哥伦比亚大学面板讲义

POLS W4292
Advanced Topics in Quantitative Research:
Models for Panel and Time-Series Cross-Section Data
Gregory Wawro
Associate Professor
Department of Political Science
Columbia University
420 W. 118th St.
New York, NY 10027
phone: (212) 854-8540
fax: (212) 222-0598
email: gjw10@columbia.edu
Section 1
General Issues With Repeated Observations Data
1.1 Introduction
Definition: data in which we observe cross-sectional units at more
than one time period.
• Repeated observations data (ROD) is a very valuable resource for
finding empirical solutions to social science puzzles.
â Quantity: increases samples sizes/provides more df.
â Quality: enables us to answer questions in ways that cross-sectional
data cannot.
• Example 1: Suppose we have a cross-sectional data set where we
observe that the participation rate of Latinos in an election is 40%.
â Could be the case that a given Latino voter has a 40% chance of
participating in any given election.
â Could also be the case that 40% of Latinos will vote in every
election and 60% will never vote.
â Can distinguish b/t these two scenarios if we get to observe these
voters over time.