BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260517T132737EDT-2887Vg2tU3@132.216.98.100
DTSTAMP:20260517T172737Z
DESCRIPTION:Bootstrap in practice\n\nThis talk focuses on three practical a
 spects of resampling: communication\, accuracy\, and software. I'll introd
 uce the bootstrap and permutation tests\, and discussed how they may be us
 ed to help clients understand statistical results. I'll talk about accurac
 y -- there are dramatic differences in how accurate different bootstrap me
 thods are. Surprisingly\, the most common bootstrap methods are less accur
 ate than classical methods for small samples\, and more accurate for large
 r samples. There are simple variations that dramatically improve the accur
 acy. Finally\, I'll compare two R packages\, the the easy-to-use 'resample
 ' package\, and the more-powerful 'boot' package.\n
DTSTART:20161102T190000Z
DTEND:20161102T200000Z
LOCATION:Room 306\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue 
 Sherbrooke Ouest
SUMMARY:Tim Hesterberg\, Google
URL:https://www.mcgill.ca/mathstat/channels/event/tim-hesterberg-google-263
 857
END:VEVENT
END:VCALENDAR