrew Nunn and Patrick Royston have between them been funded by the MRC for a total of 95 years.The day was made up of scientific presentations from collaborators with whom the three have worked closely.
Patrick Royston is a Professor of Statistics who has made remarkable contributions to several areas of biostatistics. Dr Ian White discussed Patrick's work on multiple imputation modelling, which is used in statistical analysis to help deal with missing data.



This event provided us with the opportunity to meet up with past and current research collaborators
Year(s) Of Engagement Activity 2014
URL http://www.ctu.mrc.ac.uk/news/2014/95_years_of_research_for_the_mrc_140414
 
Description ISCB course Demystifying causal inference 2016 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact 40 researchers from many countries attended a course at the 2016 conference of the International Society for Clinical Biostatistics in Birmingham, UK. The course was entitled "Demystifying causal inference in randomised trials".
Year(s) Of Engagement Activity 2016
 
Description Ian / DATES TSC 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Member of the Trial Steering Committee for the DATES trial evaluating a mobile-phone intervention to improve diabetic control of diabetis patients in Kuwait. Making statistical input.
Year(s) Of Engagement Activity 2016
 
Description Ian/Novartis trtchg course 2016 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Gave a 1.5-day course on "Methods to adjust for treatment switching in randomised controlled trials" to Novartis in Basel, Switzerland. Participants were actively involved in analysing trials with treatment switching and learned ways to improve their analyses and choose the right analysis.
Year(s) Of Engagement Activity 2016
 
Description Incorporating external evidence on heterogeneity and bias in meta-analysis (Royal Statistical Society Conference, Exeter) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Other audiences
Results and Impact Statisticians attended this talk, which led to discussion of the research and interest in using informative priors for between-study heterogeneity in meta-analysis.
Year(s) Of Engagement Activity 2015
 
Description InterTASC course 2016 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact 30 researchers, mainly members of technology assessment groups (TAGs) contributing to technology appraisals by the National Institute for Health and Clinical Excellence (NICE), attended a one-day workshop on handling treatment switching in technology appraisals.
Year(s) Of Engagement Activity 2016
 
Description International Conference of the ERCIM on Computational and Methodological Statistics, London. Invited speaker 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact International Conference of the ERCIM on Computational and Methodological Statistics, London. Invited speaker. I gave an invited talk on methods for repeated attempts modelling for missing data.
Year(s) Of Engagement Activity 2013
 
Description Invited course in Switzerland on missing data methods 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Postgraduate students
Results and Impact Invited to give a course to PhD students from all over western half of Switzerland on methods for handling missing data.
Year(s) Of Engagement Activity 2016
 
Description Invited participation in workshop at Cochrane Colloquium 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact The workshop included presentations, with plenty of time for discussion and audience participation. There was a good debate of current practice in Cochrane reviews and the need for improvement.
Year(s) Of Engagement Activity 2015
 
Description Invited speaker at the London School of Hygiene and Tropical Medicine seminar series. 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Invited speaker at the London School of Hygiene and Tropical Medicine seminar series. I gave a talk on network meta-analysis.
Year(s) Of Engagement Activity 2013
 
Description Invited talk at Hubs for Trials Methodology Research network meeting (CDI) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Talk given and useful discussion followed
Year(s) Of Engagement Activity 2016
 
Description LSE missing data course 2016 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact 30 researchers attended a course on "Multiple imputation methods for addressing missing data in cost-effectiveness analysis of clinical trials" at LSE. I was invited to give a lecture on "Introduction to multiple imputation (MI) for handling missing data in Stata".
Year(s) Of Engagement Activity 2016
 
Description Lecture to Cambridge undergraduates 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Undergraduate students
Results and Impact Audience appeared engaged, and we had some good discussion.

Several of the undergraduates attending this series of lectures expressed interest in applying for a PhD position at the MRC Biostatistics Unit.
Year(s) Of Engagement Activity 2012,2013,2014,2015,2016
 
Description MRC Board Advisory Group for Unit for Integrative Epidemiology 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Health professionals
Results and Impact The MRC Board Advisory Group for Unit for Integrative Epidemiology works with the Unit to develop a structure that enables public views to be fed into the Institute's strategic thinking, ensures excellent engagement across the research lifecycle, and is complementary to and knitted in with other relevant developments across the University of Bristol; ensuring that the academic and societal impact of the scientific research will grow, with an increasing focus on industrial partnerships as their methodological advances become more relevant to a translational context.

