文档介绍：P1: FJJ/Shraban
WV006-01 February 16, 2001 12:54
Logistic Regression in Rare
Events Data
Gary King
Center for Basic Research in the Social Sciences, 34 Kirkland Street,
Harvard University, Cambridge, MA 02138
e-mail: ******@
Langche Zeng
Department of Political Science, e Washington University,
Funger Hall, 2201 G Street NW, Washington, DC 20052
e-mail: ******@
We study rare events data, binary dependent variables with dozens to thousands of times
fewer ones (events, such as wars, vetoes, cases of political activism, or epidemiological
infections) than zeros (“nonevents”). In many literatures, these variables have proven dif-
ficult to explain and predict, a problem that seems to have at least two sources. First,
popular statistical procedures, such as logistic regression, can sharply underestimate the
probability of rare events. We mend corrections that outperform existing methods
and change the estimates of absolute and relative risks by as much as some estimated
effects reported in the literature. Second, commonly used data collection strategies are
grossly inefficient for rare events data. The fear of collecting data with too few events has
led to data collections with huge numbers of observations but relatively few, and poorly
measured, explanatory variables, such as in international conflict data with more than a
quarter-million dyads, only a few of which are at war. As it turns out, more efficient sam-
pling designs exist for making valid inferences, such as sampling all available events (.,
wars) and a tiny fraction of nonevents (peace). This enables scholars to save as much
as 99% of their (nonfixed) data collection costs or to collect much more meaningful ex-
planatory variables. We provide methods that link these two results, enabling both types of
corrections to work simultaneously, and software that implements the methods developed.
Authors’ note: We thank J