Statistics Seminars: Informative or non-informative calls for gene expression: a latent variable approach
14 February 2011 15:15 in CM221
The strength and weakness of microarray technology may be attributed to the enormous amount of information it generates. To fully enhance the benefit of microarray technology for understanding gene functions, tumours classification, drug target identification and prediction of response to therapy, there is a need to minimize the amount of irrelevant genes often present in microarray data. A major interest is to use probe level data of Affymetrix microarray platform to call genes informative or non-informative based on the trade-off between the array-to-array variability and the measurement error.
In this presentation, I will discuss statistical approach to informative or non-informative calls based on fixed effects model, factor analysis model and random intercept linear mixed effects model. I will also discuss the limitations of the existing methods and introduce more flexible model based on latent class linear mixed effect model.
Host: Michael Goldstein
Contact email@example.com for more information