N/A
Year(s) Of Engagement Activity 2012,2013
URL http://www.bristol.ac.uk/integrative-epidemiology/
 
Description MRC Centenary Open Day 
Form Of Engagement Activity Participation in an open day or visit at my research institution
Part Of Official Scheme? No
Type Of Presentation Workshop Facilitator
Geographic Reach Local
Primary Audience Public/other audiences
Results and Impact Helped out in writing contents for the exhibit as well as manning the Unit's display.
50 + people attended an exhibition about the history, pioneers and discoveries of the MRC Biostatistics Unit, and a series of talks and lectures as part of the BSU contribution to MRC Centenary Open Days

Raised the profile of the Unit in the local region
Year(s) Of Engagement Activity 2013
URL http://www.mrc-bsu.cam.ac.uk/NewsandEvents/mrccentenary.html
 
Description Media enquiry - BBC News 
Form Of Engagement Activity A press release, press conference or response to a media enquiry/interview
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Media (as a channel to the public)
Results and Impact Article in BBC News on hidden red hair gene in skin cancer - article linked to research paper, co-authored by Finbarr Leacy, PhD student: http://www.ncbi.nlm.nih.gov/pubmed/27403562
Year(s) Of Engagement Activity 2016
URL http://www.bbc.co.uk/news/uk-36795219
 
Description Medical Research Council's Methodology Research Panel 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Health professionals
Results and Impact Take decision in funding from MRP, methodology research includes: Methods development to underpin the biomedical and health-related sciences, with methodological outputs that are applicable beyond a specific case study. And 'Methods in research' for developing methods and their implementation in research standards with the aim of improving quality and consistency in practice, for example consensus statements.

N/A
Year(s) Of Engagement Activity 2008,2009,2010,2011,2012
URL http://www.mrc.ac.uk/funding/browse/methodology-research-programme/
 
Description Member of DMEC for Vitamin D supplementation trial 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Health professionals
Results and Impact Appointed member of the Data Monitoring and Ethics Committee (DMEC) for Vitamin D supplementation trial

This trial was adopted by the NIHR Diabetes Research Network with the support of the North East London Diabetes and the Eastern Diabetes Local Research Networks.
A Study protocol was published, acknowledging the work of IW as part of the DMEC: The effects of vitamin D2 or D3 supplementation on glycaemic control and related metabolic parameters in people at risk of type 2 diabetes: protocol of a randomised double-blind placebo-controlled trial
Year(s) Of Engagement Activity 2010,2011,2012,2013
URL http://www.biomedcentral.com/1471-2458/13/999
 
Description Member of TSC for DIAMOND trial: Digital Alcohol Management On Demand 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? Yes
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Apointed member of TSC for DIAMOND trial: Digital Alcohol Management On Demand (2014-2016)
Digital Alcohol Management On Demand (DIAMOND): Excess alcohol consumption is the second most important risk factor for avoidable long term conditions and premature mortality in the UK, with eight million adults in England drinking over current guidelines for safe alcohol consumption. Excess alcohol consumption is a highly tractable behaviour, but treatment availability is limited by costs and lack of trained staff. Online alcohol treatments may help overcome these barriers. The DIAMOND study will determine the feasibility of a definitive trial to compare the effectiveness and cost-effectiveness of supported access to a web-based alcohol intervention - Healthy Living for People who Drink (HELP-Drink) with traditional face to face treatment. The DIAMOND feasibility study will be rolled out in the inner city London boroughs of Islington, Camden and Haringey. Following this we will apply for external funding to conduct a Randomised Controlled Trial to establish whether an online intervention is as effective, and more cost-effective than traditional face-to-face counselling for alcohol.

The DIAMOND study will determine the feasibility of a definitive trial to compare the effectiveness and cost-effectiveness of supported access to a web-based alcohol intervention - Healthy Living for People who Drink (HELP-Drink) with traditional face to face treatment. The DIAMOND feasibility study will be rolled out in the inner city London boroughs of Islington, Camden and Haringey. Following this we will apply for external funding to conduct a Randomised Controlled Trial to establish whether
Year(s) Of Engagement Activity 2014,2015,2016
URL http://www.clahrcpp.co.uk/#!behaviour-change-newsletter/c1z9i
 
Description Member of Trial Steering Committee for STAMPP trial 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? Yes
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Appointed Member of Trial Steering Committee for STAMPP trial (effectiveness of a schools based alcohol education programme in Northern Ireland and Glasgow) .
Given the prevalence of underage drinking in the UK, the reported problems, costs and harms associated with this behaviour, and the lack of a robust UK evidence base for alcohol prevention the STAMPP trial wish to investigate the effectiveness of a school based alcohol education curriculum with parental training components in reducing hazardous levels of drinking and alcohol related harms in school children.
When is study starting and how long is it expected to run for? The study will start in 2011 and last for 53 months.

