Details of Grant 

EPSRC Reference:	GR/R69884/01
Title:	Statistical Inference and Diagnostics in Modelling Covariance Structures in Longitudinal Randomised Controlled Trials
Principal Investigator:	Pan, Professor J
Other Investigators:	MacKenzie, Professor G
Researcher Co-Investigators:
Project Partners:
Department:	Mathematics
Organisation:	University of Manchester, The
Scheme:	Fast Stream
Starts:	01 October 2002	Ends:	30 September 2005	Value (£):	62,639
EPSRC Research Topic Classifications:	Statistics & Appl. Probability
EPSRC Industrial Sector Classifications:	Environment Healthcare No relevance to Underpinning Sectors
Related Grants:
Panel History:
Summary on Grant Application Form
In longitudinal studies, repeated measurements are made on subjects over time and responses within a subject may be correlated although responses between subjects are likely to be independent. If the within-subject correlation is not taken into account in statistical modelling, the resultingstatistical inferences may be biased. The literature work assumes a specific covariance structure (or selects one from a limited class of Icandidates) when modelling the mean structure of repeated measures. This menu-selection method, however, may choose a sub-optimal or wrong covariance structure.This project is to simultaneously model the mean and covariance structures in LDA using data-driven methods which avoid mis-specification of covariance structures. We will start applying techniques of polynomials of time, adaptively choosing the degrees of ploynomials and incorporating baseline covariates into the modelling. We will then use semi- or non-parametric procedures to parsimoniously model the mean and covariance structures. Statistical diagnostics will be studied in terms of case-deletion and local influence approaches within the framework of joint mean-covariance models. The methods will be applied to two typies of structured models: linear mixed models and growth curve models. The performance of the new methods will be assessed using simulation studies and existing real data sets. The work will also be applied to practical randomised controlled trials being conducted by The North Staffordshire Hospital.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk Summary Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:
Further Information:
Organisation Website:	http://www.man.ac.uk