What econometrics can learn from machine learning and vice versa

I have written a paper for economists that describes some of the techniques from machine learning that can be helpful for econometric analysis. This talk is an attempt to look at the reverse issue: what techniques from econometrics may be helpful for machine learning. One set of issues involves non-IID data such as time series and panel data. But the most important set of issues involves estimating causal effects, where seemingly straightforward approaches lead to serious estimation problems. Luckily there are a number of econometric techniques that can be applied to deal with these problems, which I will outline in the talk.
Speaker: Hal Varian, Google
Wednesday, 01/29/14
Contact:
Website: Click to VisitCost:
FreeSave this Event:
iCalendarGoogle Calendar
Yahoo! Calendar
Windows Live Calendar
Gates Computer Science Building
Stanford University
NEC Auditorium (B3)
Stanford, CA 94305
NEC Auditorium (B3)
Stanford, CA 94305
Website: Click to Visit
