2 results
14 - Big Data in Economics: Evolution or Revolution?
-
- By Christine De Mol, Université libre de Bruxelles, Brussels, Belgium, Eric Gautier, Toulouse School of Economics, Toulouse, Domenico Giannone, Federal Reserve Bank of New York, New York, Sendhil Mullainathan, Harvard University, Cambridge, MA, USA, Lucrezia Reichlin, London Business School, London, UK, Herman Van Dijk, Erasmus University Rotterdam, Rotterdam, Jeffrey Wooldridge, Michigan State University, East Lansing, MI, USA
- Edited by Laszlo Matyas, Central European University, Budapest, Richard Blundell, University College London, Estelle Cantillon, Université Libre de Bruxelles, Barbara Chizzolini, Università Commerciale Luigi Bocconi, Milan, Marc Ivaldi, Wolfgang Leininger, Universität Dortmund, Ramon Marimon, European University Institute, Florence, Frode Steen
-
- Book:
- Economics without Borders
- Published online:
- 24 March 2017
- Print publication:
- 27 April 2017, pp 612-632
-
- Chapter
-
- You have access Access
- Open access
- Export citation
-
Summary
Abstract
The Big Data Era creates a lot of exciting opportunities for new developments in economics and econometrics. At the same time, however, the analysis of large datasets poses difficultmethodological problems that should be addressed appropriately and are the subject of the present chapter.
Introduction
‘Big Data’ has become a buzzword both in academic and in business and policy circles. It is used to cover a variety of data-driven phenomena that have very different implications for empirical methods. This chapter discusses some of these methodological challenges.
In the simplest case, ‘Big Data’ means a large dataset that otherwise has a standard structure. For example, Chapter 13 describes how researchers are gaining increasing access to administrative datasets or business records covering entire populations rather than population samples. The size of these datasets allows for better controls and more precise estimates and is a bonus for researchers. This may raise challenges for data storage and handling, but does not raise any distinct methodological issues.
However, ‘Big Data’ often means much more than just large versions of standard datasets. First, large numbers of units of observation often come with large numbers of variables, that is, large numbers of possible covariates. To illustrate with the same example, the possibility to link different administrative datasets increases the number of variables attached to each statistical unit. Likewise, business records typically contain all consumer interactions with the business. This can create a tension in the estimation between the objective of ‘letting the data speak’ and obtaining accurate (in a way to be specified later) coefficient estimates. Second, Big Data sets often have a very different structure from those we are used to in economics. This includes web search queries, real-time geolocational data or social media, to name a few. This type of data raises questions about how to structure and possibly re-aggregate them.
The chapter starts with a description of the ‘curse of dimensionality’, which arises from the fact that both the number of units of observation and the number of variables associated with each unit are large. This feature is present in many of the Big Data applications of interest to economists. One extreme example of this problem occurs when there are more parameters to estimate than observations.
12 - The impact of electoral debate on public opinions: an experimental investigation of the 2005 New York City mayoral election
-
- By Sendhil Mullainathan, Harvard University, Ebonya Washington, Yale University, Julia R. Azari, Marquette University
- Edited by Ian Shapiro, Yale University, Connecticut, Susan C. Stokes, Yale University, Connecticut, Elisabeth Jean Wood, Yale University, Connecticut, Alexander S. Kirshner, Yale University, Connecticut
-
- Book:
- Political Representation
- Published online:
- 05 June 2012
- Print publication:
- 14 January 2010, pp 324-341
-
- Chapter
- Export citation
-
Summary
Introduction
Political debates have long been a part of the American polity. The early practice was aimed primarily at promoting parliamentary and elite deliberation, as well as informing the broader public about issues and candidates (Jamieson and Birdsell 1988: 37). Televised debates have altered this dynamic, structuring debate as a practice to educate the electorate. Yet the impact of televised debates on the quality of democracy has been somewhat controversial, with proponents casting debates as opportunities “to provide sustained analysis of issues and close comparison of candidates” (ibid.: 5), and others expressing the concern that the televised debates would increase the emphasis on image rather than substance (Druckman 2003).
Whether debates influence opinions by showcasing candidate viewpoints or by simply presenting shallow cues of candidate image, conventional wisdom assumes that televised debates will somehow influence viewers' opinions regarding the candidates. Information in the electoral process is presumed to help voters make decisions more in line with their preferences (Lupia and McCubbins 1998). In light of the emphasis on the informative potential of debates, it is natural to pose the question of whether debates truly provide citizens with information that influences their opinions or choices.
To this end, there is a large literature examining the impact of debates on citizens' political opinions and voting behavior. This research has concluded that debates are able to alter viewers' opinions of candidates, but only in a small way.