BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250713T054817EDT-3413SctLwF@132.216.98.100
DTSTAMP:20250713T094817Z
DESCRIPTION:Performance Assessment of High-dimensional Variable Estimation.
 \n\nSince model selection is ubiquitous in data analysis\, reproducibility
  of statistical analysis demands a reality check of the employed model sel
 ection method no matter what label it may have in terms of good properties
 . Instability measures have been proposed for evaluating model selection u
 ncertainty. However\, low instability does not necessarily indicate that t
 he selected model is trustworthy\, since low instability can also arise wh
 en a certain method tends to select an overly parsimonious model. In this 
 work\, we propose an estimation method based on F and G measures to evalua
 te the accuracy of variable selection methods in terms of model identifica
 tion (not prediction). We show that our approach provides reliable estimat
 es of the true F and G measures of the selected models. This gives the dat
 a analyst a valuable tool to compare different model selection methods bas
 ed on the data at hand. Extensive simulations are conducted to show its ve
 ry good finite sample performance. We further demonstrate the application 
 of our methods using several microarray gene expression data sets.\n
DTSTART:20161101T193000Z
DTEND:20161101T203000Z
LOCATION:Room 24\, Purvis Hall\, CA\, QC\, Montreal\, H3A 1A2\, 1020 avenue
  des Pins Ouest
SUMMARY:Yi Yang\, ºÃÉ«TV
URL:/mathstat/channels/event/yi-yang-mcgill-university
 -263854
END:VEVENT
END:VCALENDAR