EMBARRASSINGLY EASY EMBARRASSINGLY PARALLEL PROCESSING IN R

EMBARRASSINGLY EASY EMBARRASSINGLY PARALLEL PROCESSING IN R The only people who have anything to fear from free software are those whose products are worth even less. David Emery 1 OVERVIEW Recently, there has been great interest in applying parallel computation routines to standard econometric procedures. This interest has arisen for at least three reasons. As the size of datasets increases, computational demands to implement even standard econometric procedures increase; many applied researchers are moving towards more computationally demanding econometric methods; and multiple processors have become standard on desktop and laptop computers. Many computationally demanding econometric procedures are ‘embarrassingly parallel’ problems, meaning that they require a large number of independent calculations. Common econometric examples of ‘embarrassingly parallel’ problems include the bootstrap, Monte Carlo simulations or nonlinear optimization in which one wants to optimize multiple times based on different starting values (i.e. ‘multistart’) to avoid local optima. To address these needs, a variety of parallel libraries in R have recently become available. Examples include the multicore (Urbanek, ), snow (Tierney et al ., ), snowfall (Knaus, ) and parallel packages ( parallel is available in base R and calls functions from both multicore and snow ). Each is freely available, and all are relatively simple to combine http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Applied Econometrics Wiley

EMBARRASSINGLY EASY EMBARRASSINGLY PARALLEL PROCESSING IN R

Loading next page...
 
/lp/wiley/embarrassingly-easy-embarrassingly-parallel-processing-in-r-0Clw3yMWSd
Publisher
Wiley
Copyright
Copyright © 2013 John Wiley & Sons, Ltd.
ISSN
0883-7252
eISSN
1099-1255
D.O.I.
10.1002/jae.2362
Publisher site
See Article on Publisher Site

Abstract

The only people who have anything to fear from free software are those whose products are worth even less. David Emery 1 OVERVIEW Recently, there has been great interest in applying parallel computation routines to standard econometric procedures. This interest has arisen for at least three reasons. As the size of datasets increases, computational demands to implement even standard econometric procedures increase; many applied researchers are moving towards more computationally demanding econometric methods; and multiple processors have become standard on desktop and laptop computers. Many computationally demanding econometric procedures are ‘embarrassingly parallel’ problems, meaning that they require a large number of independent calculations. Common econometric examples of ‘embarrassingly parallel’ problems include the bootstrap, Monte Carlo simulations or nonlinear optimization in which one wants to optimize multiple times based on different starting values (i.e. ‘multistart’) to avoid local optima. To address these needs, a variety of parallel libraries in R have recently become available. Examples include the multicore (Urbanek, ), snow (Tierney et al ., ), snowfall (Knaus, ) and parallel packages ( parallel is available in base R and calls functions from both multicore and snow ). Each is freely available, and all are relatively simple to combine

Journal

Journal of Applied EconometricsWiley

Published: Nov 1, 2013

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off