Thesis (Ph. D.)--University of Rochester. Department of Political Science, 2014.
The dissertation consists of three distinct essays about the politics of conflict
and diplomacy. The first essay examines the politics of internal divisions in
an externally occupied territory. It uses a formal model to develop a new
theory of how the policies of an extractive outside force affect the occurrence
of internal social conflict, and vice versa. The results of the analysis run
counter to the conventional wisdom of “divide and rule.” All else equal, a
ruler would rather govern a unified society than a divided one, as internal
conflict is economically destructive. Similarly, the essay shows that an outside
force has no incentive to create artificial inequality between identical social
groups.
The second essay studies the problems of diplomatic communication between
states that have a common purpose, such as in a joint military effort.
It employs a formal model to characterize the conditions under which a state
can credibly reveal private information to its ally. The results call into question
the supposition that alliances play a general information-sharing role.
No informative communication is possible when the states’ private information concerns their cost of contributing to the project or, equivalently,
their willingness to contribute. When the source of private information is
intelligence about how much effort will be required for the joint project to
succeed, communication is possible only under highly restrictive conditions.
On the other hand, communication is broadly possible if there are multiple
avenues of contribution (e.g., ground and air power) and states have private
information about their specialty.
The third essay concerns methodology for dealing with systematic missing
data or measurement error in a binary dependent variable, a common issue in
empirical studies of conflict. The essay provides methods to estimate bounds
on the set of results that could be obtained under any assumption about the
source of missingness. Unlike usual approaches, these estimators do not depend
on untestable assumptions or require application-specific programming.
The essay applies these methods to data from two previous studies of conflict
to examine the robustness of their results against potential miscoding of
outcomes.