BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//jEvents 2.0 for Joomla//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:75e942ae2889b726ace54395942448fe
CATEGORIES:Seminars
CREATED:20170418T191238
SUMMARY:Ruey Tsay - University of Chicago Booth School of Business
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:Analysis of Big Dependent Data in Economics and Finance\nAbstract:\nBig dat
 a are common in many scientific fields and have attracted much research int
 erest in machine learning, computer science, optimization and statistics. E
 conometrics and finance are no exception.\nThe goal of analyzing big data i
 s to extract its useful information effectively and timely. In this talk, w
 e introduce analysis of big dependent data by focusing on economics and fin
 ance.\nWe review methods available for analyzing big data and discuss their
  advantages and limitations. We compare the concepts of sparsity and parsim
 ony in modeling, and emphasize the impact of serial dependence on methods d
 eveloped for independent data.\nExamples are used to demonstrate the analys
 is. The methods discussed include (a) various penalized likelihood methods 
 for statistical modeling such as LASSO regression and its extensions, (b) t
 ransformation to functional data for simplification, (c) tree-based methods
  for classification and prediction such as bagging, boosting, and random fo
 rests, (d) some methods for analyzing big dependent data.\nThe demonstratio
 n is carried out using the R software. Cross-validation (both leave-one-out
  and K folds) is used to select the penalty (or smoothing) parameter. If ti
 me permits, we further illustrate some applications.\n
DTSTAMP:20260406T151101Z
DTSTART:20160929T173000Z
DTEND:20160929T190000Z
SEQUENCE:0
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR