Muhammet Ali Bas

Statistical Backwards Induction: A Simple Method for Estimating Recursive Strategic Models

We present a simple method for estimating regressions based on recursive extensive-form games. Our procedure, which can be implemented in most standard statistical packages, involves sequentially estimating standard logits (or probits) in a manner analogous to backwards induction. We demonstrate that the technique produces consistent parameter estimates and show how to calculate consistent standard errors. To illustrate the method, we replicate Leblang’s (2003) study of speculative attacks by financial markets and government responses to these attacks.

Arms Diffusion and War

The authors present a model of the relationship between the spread of new military technologies and the occurrence of war. A new technology could shift the balance of power, causing anticipatory war as one side tries to prevent the other from obtaining it. When one side already has it, war is more likely when the shift in power is large, likely, and durable. When neither side has it, war is more likely when the expected shift is asymmetric (e.g., one side is more likely to get it) and when the two sides fear that a war will occur once one of them has it. The authors illustrate the model with historical examples from the spread of firearms (the Musket Wars in precolonial New Zealand) and of nuclear weapons (the end of US nuclear monopoly and the 1967 Six-Day War). A broader implication is that major power competition can unintentionally cause wars elsewhere.

Measuring Uncertainty in International Relations: Heteroskedastic Strategic Models

Actor-level variations in the amounts of uncertainty have been widely ignored in the growing literature on statistical models of strategic interaction in international relations. In this article, I provide a tool for testing theories about the level of uncertainty in strategic interactions. I show that ignoring potential variations in levels of uncertainty across different cases can be a source of bias for empirical analyses. I propose a method to incorporate this form of heteroskedasticity into existing estimators and show that this method can improve inferences. With a series of Monte Carlo experiments, I evaluate the magnitude and the severity of the bias and inconsistency in estimators that ignore heteroskedasticity. More importantly, the tools developed in this article have many interesting substantive application areas. Examples considered include measuring speculators’ suboptimal behavior tendencies in international currency crises, and capturing varying levels of signaling and Bayesian updating behavior in the recent strategic models of signaling.

A Dynamic Theory of Nuclear Proliferation and Preventive War

We develop a formal model of bargaining between two states where one can invest in a program to develop nuclear weapons and the other imperfectly observes its efforts and progress over time. In the absence of a nonproliferation deal, the observing state watches the formers program, waiting until proliferation seems imminent to attack. Chance elements—when the program will make progress and when the other state will discover this—determine outcomes. Surprise proliferation, crises over the suspected progress of a nuclear program, and possibly “mistaken” preventive wars arise endogenously from these chance elements. Consistent with the models predictions and contrary to previous studies, the empirical evidence shows that the progress of a nuclear program and intelligence estimates of it explain the character and outcomes of most interactions between a proliferant and a potential preventive attacker. Counterintuitively, policies intended to reduce proliferation by delaying nuclear programs or improving monitoring capabilities may instead encourage it.

Democratic Inefficiency? Regime Type and Suboptimal Choices in International Politics

This article examines the relationship between regime type and decision makers’ tendency to make suboptimal choices in international crises. To test hypotheses on the optimality of democratic foreign policy, the author uses a novel statistical measure of suboptimality in foreign policy behavior. This estimator builds on Signorino’s statistical strategic models to allow for actor-level variation in deviations from optimal behavior in a strategic setting. An analysis of the international disputes from 1919 to 1999 shows that democratic leaders have a greater tendency to choose policies not optimal for their citizens than do nondemocratic leaders.

How Uncertainty about War Outcomes Affects War Onset

In canonical accounts of war, conflict outcomes are inherently uncertain. Contesting literatures posit that this uncertainty, arising from stochastic elements of the war-fighting process, may induce conflict due to greater risks of miscalculation or foster peace by breeding caution. We theorize that states, on average, exhibit prudence when confronting greater uncertainty. Despite its conceptual importance, extant proxies for uncertainty at various levels of analysis—such as polarity, balance of power, system concentration, and dyadic relative capabilities—are imprecise and theoretically inappropriate indicators. To overcome this shortcoming, we theorize the conditions that elevate the magnitude of uncertainty over conflict outcomes and introduce a novel measure that captures this uncertainty within any k-state system. Through extensive empirical analysis, we confirm uncertainty’s pacifying effect and show how this effect operates at different levels of analysis.

Accounting for Extra-Dyadic Sources of International Outcomes

ABSTRACT Leaders consider the broader international landscape when making foreign policy choices. This landscape could encompass a single external actor, the local region, or even the whole international system. Quantitative analyses of international outcomes, however, frequently do not account for this broader context. This study suggests a corrective, illustrating the value of incorporating extra-dyadic variables into analyses with dyadic and monadic outcomes. The challenge is to parsimoniously capture theoretically salient elements of the multilateral environment. We contend that a measure that links distributions of power within any k-set of relevant states to uncertainty over conflict outcomes is a promising option for two reasons. First, the measure builds from and accords with canonical theories of international politics. Second, it offers scholars a simple and flexible means to define and account for the set of states that constitute the relevant multilateral landscape. Illustrative applications linking power distributions and outcome uncertainty to alliance formation and pursuit of nuclear weapons demonstrate that extra-dyadic factors consistently influence foreign policy outcomes. This study thus shows that situating such outcomes within their broader context is both feasible and substantively important. Moreover, it contributes to recent efforts to address shortcomings of monadic and dyadic studies.

Natural Disasters and the Size of Nations

ABSTRACT What is the relationship between natural disasters and country size? Is an increasing likelihood of environmental shocks linked to political integration or secessionism? We argue that natural disasters are associated with a decline in country size. This relationship arises because costs generated by disasters are higher for citizens located farther away from the political center of a country, and costs are amplified as disasters affect a larger area in a country, which in turn makes it less desirable for citizens in remote regions to remain part of a larger country. Our empirical results show that greater risks of environmental shocks are indeed associated with smaller countries, as well as smaller administrative units.

Knowing one’s future preferences: A correlated agent model with Bayesian updating

We generalize two classes of statistical sequential incomplete information games: (1) those resembling typical signaling games, in which a single agent represents each player, allowing for information to be revealed about future play; and (2) those in which each player is represented by a set of independent agents, where moves do not reveal private information. The generalized model we develop, the Correlated Agent Model, relies on a parameter, ρ, which denotes the correlation between two agents’ private information, i.e. the extent to which a player knows the future private component of her preferences. The independent agent and single agent models are special cases, where ρ=0 and ρ=1, respectively. The model also allows 0 < ρ < 1, a class of games which have not yet been considered. We apply the model to crisis bargaining and demonstrate how to estimate ρ, as well as parameters associated with utilities.