Simon G. Thompson
Research Subjects
Simon G. Thompson has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
Jochen Kienast
Medizinische Klinik und Poliklinik der Westfälischen Wilhelms-Universität, Abteilung Innere Medizin A, Münster, Germany
1 shared publicationRainer Buchwalsky
Abteilung für Kardiologie, Schüchtermann-Klinik, Bad Rothenfelde, Germany
1 shared publication- Rebecca Hardy
School of Sport, Exercise and Health Sciences, Loughborough University, United Kingdom (R.H.).
1 shared publication Stephen D M Pyke
Medical Statistics Unit, The London School of Hygiene and Tropical Medicine, London, United Kingdom
1 shared publicationStephen D. M. Pyke
Glaxo Wellcome, Stockley Park West, Uxbridge, Middx UB11 IBT, U.K.
1 shared publicationon behalf of the ECAT Angina Pectoris Study Group
1 shared publication
Latest Publications
- 30 September 1997
- Published by Wiley in Statistics in Medicine
- Vol. 16 (18) , 2063-2079
The design and analysis of paired cluster randomized trials: an application of meta-analysis techniques
The statistical issues in clinical trials where clusters, communities or groups rather than individuals are randomized are often not fully appreciated. In this paper we discuss the design and analysis of trials in which pairs of clusters are randomized in the context of one recent trial, the British Family Heart Study. Both sample size calculations and the analysis strategy need to take account of the between‐cluster component of variance. The analysis can be considered as a random effects meta‐analysis across cluster pairs, and can usefully be presented as such. Techniques developed in the context of meta‐analysis can then be used in the analysis, for example using a profile likelihood method to derive a confidence interval for the overall treatment effect which takes into account the variability in the estimate of the between‐cluster variance. The methods presented here are contrasted with previously published methods for cluster randomized trials. © 1997 by John Wiley & Sons, Ltd.
- 30 September 1997
- Published by Wiley in Statistics in Medicine
- Vol. 16 (18) , 2063-2079
The design and analysis of paired cluster randomized trials: an application of meta-analysis techniques
The statistical issues in clinical trials where clusters, communities or groups rather than individuals are randomized are often not fully appreciated. In this paper we discuss the design and analysis of trials in which pairs of clusters are randomized in the context of one recent trial, the British Family Heart Study. Both sample size calculations and the analysis strategy need to take account of the between‐cluster component of variance. The analysis can be considered as a random effects meta‐analysis across cluster pairs, and can usefully be presented as such. Techniques developed in the context of meta‐analysis can then be used in the analysis, for example using a profile likelihood method to derive a confidence interval for the overall treatment effect which takes into account the variability in the estimate of the between‐cluster variance. The methods presented here are contrasted with previously published methods for cluster randomized trials. © 1997 by John Wiley & Sons, Ltd.
- 1 November 1993
- Published by Georg Thieme Verlag KG in Thrombosis and Haemostasis
- Vol. 70 (05) , 743-746
Variability over Time of Haemostatic and Other Cardiovascular Risk Factors in Patients Suffering from Angina Pectoris
The variability of haemostatic factor measurements in patients presenting with angina pectoris is investigated. In all, 219 middle aged patients (almost all men) provided repeat measurements 2.5 years apart on a battery of haemostatic and haematological tests and other cardiovascular risk factors. Correlations between repeat measurements were lower than might be expected in a healthy population, reflecting a relatively large degree of variability within individuals over time. The highest correlations observed for haemostatic factors were for von Willebrand factor related antigen (r = 0.48) and fibrinogen (r = 0.45). The correlations were generally lower amongst patients who had undergone coronary surgery or angioplasty between the two measurements. We conclude that the underlying relationship of fibrinogen to coronary risk must be much greater than is generally appreciated, since even single measurements are found to be important predictors of risk, despite only moderate stability over time. The very low correlations for β-thromboglobulin (r = 0.10) and platelet factor 4 (r = 0.03) which were observed in this study casts doubt on their potential usefulness as predictors of long-term cardiovascular risk.
- 1 November 1993
- Published by Georg Thieme Verlag KG in Thrombosis and Haemostasis
- Vol. 70 (05) , 743-746
Variability over Time of Haemostatic and Other Cardiovascular Risk Factors in Patients Suffering from Angina Pectoris
The variability of haemostatic factor measurements in patients presenting with angina pectoris is investigated. In all, 219 middle aged patients (almost all men) provided repeat measurements 2.5 years apart on a battery of haemostatic and haematological tests and other cardiovascular risk factors. Correlations between repeat measurements were lower than might be expected in a healthy population, reflecting a relatively large degree of variability within individuals over time. The highest correlations observed for haemostatic factors were for von Willebrand factor related antigen (r = 0.48) and fibrinogen (r = 0.45). The correlations were generally lower amongst patients who had undergone coronary surgery or angioplasty between the two measurements. We conclude that the underlying relationship of fibrinogen to coronary risk must be much greater than is generally appreciated, since even single measurements are found to be important predictors of risk, despite only moderate stability over time. The very low correlations for β-thromboglobulin (r = 0.10) and platelet factor 4 (r = 0.03) which were observed in this study casts doubt on their potential usefulness as predictors of long-term cardiovascular risk.