Statistical modelling: theory and applications

Lead Research Organisation: MRC Biostatistics Unit

Abstract

The human and financial costs associated with medical research motivate efforts to make the best possible use of the data collected. Appropriate statistical methodology helps to reveal findings that can provide information on the relationship between disease and genetic and lifestyle factors, and help to provide informed treatment choices for diseased individuals. We aim to apply the most appropriate methodology to studies in a variety of areas, including rheumatology and cancer, and to develop, when necessary, new methods for the analysis of medical data

Technical Summary

We propose to develop methods of statistical inference for the analysis of longitudinal data and other challenging data structures. Much of the work will derive from specific areas of medical research but, generally, will have broader applicability. Methodological work on methods of analysis in the presence of informative observation will be considered, motivated by various longitudinal studies. Other methodological investigations will address the analysis of two part models for data which are “zero-heavy” and extensions of the analysis of plaid-square designs to generalised linear models. Our major collaborations in rheumatology will continue. Based on a cohort of patients with psoriatic arthritis, we will consider the modelling of individual joint damage and quality of life, the definition of outcome variables for clinical trials and genetic determinants of disease and disease course. For systemic lupus erythematosus patients, we will continue studies of neuropsychiatric events and the development of permanent damage and continue our investigations of measures of disease activity. We will also collaborate in a clinical trial to evaluate pulmonary metastectomy for colo-rectal cancer patients.

Publications

10 25 50
 
Description Book- Using and Understanding Medical Statistics 4th Edition
Geographic Reach Multiple continents/international 
Policy Influence Type Influenced training of practitioners or researchers
Impact Book- Using and Understanding Medical Statistics
 
Description Book- Using and Understanding Medical Statistics 5th Edition
Geographic Reach Multiple continents/international 
Policy Influence Type Influenced training of practitioners or researchers
Impact Book published: Using and Understanding Medical Statistics 5th edition
 
Description Developed and implemented trials of communication training for physicians
Geographic Reach National 
Policy Influence Type Influenced training of practitioners or researchers
 
Description Influenced training of practitioners or researchers - Book chapter 'Missing Confounder Data in Propensity Score Methods for Causal Inference'
Geographic Reach Multiple continents/international 
Policy Influence Type Influenced training of practitioners or researchers
Impact book chapter in Statistical Causal Inferences and Their Applications in Public Health Research by Springer
 
Description Introductory statistics short courses at MRC Biostatistics Unit
Geographic Reach National 
Policy Influence Type Influenced training of practitioners or researchers
Impact Organise the new introductory statistics short courses at the MRC Biostatistics Unit
 
Description Cancer Research UK
Amount £24,919 (GBP)
Organisation Cancer Research UK 
Sector Charity/Non Profit
Country United Kingdom
Start 10/2009 
End 09/2011
 
Description HOD: Handling missing data and time-varying confounding in causal inference for observational event history data
Amount £8,500 (GBP)
Funding ID MR/M025152/1 
Organisation Medical Research Council (MRC) 
Sector Academic/University
Country United Kingdom
Start 10/2015 
End 09/2018
 
Description MASTERPLANS
Amount £164,800 (GBP)
Funding ID MR/M01665X/1 
Organisation Medical Research Council (MRC) 
Sector Academic/University
Country United Kingdom
Start 04/2015 
End 03/2019
 
Description MRC Project Grant
Amount £97,249 (GBP)
Organisation Medical Research Council (MRC) 
Sector Academic/University
Country United Kingdom
Start 01/2007 
End 12/2009
 
Description MRC/ABPI
Amount £90,156 (GBP)
Organisation Medical Research Council (MRC) 
Sector Academic/University
Country United Kingdom
Start 12/2011 
End 12/2017
 
Description Medical Research Council - Career development award in biostatistics
Amount £134,580 (GBP)
Organisation Medical Research Council (MRC) 
Sector Academic/University
Country United Kingdom
Start 10/2010 
End 09/2013
 
Description Research Collaboration
Amount $30,000 (USD)
Organisation Systemic Lupus International Collaborating Clinics 
Sector Academic/University
Country United Kingdom
Start 06/2012 
End 05/2015
 
Description University of Birmingham- Caroline Gordon
Amount £28,000 (GBP)
Organisation UCB Pharma 
Sector Private
Country United Kingdom
Start 01/2015 
End 12/2017
 
