Skip to content Skip to navigation

statistics colloquium: Edward J. Bedrick

Event Type: 
Colloquium
Speaker: 
Edward Bedrick
Event Date: 
Friday, November 6, 2015 -
3:30pm to 5:00pm
Location: 
SMLC 120
Audience: 
General PublicFaculty/StaffStudentsAlumni/Friends
Sponsor/s: 
Math and Stat Department

Event Description: 

Title:
Quantifying Small Effects in Regression Models
Abstract:
Scientists generally recognize the distinction between statistical
significance and practical significance. However, it is not always obvious
how to calibrate whether statistical effects are important, especially
small effects in complex statistical models. We develop a novel approach
for quantifying small regression effects in linear regression models. Our
method is based on variation in the mean function, in contrast to methods
that focus on regression coefficients.  Our idea applies in diverse
settings such as testing for a negligible trend to quantifying subtle
differences in regression structure across subgroups. Straightforward
Bayesian methods are proposed for inference. Several published analyses are
used to illustrate the ideas and methodology. The presentation will not be
overly technical and should be accessible to graduate students who have a
basic understanding of linear models.
 

 

Event Contact

Contact Name: Yan Lu

Contact Phone: 505-277-2544

Contact Email: luyan@math.unm.edu