Inference using calibration samples

Lead Research Organisation: King's College London
Department Name: Biostatistics

Abstract

This project refines methods that enable overall conclusions to be reached from the analysis of multiple studies where some of the key measurements have been made in different ways. The methods are developed and compared in a study of general population cohorts, a clinical cohort, and two randomised trials.

Technical Summary

It is commonplace for researchers to want to undertake analysis of several studies combined together but are prevented from doing so by the differences in measurement protocols used. We examine various methods (structural equation modelling, multiple imputation and meta-regression) for overcoming this problem by the use of internal or external cross-measure calibration samples. We will highlight differences among the methods and designs in the assumptions made, and in the power and robustness of the conclusions reached. The methods are developed and compared in a study of general population cohorts, a clinical cohort, and two randomised trials.

Publications

10 25 50

publication icon
Botting N (2016) Emotional health, support, and self-efficacy in young adults with a history of language impairment. in The British journal of developmental psychology

publication icon
Conti-Ramsden G (2018) Education and employment outcomes of young adults with a history of developmental language disorder. in International journal of language & communication disorders

publication icon
Durkin K (2017) Social Confidence in Early Adulthood Among Young People With and Without a History of Language Impairment. in Journal of speech, language, and hearing research : JSLHR

publication icon
Durkin K (2016) Learning to drive in young adults with language impairment. in Transportation research. Part F, Traffic psychology and behaviour

publication icon
Farnell DJ (2011) Measurement error in statistical models of shape. in Computer methods and programs in biomedicine

 
Description BASIS Training Day
Geographic Reach National 
Policy Influence Type Influenced training of practitioners or researchers
 
Description NÍHR Biomedical Research Centre
Amount £60,000,000 (GBP)
Organisation National Institute for Health Research 
Department NIHR Biomedical Research Centre
Sector Public
Country United Kingdom
Start 04/2017 
End 03/2022
 
Title Stata2Mplus Simulator 
Description A utility for undertaking simulation in the statistical program Stata and analysis within the structural equation modelling program Mplus. 
Type Of Material Data analysis technique 
Year Produced 2010 
Provided To Others? Yes  
Impact None have yet reached output stage 
 
Description ALSPAC-NATSEL pooled analysis of chlamydia infection 
Organisation University College London
Department Institute of Epidemiology and Health Care
Country United Kingdom 
Sector Academic/University 
PI Contribution Provided methodological principles and advice to local NIHR funded postdoc who is undertaking the analysis
Collaborator Contribution Expert insight into data
Impact No outputs as yet. Involves statistics, epidemiology, behavioral science and infectious diseases
Start Year 2016
 
Description British Autism Sibling Infant Study 
Organisation Birkbeck, University of London
Department Centre for Brain and Cognitive Development
Country United Kingdom 
Sector Academic/University 
PI Contribution Conceptual and analysis
Collaborator Contribution Rich developmental data
Impact Journal article publication
Start Year 2012
 
Description Language & Behavioural Development 
Organisation University of Manchester
Department School of Medicine Manchester
Country United Kingdom 
Sector Academic/University 
PI Contribution Providing methods to enable behavioural trajectories in a cohort of language impaired children to be identified in spite of change in measurement instruments
Collaborator Contribution Providing example of the need for the methodology
Impact J Commun Disord. 2010 Oct 1. [Epub ahead of print] A paper published in the journal of communication disorders. St Clair MC, Pickles A, Durkin K, Conti-Ramsden (2010 Epub) A longitudinal study of behavioral, emotional and social difficulties in individuals with a history of specific language impairment (SLI). Statistics and Psychology
 
Description Wirral Child Health and Development Study 
Organisation University of Manchester
Department School of Medicine Manchester
Country United Kingdom 
Sector Academic/University 
PI Contribution Used calibration methods to enable longitudinal modelling of developmental data
Collaborator Contribution Provided the empirical context
Impact In prepararion
Start Year 2013
 
Description Baby Sibs Research Consortium USA 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Other audiences
Results and Impact Provide external expert opinion to consortium of >20 research groups
Year(s) Of Engagement Activity 2015
 
Description Society for Research in Child Development Conference 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact To show how child development could be tracked in spite of changes in measurement scales and the additional vale of cross-measure calibration samples. Of value to those concerned with child development research and policy making.
Year(s) Of Engagement Activity 2015
 
Description Teaching at White Rose ESRC Social Science Doctoral Training Centre (Sheffield) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? Yes
Geographic Reach National
Primary Audience Public/other audiences
Results and Impact Raised awareness of mechanisms research

Email enquiry
Year(s) Of Engagement Activity 2014
 
Description Training 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 2-day training course on measurement given at NIMHANS, Bangalore, India for 20 participants that included examples of model based data harmonisation.
Year(s) Of Engagement Activity 2018