The Statistical Society of Australia, Inc.
View latest news

Non-members

Register here to receive the SSAI online newsletter and event alerts

Register

 
Member Login
member #
password
Branches
 

QLD Branch - Upcoming Meetings

Monday 20 February 2012

Time: 4:00pm– 5:00pm.

Location: TBA.

Speaker: Liliana Orellana

Title: TBA

Abstract: TBA

Biography: TBA

Tuesday 20 March 2012

Queensland Branch Annual General Meeting

Time: TBA.

Location: QUT, Gardens Point Campus, Room: TBA.

AGM immediately followed by ...

Time: TBA.

Speaker: Associate Professor Benoit Liquet, University of Bordeaux

Title: On Akaike and likelihood cross-validation criteria for model selection

Abstract: The talk discusses Akaike and likelihood cross-validation criteria for model/estimator choice. After a presentation of the main concept on model selection, we will focus on the choice of estimators in non-standard cases. First, we study two examples arising when we wish to assess the quality of estimators on a particular set of information, while the estimators may use a larger set of information. The first example occurs when we construct a model for an event which happens if a continuous variable is above a certain threshold. We can compare estimators based on the observation of only the event or on the whole continuous variable. The other example is that of predicting survival based on survival information only, or using in addition information on patient's disease. We develop modified AIC and LCV criteria to compare estimators in this non-standard situation. Second, we study the choice of estimators in prognostic studies. Estimators for a clinical event may use repeated measurements of markers in addition to fixed covariates. These measurements can be linked to the clinical event by joint modelling involving latent structures. When the objective is to choose between different estimators based on joint models for prediction, the conventional Akaike information criterion (AIC) is not well adapted and decision should be based on predictive accuracy. We define an adapted risk function called expected prognostic cross entropy (EPCE) and further modify it for right-censored observations. The risk functions can be estimated by leave-one-out cross validation, for which we give approximate formulas and asymptotic distributions.

Biography: Benoit Liquet is an Associate Professor at INSERM (the French national institute of health) in Bordeaux. His PhD in 2002 was on semi-parametric model selection. He has published papers on: model Selection; dimension reduction and semi-parametric models; multi-state and survival models; and multiple testing.