Working Papers and Papers Under Review
Park, Sunhee, and David J. Hendry. "Reassessing Schoenfeld Residual
Tests of Proportional Hazards in Political Science Event History Analyses."
(Invited to revise and resubmit at American Journal of Political
Abstract: An underlying assumption of proportional hazards
models is that the effect of a change in a covariate on the hazard rate of
event occurrence is constant over time. For scholars using the Cox model, a
Schoenfeld residual-based test has become the disciplinary standard for
detecting violations of this assumption. However, using this test requires
researchers to make a choice about a transformation of the time scale. In
practice, this choice has largely consisted of arbitrary decisions made
without justification. Using replications and simulations, we demonstrate
that the decision about time transformations can have profound implications
for the conclusions reached. In particular, we show that researchers can
make far more informed decisions by paying closer attention to the presence
of outlier survival times and levels of censoring in their data. We suggest
a new standard for best practices in Cox diagnostics that buttresses the
current standard with in-depth exploratory data analysis.
[Main - pdf]
[Appendix 1 - pdf]
[Appendix 2 - pdf]
Gerber, Alan S., Gregory A. Huber, Marc Meredith, Daniel R. Biggers, and
David J. Hendry. "Can Incarcerated Felons Be (Re)integrated into the
Political System? Results from a Field Experiment." (Under review).
Abstract: How does America's high rate of incarceration shape
political participation? Few studies have examined the direct effects of
incarceration on patterns of political engagement. Answering this question is
particularly relevant for the 93% of formerly incarcerated individuals who are
eligible to vote. Drawing on new administrative data from Connecticut, we
present evidence from a field experiment showing that a simple informational
outreach campaign to released felons can recover a large proportion of the
reduction in participation observed following incarceration. The treatment
effect estimates imply that efforts to reintegrate released felons into the
political process can substantially reduce the participatory consequences of
[Main - pdf]
[Appendix - pdf]
Hendry, David J.. "Small-group Conformity and Political Attitudes."
Abstract: Public responses to attitudinal questions tapping
sensitive social issues are likely to paint an optimistic picture of the
degree to which individuals adhere to desirable social norms. But little is
known empirically about how social pressures operate at the level of
interpersonal interactions. This study conducts a laboratory experiment to
address the question of how even minimal social pressure leads to conformity
with respect to attitude expressions about adherence to egalitarian norms.
Baseline attitudinal measurements were taken of subjects, and then those
measurements were used to exert social pressure in a contrived group setting.
An asymmetric effect was found in which subjects who were willing to espouse
an inegalitarian attitude in private were more likely to succumb to social
pressure to change their expressed attitudes when faced with an opposed group
opinion. For subjects who espouse egalitarian attitudes in private, social
pressure to provide an inegalitarian response has little impact.
[Main - pdf]
[Appendix - pdf]
Gerber, Alan S., Gregory A. Huber, Daniel R. Biggers, and David J. Hendry
. Forthcoming. "Ballot Secrecy Concerns and Voter Mobilization: New
Experimental Evidence about Message Source, Context, and the Duration of
Mobilization Effects." American Politics Research.
Abstract: Recent research finds that doubts about the
integrity of the secret ballot as an institution persist among the American
public. We build on this finding by providing novel field experimental
evidence about how information about ballot secrecy protections can increase
turnout among registered voters who had not previously voted. First, we show
that a private group's mailing designed to address secrecy concerns modestly
increased turnout in the highly contested 2012 Wisconsin gubernatorial recall
election. Second, we exploit this and an earlier field experiment conducted in
Connecticut during the 2010 congressional midterm election season to identify
the persistent effects of such messages from both governmental and
non-governmental sources. Together, these results provide new evidence about
how message source and campaign context affect efforts to mobilize previous
non-voters by addressing secrecy concerns, as well as show that attempting to
address these beliefs increases long term participation.
Althaus, Scott L., Nathaniel Swigger, Svitlana Chernykh, David J. Hendry
, Sergio C. Wals, and Christopher Tiwald. Forthcoming. "Uplifting Manhood
to Wonderful Heights? News Coverage of the Human Costs of Military Conflict
from World War One to Gulf War Two." Political Communication.
Abstract: Domestic political support is an important factor
constraining the use of American military power around the world. Although
the dynamics of war support are thought to reflect a cost-benefit calculus,
with costs represented by numbers of friendly war deaths, no previous study
has examined how information about friendly, enemy, and civilian casualties is
routinely presented to domestic audiences. This paper establishes a baseline
measure of historical casualty reporting by examining New York Times
coverage of five major wars that occurred over the past century. Despite
important between-war differences in the scale of casualties, the use of
conscription, the type of warfare, and the use of censorship, the frequency of
casualty reporting and the framing of casualty reports has remained fairly
consistent over the past 100 years. Casualties are rarely mentioned in
American war coverage. When casualties are reported, it is often in ways that
minimize or downplay the human costs of war.
Hendry, David J. 2014. "Data Generation for the Cox Proportional
Hazards Model with Time-Dependent Covariates: A Method for Medical
Researchers." Statistics in Medicine 33(3): 436–454.
Abstract: The proliferation of longitudinal studies has
increased the importance of statistical methods for time-to-event data that
can incorporate time-dependent covariates. The Cox proportional hazards model
is one such method that is widely used. As more extensions of the Cox model
with time-dependent covariates are developed, simulations studies will grow in
importance as well. An essential starting point for simulation studies of
time-to-event models is the ability to produce simulated survival times from a
known data generating process. This paper develops a method for the
generation of survival times that follow a Cox proportional hazards model with
time-dependent covariates. The method presented relies on a simple
transformation of random variables generated according to a truncated
piecewise exponential distribution, and allows practitioners great flexibility
and control over both the number of time-dependent covariates and the number
of time periods in the duration of follow-up measurement. Within this
framework, an additional argument is suggested that allows researchers to
generate time-to-event data in which covariates change at integer-valued steps
of the time scale. The purpose of this approach is to produce data for
simulation experiments that mimic the types of data structures applied
researchers encounter when using longitudinal biomedical data. Validity is
assessed in a set of simulation experiments and results indicate that the
proposed procedure performs well in producing data that conform to the
assumptions of the Cox proportional hazards model.
Althaus, Scott L., Nathaniel Swigger, Svitlana Chernykh,
David J. Hendry,
Sergio C. Wals, and Christopher Tiwald. 2011. "Assumed Transmission in
Political Science: A Call for Bringing Description Back In." Journal
of Politics 73(4): 1065–1080.
Abstract: News outlets cannot serve as reliable conveyors of
social facts, nor do their audiences crave such content. Nonetheless, much
political science scholarship assumes that objective information about social,
political, and economic topics is routinely transmitted to the mass public
through the news. This article addresses the problem of selection bias in
news content and illustrates the problem with a content analytic study of
New York Times coverage given to American war deaths in five major
conflicts that occurred over the past century. We find that news coverage of
war deaths is unrelated to how many American combatants have recently died.
News coverage is more likely to mention war deaths when reporting combat
operations and less likely to mention them when a war is going well. These
findings underscore the need to document selection biases in information flows
before theorizing about proximate causes underlying the relationships between
political systems and public opinion.
Hendry, David J., Robert A. Jackson, and Jeffery J. Mondak. 2009. "Abramoff,
Email, and the Mistreated Mistress: Scandal and Character 2006 Elections." In
Fault Lines: Why the Republicans Lost Congress, eds., Jeffery J.
Mondak and Dona-Gene Mitchell. New York: Routledge pp. 84–110.