Grant: Discovery Grants Program - Individual
McGill University
$38,000.00
Applied bayesian biostatistics
FY 2009-10
Summary
Applied Bayesian Biostatistics
Bayesian analysis is a statistical paradigm with many advantages for analysing the results of complex medical experiments. In the Bayesian paradigm, past information is combined with that provided by the current study, so that overall conclusions that incorporate all information can be obtained. Importantly, recent advances in computer technology and Bayesian numerical algorithms have freed researchers from the restrictions of standard models, so that the complexity of the model can closely approximate the reality. I will address two particular topics in the Bayesian design and analysis of medical studies:
First, I will look at the analysis of data from studies that evaluate new diagnostic tests or use diagnostic tests for estimating the prevalence of a condition in a particular population. While seemingly simple, these are in fact difficult estimation problems due to the lack of good tests for many diseases or conditions, which leads to many healthy subjects being diagnosed as diseased, and vice versa. I will develop new methods for such situations, and distribute software so that others can use the methods in their own studies.
Second, the decision about the number of subjects to include is an important component of the planning of almost all studies. I will look at sample size determination for a wide variety of study designs, including planning studies that use diagnostic tests. In particular, I will look at new criteria for sample size which may lead to quite different sizes compared to currently popular criteria. The main purpose of this work is to enable real medical studies to be both better designed and better analysed.
Program
Discovery Grants Program - Individual
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
46416-2009
Name nom
Joseph, Lawrence
Department département
Epidemiology and Biostatistics
Organization id
61
Institution établissement
McGill University
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2009
Competition year année de concours
2009
Award amount
38000
Program id
RGPIN
Program nane en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
14
Committee name en
Statistical Sciences
Committee name fr
Statistique
Area of application code
1211
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Medical and health sciences
Area of application fr
Sciences médicales et de la santé
Research subject code
3005
Research subject group en
Statistics and probability
Research subject group fr
Statistique et probabilité
Research subject en
Biostatistics
Research subject fr
Biostatistiques
Partie
1
Nb partie
5
Application title
Applied bayesian biostatistics
Keyword
NA
Application summary
Applied Bayesian Biostatistics
Bayesian analysis is a statistical paradigm with many advantages for analysing the results of complex medical experiments. In the Bayesian paradigm, past information is combined with that provided by the current study, so that overall conclusions that incorporate all information can be obtained. Importantly, recent advances in computer technology and Bayesian numerical algorithms have freed researchers from the restrictions of standard models, so that the complexity of the model can closely approximate the reality. I will address two particular topics in the Bayesian design and analysis of medical studies:
First, I will look at the analysis of data from studies that evaluate new diagnostic tests or use diagnostic tests for estimating the prevalence of a condition in a particular population. While seemingly simple, these are in fact difficult estimation problems due to the lack of good tests for many diseases or conditions, which leads to many healthy subjects being diagnosed as diseased, and vice versa. I will develop new methods for such situations, and distribute software so that others can use the methods in their own studies.
Second, the decision about the number of subjects to include is an important component of the planning of almost all studies. I will look at sample size determination for a wide variety of study designs, including planning studies that use diagnostic tests. In particular, I will look at new criteria for sample size which may lead to quite different sizes compared to currently popular criteria. The main purpose of this work is to enable real medical studies to be both better designed and better analysed.