Report to be publisehd in 2016: PHR - 10/3002/09: Steps towards alcohol misuse prevention programme (STAMPP): a school and community based cluster randomised controlled trial
Year(s) Of Engagement Activity 2011,2012,2013,2014,2015
URL http://www.nets.nihr.ac.uk/projects/phr/10300209
 
Description Member of Trial Steering Committee, SIPS junior trial 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? Yes
Geographic Reach National
Primary Audience Health professionals
Results and Impact Member of Trial Steering Committee SIPS Trials 2011-2016.
This research programme will provide estimates of the level of alcohol consumption and alcohol-related problems in adolescents attending ED. It will also develop, implement and evaluate screening and alcohol interventions for adolescents in the ED setting.
The programme will be conducted over the next 5 years and provide estimates of prevalence, optimum screening tools, and age appropriate alcohol intervention guidelines.

N/A as yet.
Aim: The programme will be conducted over the next 5 years and provide estimates of prevalence, optimum screening tools, and age appropriate alcohol intervention guidelines.
This research will have important implications and impact both on the way adolescent drinkers are managed in ED, and on the prevention of future alcohol-related harm in this population through targeted early interventions. Outputs from the research will include age appropriate screening and intervention methods for use by NHS staff, including training packages and methods. The research team is highly experienced in addiction research and has recently completed a similar programme of research in adults in ED and other health and criminal justice settings for the Department of Health.
Year(s) Of Engagement Activity 2010,2011,2012,2013,2014
URL http://www.sipsjunior.net/
 
Description Member of trial steering committee, POSNOC trial 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? Yes
Geographic Reach National
Primary Audience Health professionals
Results and Impact Appointed member of trial steering committee, POSNOC trial (2014-2019): POSNOC - A randomised trial of armpit (axilla) treatment for women with early stage breast cancer.

The POSNOC trial will provide evidence relevant to patients and to the NHS. The protocol has been designed to integrate into current NHS
practice.
The hypothesis of the POSNOC trial is that low axillary tumour burden patients (clinically and ultrasound negative) with macrometastases in 1 or 2 SNs, receiving systemic therapy, would have non-inferior outcomes whether they are randomised to adjuvant therapy alone or adjuvant therapy plusaxillary treatment (ANC or ART)
Year(s) Of Engagement Activity 2014
URL http://www.nets.nihr.ac.uk/__data/assets/pdf_file/0004/111469/PRO-12-35-17.pdf
 
Description Missing Data in Mental Health Research Course 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Health professionals
Results and Impact 1 day course for 20 statisticians and investigators.
Participants introduced to some accessible methods for analysing mental health studies in the presence of missing data, but also to be aware of the pitfalls and limitations of the techniques.
We provide a number of practical examples from our own experience of analysing data in mental health research.
We provide step-by-step instructions for carrying out analyses in Stata with the practical sessions dedicated to hands-on analysis of mental health data sets.

Feedback from participants was very good.
This course is now in its 4th year (2013).
Year(s) Of Engagement Activity 2010,2011,2013
URL http://www.mrc-bsu.cam.ac.uk/training/short-courses/
 
Description Missing Outcomes in Randomised Trials Course 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Health professionals
Results and Impact 1 and 2 day course for 25 statisticians-
This is a MRC Biostatistics Hub for Trials Methodology Research activity.
The course provided practising statisticians with the necessary practical skills to handle missing data in their analyses, and in particular to move beyond the use of complete-case analysis and last observation carried forward analysis.
Has been run 3 times in Cambridge, once in Melbourne, Australia and once (as a pre-confernce course) in Vienna, Austria.



Feedback from participants was excellent.
Year(s) Of Engagement Activity 2011,2012,2013,2014
URL http://www.mrc-bsu.cam.ac.uk/training/short-courses/
 
Description Multiple Imputation Course 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Each course is a 2 day course for 30 scientists needing to tackle missing data in their research. Feedback has always been excellent. Many of the attendees have gone on to use multiple imputation.