Title Measures for rheumatological research 
Description Developed and evaluated measures of disease activity in rheumatology 
Type Of Material Model of mechanisms or symptoms - human 
Year Produced 2007 
Provided To Others? Yes  
Impact These measures are widely used in rheumatological research 
 
Title New methodology for analysis of complex data 
Description New methodology for analysis of complex data 
Type Of Material Model of mechanisms or symptoms - human 
Year Produced 2006 
Provided To Others? Yes  
Impact Provision of methods for the analysis of observational data when the observation process is informative 
 
Description Abbott 
Organisation Abbott
Country Spain 
Sector Private 
PI Contribution Statistical analysis and manuscripts
Collaborator Contribution Provide data
Impact Two published papers. Developed response index for trials.
Start Year 2007
 
Description Amgen 
Organisation Amgen Inc
Country United States 
Sector Private 
PI Contribution Statistical analysis and manuscripts
Collaborator Contribution Provide data
Impact Two papers published. Developed response index trials
Start Year 2007
 
Description Cardiff University 
Organisation Cardiff University
Department School of Medicine
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical methods development
Collaborator Contribution Joint research
Impact PMID: 21487408 ; PMID: 21119659 Currently preparing manuscripts.
Start Year 2007
 
Description Centocor 
Organisation Janssen Biotech, Inc.
Country United States 
Sector Private 
PI Contribution Statistical analysis and manuscripts
Collaborator Contribution Provide data
Impact Two papers published. Developed response index trials
Start Year 2007
 
Description Cincinnati Children's Hospital 
Organisation Cincinnati Children's Hospital Medical Center
Country United States 
Sector Hospitals 
PI Contribution Develop statistical methods for patten mixture models and sensitivity analysis for non-response two-phase sampling
Collaborator Contribution Expertise in missing data research
Impact No output yet.
Start Year 2016
 
Description Dalhousie University 
Organisation Dalhousie University
Department Division of Rheumatology
Country Canada 
Sector Academic/University 
PI Contribution Statistical methods
Collaborator Contribution Medical collaboration and data collection
Impact PMID: 21893582; PMID:21342917; PMID: 20833737; PMID: 19359262; PMID: 20438730; PMID: 20155829
 
Description End of life care 
Organisation University of Cambridge
Department Cambridge Institute of Public Health
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical analysis
Collaborator Contribution Data provision
Impact NA
Start Year 2009
 
Description Fudan University 
Organisation Fudan University
Country China 
Sector Academic/University 
PI Contribution Develop methods for causal inference using electronic health records data
Collaborator Contribution Develop methods for causal inference using electronic health records data
Impact No outcome yet
Start Year 2017
 
Description Health Protection Agency 
Organisation Public Health England
Department Centre of Infectious Disease Surveillance and Control
Country United Kingdom 
Sector Public 
PI Contribution Methodological analysis
Collaborator Contribution Intellectual contribution and data sharing
Impact PMID: 21903689
Start Year 2009
 
Description Keele University 
Organisation Keele University
Country United Kingdom 
Sector Academic/University 
PI Contribution Develop methods for quantile estimation using complex survey data
Collaborator Contribution Expertise in nutritional research and growth chart estimation
Impact No outcome yet
Start Year 2015
 
Description MASTERPLANS consortium in lupus 
Organisation Wellcome Trust
Department Wellcome Trust Centre for Cell-Matrix Research
Country United Kingdom 
Sector Charity/Non Profit 
PI Contribution Co-investigator
Collaborator Contribution Principle Investigator of the funded consortium
Impact No outcome yet
Start Year 2015
 
Description MRC Biostatistics Unit 
Organisation NHS National Services Scotland (NSS)
Department Health Protection Scotland
Country United Kingdom 
Sector Public 
PI Contribution Statistical methodology development and analysis of HCV
Collaborator Contribution Data provision
Impact N/A as the collaboration has just begun
Start Year 2011
 
Description MRC Clinical Trials Unit 
Organisation Medical Research Council (MRC)
Department MRC Clinical Trials Unit
Country United Kingdom 
Sector Public 
PI Contribution Statistical expertise/ Methodological work
Collaborator Contribution Data providing and intellectual contribution
Impact PMID: 20963770 - Detailed study of the impact of categorisation of a continuous explanatory variable when interest centres on interactions involving this variable.
Start Year 2006
 
