2003-04
Paul Kellstedt
Texas A&M University
“National Moods and Issue-Specific Opinion Dynamics”
Thursday, November 13, 2003
Abstract: Aggregate public opinion drifts in both liberal and conservative directions over time. And yet,
when opinion does move, pundits and analysts tend to assume that the shift is the result of issue-specific politics.
On the other hand, the recent theoretical and empirical advancements surrounding the existence of a cross-issues
liberal-conservative Mood might suggest the opposite-that all single-issue movement is a function of the shifting national
Mood. In this paper, we investigate the extent to which Mood dominates issue-specific opinion, and (by implication) the
extent to which issue-specific opinion moves independently of Mood. We pursue this agenda by examining three issue
areas—education, the environment, and health care. A substantial part of this project involves the measurement of national
Mood, and, in particular, aggregate issue-specific opinion. We use Stimson's (1991) measure of national Mood, and a large
database of over-time survey marginals to construct time-series measures of issue-specific opinion through a process that is
analogous to dynamic factor analysis, but which allows for missing data. We compare these issue-specific opinion indices to
Mood, and then purge each index of the part that Mood can explain. We conclude by speculating on the forces, including
policy feedback and the cycles of issue attention, that might cause issue-specific opinion to diverge from the broader trend
in Mood.
Bio: Paul Kellstedt is an Assistant Professor at Texas A&M University with research interests in American politics,
public opinion, and political methodology. He is the author of The Mass Media and the Dynamics of American Racial Attitudes
(Cambridge University Press, 2003).
Walter Enders
University of Alabama
“After 9/11: Is It All Different Now?” (Sponsored by the Mershon Center)
Friday, April 9, 2004
Abstract: Using time-series procedures, we investigate whether transnational terrorism changed following 9/11 and the
subsequent US-led “war on terrorism.” Perhaps surprising, little has changed to the time series of overall incidents and
most of its component series. When 9/11 is prejudged as a break date, we find that logistically complex hostage-taking
events have fallen as a proportion of all events, while logistically simple, but deadly, bombings have increased as a
proportion of deadly incidents. These results hold when we apply the Bai-Perron procedure where structural breaks are data
identified. This procedure locates earlier breaks in the mid-1970s and 1990s. Reasonable out-of-sample forecasts are possible
if structural breaks are incorporated fairly rapidly into the model.
Bio: Professor Enders is an expert in time series analysis, and his book, Applied Econometric Time-Series, is the
leading book in the field; it is also used in the ITV Time Series course being taught now. Enders’ current research
focuses on the development and application of time-series models to areas in economics and finance.
View a Real Media stream of his presentation
HERE.
Narayan Sastry
RAND Corporation
“Family and Neighborhood Effects on Inequality in Children's Well-Being”
Thursday, May 6, 2004
Abstract: This paper examines family and neighborhood sources of socioeconomic inequality in children s well-being.
We consider children's reading and mathematics achievement as well as behavioral problems. We use data from the 2000-2001
Los Angeles Family and Neighborhood Study, a new survey designed to support multilevel studies on a number of topics.
To describe inequality in children's well-being, we use Gini coefficients and concentration indices and multilevel
regression models. We find no inequality in children s achievement by family income once other variables in the model
were held constant. Mothers reading scores and average neighborhood levels of income account for the largest proportion of
inequality in children s achievement.
Bio: Narayan Sastry is a research scientist at RAND Corporation. He holds a Ph.D. in public affairs from Princeton
University. Sastry’s research focuses on child health and mortality, population and development, and aging. Sastry possesses
methodological interests in duration models and multilevel modeling. His work has appeared in Journal of the American
Statistical Association, Demography, and other journals.
Douglas Rivers
Stanford University
“Panel Data Methods in Political Science” (Co-sponsored with ITV)
Wednesday, May 5, 2004
Bio: Doug Rivers is Professor of Political Science at Stanford University, Senior Fellow at the Hoover Institute,
and a Research Fellow at the Stanford Institute for the Quantitative Study of Society. Dr. Rivers specializes in American
Politics and the statistical analysis of electoral data. In 2000, he was named Market Research Executive of the Year by
the Research Business Report.
View a Real Media stream of his presentation
HERE.
David Darmofal
University of Illinois
“Spatial Econometrics and Models of Political Behavior”
Wednesday, May 19, 2004
Abstract: All data are spatial data: political behaviors in which we are interested occur at discrete geographic
locations. Many of our models of political behavior posit that these locations shape political behavior as the behavior of
observed units is influenced by units in close proximity. Despite these theoretical advances, our empirical tests of spatial
effects on behavior have often lagged behind. Recent advances in spatial econometrics and geographic information systems
(GIS) now allow for much more rigorous testing of spatial influences on political behavior than has previously been possible.
This talk will examine the problems that spatial effects pose for standard approaches to statistical inference. It will also
examine the statistical foundations of spatial econometrics. The talk will conclude by examining how spatial effects are
estimated using spatial econometric models, with particular applications to political behaviors.
Bio: David Darmofal holds a Ph.D. from the University of Illinois and will be PRISM Senior Methods Fellow at
Ohio State University in the 2004-05 academic year. He has research interests in political behavior and quantitative
methods.