We haved gone on to write two methodological papers with people who have attended the course (doi 10.1186/s13104-016-1853-5; 2nd accepted but not yet published).

We have also written a highly cited tutorial paper (>1000 citations at March 2016) based in the material in the course and our experiences of teaching the course.

Course has now been repeated successfully 9 times in Cambridge and once (as a 1-day course) in Birmingham.
Year(s) Of Engagement Activity 2008,2009,2010,2011,2012
URL http://www.mrc-bsu.cam.ac.uk/MIcourse/
 
Description Net health benefit as a measure of prognostic ability 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Other academic audiences (collaborators, peers etc.)
Results and Impact Talk sparked very interesting questions and discussion afterwards

Netwroking opportunities arised for possible future research collaborations
Year(s) Of Engagement Activity 2014
 
Description Network meta-analysis talk at LSHTM 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? Yes
Geographic Reach Regional
Primary Audience Professional Practitioners
Results and Impact Talk sparked questions and discussion afterwards.


Networking opportunities arised for possible futere collaborations.
Year(s) Of Engagement Activity 2014
URL http://www.lshtm.ac.uk/newsevents/events/2014/01/network-meta-analysis
 
Description Network meta-analysis: the frequentist alternative 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Other academic audiences (collaborators, peers etc.)
Results and Impact Feedback from participants was very good.

Networking opportinities arised for possible future research collaborations
Year(s) Of Engagement Activity 2014
 
Description Parliamentary Links Event 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Policymakers/politicians
Results and Impact PhD student, Susan Connolly, attended Parliamentary Links Event at House of Lords, speaking with MPs about the importance of statistical research, organised through RSS Ambassador Programme
Year(s) Of Engagement Activity 2017
 
Description Parliamentary Links Lunch 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Policymakers/politicians
Results and Impact PhD student, Susan Connolly, attended Parliamentary Links Lunch at House of Lords, meeting Daniel Zeicher MP, discussing importance of statistics (organised via RSS Ambassador Scheme)
Year(s) Of Engagement Activity 2017
 
Description Pooling cohorts, Cambridge 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Type Of Presentation Keynote/Invited Speaker
Geographic Reach Local
Primary Audience Health professionals
Results and Impact Around 50 health professionals from different backgrounds attended event

N/A
Year(s) Of Engagement Activity 2011
 
Description Poster presentation at Clinical Trials Methodology conference 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Other academic audiences (collaborators, peers etc.)
Results and Impact Useful discussion.

Discussion with researchers working in related areas was helpful for planning next stages of research.
Year(s) Of Engagement Activity 2013
 
Description Poster presentation at International Society for Clinical Biostatistics conference (KR) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Other academic audiences (collaborators, peers etc.)
Results and Impact Useful discussion and feedback.

Useful feedback, and requests for receiving paper presenting this work.
Year(s) Of Engagement Activity 2014
 
Description Providing advice to MRC Methodology Panel 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? Yes
Geographic Reach National
Primary Audience Other academic audiences (collaborators, peers etc.)
Results and Impact The MRC Methodology Panel drew up a call for grant applications, a call which used the information in the report that we had given them.

The MRC Methodology Panel has received a number of grant applications in this area.
Year(s) Of Engagement Activity 2013
 
Description Royal Statistical Society Conference, Exeter: Invited speaker. 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Other audiences
Results and Impact Royal Statistical Society Conference, Exeter: Invited speaker.I gave an invited talk on stratified medicine.
Year(s) Of Engagement Activity 2015
 
Description STEM Fair 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Schools
Results and Impact Participation in STEM Fair at Duxford Imperial War Museum - an enrichment day for secondary school students in the region to learn and be inspired by the various scientific organisations in the area. BSU presented a workshop to 2x sets of 20 Year 10 students, leading 2 interactive activities, analysing and investigating hyperthetical data from human related studies, answering a series of questions about the data.

Both workshops were very successful, inspiring students and nurturung a future generation of statisticians.
Year(s) Of Engagement Activity 2016
URL http://www.mrc-bsu.cam.ac.uk/inspiring-with-statistics-at-stem-fair-2016/
 
Description Scientific Program Committee for ISCB 2014 (Vienna ) 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Health professionals
Results and Impact The International Society for Clinical Biostatistics was founded in 1978 to stimulate research into the principles and methodology used in the design and analysis of clinical research and to increase the relevance of statistical theory to the real world of clinical medicine.