Description MRC/ABPI I & I Inititative 
Organisation King's College London
Country United Kingdom 
Sector Academic/University 
PI Contribution leading statistical expert
Collaborator Contribution Data, expertise.
Impact Granted awarded: Title: Towards a cure for early rheumatoid arthritis (TACERA) Funder: MRC/ABPI. Award letter dates 3 March 2011 Start date: Still at contract prep stage so no funds in 2011 Funds: I will fund a full time B4 scientist other outcome/output: Not applicable, the collaboration has just started this year
Start Year 2011
 
Description Mammalian embryo vitality 
Organisation University of Cambridge
Department Gurdon Institute
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical analysis
Collaborator Contribution Data provision
Impact PMID: 21829179
Start Year 2011
 
Description Missing confounder data and time varying confounding 
Organisation University College London
Department Institute of Child Health
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical methods collaboration
Collaborator Contribution Statistical methods collaboration
Impact Funded grant application
Start Year 2015
 
Description NIHR Programme Grants for Applied Research 
Organisation King's College Hospital NHS Foundation Trust (NCH)
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical methodology and analysis
Collaborator Contribution responsible for patients and clinical expertise
Impact Not yet
Start Year 2011
 
Description PulMiCC 
Organisation University College London
Department Clinical Operations Research Unit
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical methods and analysis
Collaborator Contribution Study design and implementation
Impact PMID: 21561890 Grant from CRUK in process
Start Year 2009
 
Description Queen's University, Canada 
Organisation Queen's University Belfast
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical expertise/ Methodological work
Collaborator Contribution Intellectual contribution
Impact Investigation concerning methods for the analysis of information on incubation times for new infectious diseases. Statistical design and analysis for non-normal nested data.
Start Year 2006
 
Description Rheumatological trials 
Organisation King's College London
Department Department of Academic Rheumatology
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical design and analysis support
Collaborator Contribution Design, implementation and data processing for trials
Impact Scientific papers
Start Year 2011
 
Description Statistical dissemination 
Organisation University of Edinburgh
Department Anaesthesia, Critical Care & Pain Medicine
Country United Kingdom 
Sector Academic/University 
PI Contribution Writing commissioned papers
Collaborator Contribution Writing
Impact PMID: 22042541; PMID: 22113542; PMID: 21908834; PMID: 21884044; PMID: 21801268; PMID: 21790718; PMID: 21784789; PMID: 21764757 PMID: 21908834; PMID: 21884044; PMID: 21801268; PMID: 21790718; PMID: 21784789; PMID: 21764757 PMID: 22113542; PMID: 22042541 PMID: 22022804; PMID: 21972915; PMID: 21884194; PMID: 21844004
Start Year 2011
 
Description The University of Texas at Austin 
Organisation University of Texas at Austin
Department Department of Statistics & Data Sciences
Country United States 
Sector Academic/University 
PI Contribution Develop methods for sensitivity analysis for analysing longitudinal data missing not at random
Collaborator Contribution Expertise in methods for handling missing data
Impact One publication in Statistics in Medicine in 2015
Start Year 2015
 
Description UCL 
Organisation University College London
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical expertise
Collaborator Contribution Intellectual contribution
Impact PMIDs: 20833737; PMID: 20181671; PMID: 19779027; PMID: 19395542; PMID: 19359262; PMID: 18438902; PMID: 18311802; PMID: 18050213; PMID: 17768173; PMID: 17195230; PMID: 17009266; PMID: 16249244
 
Description University College London 
Organisation University College London
Department Institute of Neurology
Country United Kingdom 
Sector Academic/University 
PI Contribution Develop multistate models for correlated processes
Collaborator Contribution Develop multistate models for correlated processes
Impact One manuscript submitted
Start Year 2016
 
Description University of Cambridge, Department of Pathology 
Organisation University of Cambridge
Department Department of Public Health and Primary Care
Country United Kingdom 
Sector Academic/University 
PI Contribution Analyse the CPRD data for disease progression of iron deficiency following oral iron treatment in primary care of UK
Collaborator Contribution Expertise in nutritional research
Impact No outcome yet
Start Year 2016
 
Description University of Cambridge, Department of Primary Care and Public Health 
Organisation University of Cambridge
Department Department of Pathology
Country United Kingdom 
Sector Academic/University 
PI Contribution Develop joint models for non-ignorable missing data
Collaborator Contribution Expertise in joint models of longitudinal and time-to-event data
Impact Ongoing research
Start Year 2017
 
Description University of North Carolina 
Organisation Boston University
Department Department of Biostatistics
Country United States 
Sector Academic/University 
PI Contribution Input into statistical collaborative projects
Collaborator Contribution Input into statistical collaborative projects
Impact Joint publications
Start Year 2012
 
Description University of Sussex 
Organisation University of Sussex
Department Brighton and Sussex Medical School
Country United Kingdom 
Sector Academic/University 
PI Contribution Statistical methods and analysis
Collaborator Contribution Data provision plus collaborative activities
Impact PMID: 21487408 ; 21119659 ; 20648018 ; 21561890
 
Description University of Toronto 
Organisation Toronto Western Hospital
Department University of Toronto Psoriatic Arthritis Clinic
Country Canada 
Sector Hospitals 
PI Contribution Statistical expertise/ Methodological work
Collaborator Contribution Data providing/ Intellectual contribution
Impact PMID: 21284011; PMID: 21245073; PMID: 20833737; PMID: 20581216; PMID: 20952468; PMID: 20595286; PMID: 20472929; PMID: 20595285 DOI: 10.1111/j.1467-9876.2011.00767.x Overview article on Rheumatology for the Encyclopedia of Biostatistics. Indianapolis, USA: John Wiley & Sons, Inc; 2005 Ongoing collaboration.
 
Description University of Waterloo 
Organisation University of Waterloo
Department Department of Statistics and Actuarial Science
Country Canada 
Sector Academic/University 
PI Contribution Statistical expertise / Methodological work
Collaborator Contribution Statistical expertise/ Intellectual contribution
Impact PMID: 20523014
 
Description 23rd Austin Bradford Hill Memorial Lecture, and Clinical Trials: Past, Present and Glorious Future meeting 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Type Of Presentation keynote/invited speaker
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Interest in early history of MRC BSU expressed
Feedback from participants was very good
Talks sparked interesting questions and discussion afterwards

Video posted online has been viewed more than 115 times. Link: http://vimeo.com/97709905
Year(s) Of Engagement Activity 2014
URL http://www.mrc-bsu.cam.ac.uk/bradford-hill-memorial-lecture/
 
Description A talk in the 14th Armitage workshop in MRC Biostatistics Unit 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Dr Li Su gave a talk on 'Two-part model for longitudinal data' in the 14th Armitage workshop at MRC Biostatistics Unit on 17th November 2016.
Year(s) Of Engagement Activity 2016
 
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 in Brown University website 
Form Of Engagement Activity A magazine, newsletter or online publication
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Undergraduate students
Results and Impact Li Su, Senior Investigator Statistician, contributed to alumni spotlight article in Brown University website https://www.brown.edu/academics/public-health/biostatistics/news/2016-05/alumni-spotlight
Year(s) Of Engagement Activity 2016
 
Description CRiSM seminar at University of Warwick, Department of Statistics 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Dr Li Su gave a talk on 'Bayesian modeling of the covariance structure for irregular longitudinal data using the partial autocorrelation function' for the CRiSM seminar series at University of Warwick, Department of Statistics in January 2016.
Year(s) Of Engagement Activity 2016
 
Description Cambridge Science Festival 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? Yes
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact Each year BSU participate in Cambridge Science Festival - members of the general public explore and discuss issues of scientific interest and concern, through a series of different events. The event also aims to raise aspirations by encouraging young people to consider a career in science, technology, engineering or mathematics.

BSU take part over two full days - 'Science Saturday' and the 'Cambridge Biomedical Campus' day. The unit presents a stand with 4 - 5 interactive activities that each communicate a basic statistical method or idea, representing one of the four research themes in the unit. Each year a new activity is developed and delivered requiring scientific input from staff across the unit. Over the two days, BSU engage with approximately 500 adults and children who visit the festival.