The ISCB annual conference provides a scientific forum for international exchange of theory, methods and applications of biostatistics in medical research and practice among clinicians, statisticians and members of other disciplines, such as epidemiologists, clinical chemists and clinical pharmacologists, working or interested in the field of clinical biostatistics.
Year(s) Of Engagement Activity 2012,2013,2014
URL http://www.iscb.info/
 
Description Simulations course 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact We gave a one-day course on "Using simulation studies to evaluate statistical methods". The audience were reasearchers either using or planning to use simulation studies in order to develop or evaluate statistical methods. Feedback indicated that the audience felt empowered to start or improve their use of simulation studies. The course was repeated in 2016 & 2017.
Year(s) Of Engagement Activity 2015,2016,2017
URL https://sites.google.com/site/simulationstudies/home
 
Description Speaker at MRC Biostatistics Unit / AstraZeneca one-day Science Symposium at Churchill College Cambridge 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Industry/Business
Results and Impact Scientists from the MRC Biostatistics Unit and from AstraZeneca arranged a day of talks about work that could be of mutual interest. I gave one of these talks, presenting my work.
Year(s) Of Engagement Activity 2015
URL http://www.mrc-bsu.cam.ac.uk/biostatisticians-and-data-scientists-working-together-in-service-of-pat...
 
Description Talk at the annual meeting of the Society for Research Synthesis Methodology, Florence. 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Talk at the annual meeting of the Society for Research Synthesis Methodology, Florence.
Year(s) Of Engagement Activity 2016
 
Description Talk at the annual meeting of the Society for Research Synthesis Methodology, York. 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Talk at the annual meeting of the Society for Research Synthesis Methodology, York. I gave a talk on methods for network meta-analysis.
Year(s) Of Engagement Activity 2014
 
Description Talk given for the University of Warwick Bridges Colliquium 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Postgraduate students
Results and Impact Talk given on methods for meta-analysis for the Warwick Bridges Colliqium
Year(s) Of Engagement Activity 2016
 
Description Talk to MRC Epidemiology Genetics Group 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Type Of Presentation Keynote/Invited Speaker
Geographic Reach Local
Primary Audience Health professionals
Results and Impact Talk given to the MRC Epidemiology Unit, Genetics Group

None as yet
Year(s) Of Engagement Activity 2009
 
Description The Times Internship 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Type Of Presentation Workshop Facilitator
Geographic Reach International
Primary Audience Media (as a channel to the public)
Results and Impact Team member spent a week at The Times Online offices in London sharing expertise between statisticians and journalists, as well as promoting understanding of statistics and best practice in their use in reporting.

Raised awareness of the work of the Unit in the media
Year(s) Of Engagement Activity 2009,2010
URL http://www.mrc-bsu.cam.ac.uk/NewsandEvents/July2010_6_Times.html
 
Description Treatment changes course for Novartis 2011 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Professional Practitioners
Results and Impact 10 employees of the pharmaceutical sector attended a one-day course on analysis of late stage cancer trials with treatment switching

N/A
Year(s) Of Engagement Activity 2011
 
Description UCL Partners Biostatistics Network Symposium Contemporary Statistical Methods in Medical Research 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? Yes
Type Of Presentation keynote/invited speaker
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact This event facilitated communication, interaction and collaboration between member statisticians

Networking enabled possible future research collaborations / knowledge transfer opportunities
Year(s) Of Engagement Activity 2014
URL http://www.ucl.ac.uk/statistics/biostatistics-network/talks/TalkWhite.pdf
 
Description UMIT course 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact A series of lectures and practicals on Treatment Switching in Randomised Trials was given in Hall, Austria as part of a 4-day course on Causal Inference Methods.
Year(s) Of Engagement Activity 2016,2017,2018
URL https://www.umit.at/page.cfm?vpath=departments/public_health/htads-continuing-education-program/caus...
 
Description Visitor to the University of North Carolina Biostatistics Department (one week). 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Other audiences
Results and Impact Visitor to the University of North Carolina Biostatistics Department (one week). I visited the university as part of our collaboration with this group.
Year(s) Of Engagement Activity 2013
 
Description network.ado at Stata Users 2013 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? Yes
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Talk sparked questions and discussion afterwards

Networking opportinities arised for possible future research collaborations
Year(s) Of Engagement Activity 2013
URL http://www.stata.com/meeting/uk13/abstracts/