Raised awareness of the Unit's work in the local schools community
Very good feedback from festival attendants
Year(s) Of Engagement Activity 2007,2008,2009,2010,2011
URL http://www.cam.ac.uk/science-festival
 
Description Cambridge Statistics Group 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
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.

None
Year(s) Of Engagement Activity 2013,2014,2015,2016
 
Description IVF 
Form Of Engagement Activity A press release, press conference or response to a media enquiry/interview
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 National and international media coverage of published paper on mammalian embryo vitality and its relationship to IVF treatment (August 2011). See links:
http://www.cam.ac.uk/research/news/selecting-the-fittest-embryos-for-survival/
http://www.wellcome.ac.uk/News/2011/News/WTVM052353.htm
http://www.nature.com/ncomms/press_releases/ncomms0811.html
http://www.natureasia.com/en/highlights/details.php?id=1374
http://www.guardian.co.uk/science/2011/aug/09/pulsations-embryos-success-ivf


National and international media coverage of published paper.
Awareness of relevance of research work developed in Cambridge
Year(s) Of Engagement Activity 2011
URL http://www.mrc-bsu.cam.ac.uk/NewsandEvents/previous_news_Aug2011.html#News_Aug2011-5
 
Description MRC BSU Centenary - Free Public Lectures 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Health professionals
Results and Impact Feedback from participants was very good
Talks sparked interesting questions and discussion afterwards
Networking enabled possible future research collaborations / knowledge transfer opportunities
This event facilitated communication, interaction and collaboration between participants

Increase in request for further information
Audience asked for more opportunities for communication and interaction with the public health researchers
Year(s) Of Engagement Activity 2013
URL http://www.mrc-bsu.cam.ac.uk/medical-research-council-centenary-celebrations-kick-off-at-mrc-biostat...
 
Description MRC BSU Centenary Conference 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Interest in early history of MRC BSU expressed
Feedback from participants was very good
Talks sparked interesting questions and discussion afterwards
Networking enabled possible future research collaborations / knowledge transfer opportunities
This event facilitated communication, interaction and collaboration between member statisticians

Further invitations to speak on this topic
Year(s) Of Engagement Activity 2014
URL http://www.mrc-bsu.cam.ac.uk/news-and-events/mrc-biostatistics-conference/
 
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
Geographic Reach Local
Primary Audience Public/other audiences
Results and Impact 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.
Interest in early history of MRC BSU expressed
Feedback from participants was very good

Raised the profile of the Unit in the local region
Year(s) Of Engagement Activity 2013
URL http://www.mrc-bsu.cam.ac.uk/mrc-bsu-successfully-joined-medical-research-council-open-week/
 
Description Patient Symposium 
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 Gave a patient symposium entitled "Is there a relationship between inflammation and joint damage"

Maintenance of patient interest in clinical cohort study
Year(s) Of Engagement Activity 2009,2010
 
Description Psoriatic Arthritis Symposium 2013 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact International symposium on current topics related to psoriatic arthritis (Toronto, Canada)
The Psoriatic Arthritis Update Scientific Symposium celebrated 35 years of the Toronto Psoriatic Arthritis Research Program
PL was invited to give a talk entitled "Statistical Analysis of Longitudinal Data from PsA Cohorts"
Feedback from participants was very good

Networking enabled possible future research collaborations / knowledge transfer opportunities
Year(s) Of Engagement Activity 2013
URL http://www.cpd.utoronto.ca/psoriaticarthritis/
 
Description Radio 4 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Media (as a channel to the public)
Results and Impact Radio interview for "Tribes of Science" programme on BBC Radio 4 (August 2011).
What is a statistician really like? Peter Curran dropped in the Royal Statistical Society's annual awards party to investigate 'The Tribes of Science: the Statisticians'.
'The Tribes of Science: the Statisticians' conducted by Peter Curran, is also available online (duration: 15 minutes) . Please see http://www.bbc.co.uk/programmes/b012xns9

Public appreciation of statistical work.
Year(s) Of Engagement Activity 2011
URL http://www.bbc.co.uk/programmes/b013851z
 
Description The Times Internship 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
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 on the Unit's work in the Media
Year(s) Of Engagement Activity 2009,2010
URL http://www.mrc-bsu.cam.ac.uk/NewsandEvents/July2010_6_Times.html