Chad Hazlett

Home CV Writing Software

Kernel Balancing (KBAL): A Balancing Method to Equalize Multivariate Densities and Reduce Bias without a Specification Search
Investigators often use matching and weighting techniques to adjust for differences between treated and control groups on observed characteristics. These methods, however, require the user to choose what functions of the covariates must be balanced, and do not in general ensure equal multivariate densities of the treated and control groups. Treatment effect estimates made after adjustment by these methods are thus sensitive to specification choices, and are biased if any function of the covariates influencing the outcome has a different mean for the treated and control groups. This paper introduces kernel balancing, a method designed to reduce this bias without relying on specification searches or balance tests. The weights derived by kernel balancing (1) achieve approximate mean balance on a large class of smooth functions of the covariates, and (2) approximately equalize the multivariate densities of the treated and controls. In two empirical applications, kernel balancing (1) accurately recovers the experimentally estimated effect of a job training program, and (2) finds that after controlling for observed differences, democracies are less likely to win counterinsurgencies, consistent with theoretical expectation but in contrast to previous findings.

Kernel Regularized Least Squares: Reducing Misspecification Bias with a
Flexible and Interpretable Machine Learning Approach (with Jens Hainmueller). Political Analysis.
Paper    Appendix 
We propose the use of Kernel Regularized Least Squares (KRLS) for social science modeling and inference problems. KRLS borrows from machine learning methods designed to solve regression and classi cation problems without relying on linearity or additivity assumptions. The method constructs a flexible hypothesis space that uses kernels as radial basis functions and fi nds the best-fi tting surface in this space by minimizing a complexity-penalized least squares problem. We argue that the method is well-suited for social science inquiry because it avoids strong parametric assumptions, yet allows interpretation in ways analogous to generalized linear models while also permitting more complex interpretation to examine non-linearities, interactions, and heterogeneous effects.We also extend the method in several directions to make it more e ffective for social inquiry, by (1) deriving estimators for the pointwise marginal eff ects and their variances, (2) establishing unbiasedness, consistency, and asymptotic normality of the KRLS estimator under fairly general conditions, (3) proposing a simple automated rule for choosing the kernel bandwidth, and (4) providing companion software. We illustrate the use of the method through simulations and empirical examples.

Angry or Weary? The effect of physical violence on attitudes towards peace in Darfur

Exposure to indiscriminate violence during civil conflict is generally thought to increase anger towards it perpetrators, the desire for vengeance, and pessimism regarding the prospects for peace and security. Alternatively, however, experiences with violence during conflict could make individuals more "weary", less interested in retribution, and more desiring of peace. While these responses theoretically play a role in the evolution and recurrence of violent conflict, it has been difficult to obtain micro-level evidence for how violence impacts these attitudes. This paper uses information about the indiscriminate nature of violence in Darfur and a new survey of Darfurian refugees to shed light on the responses of Darfurian civilians to violence. Results consistently support the "weary" response, with individuals exposed to direct physical violence more likely to report that peace is possible, and less likely to demand that their enemies be executed. This finding qualifies existing theories of recurrent violence, but is consistent with an emerging view that exposure to violence increases some pro-social attitudes. It also suggests that victims of violence can play an important role in political settlement processes.

KRLS: A Stata Package for Kernel-Based Regularized Least Squares (with Jeremy Ferwerda, Jens Hainmueller)
The Stata package krls implements Kernel-Based Regularized Least Squares (KRLS), a machine learning method described in Hainmueller and Hazlett (2013) that allows users to solve regression and classifi cation problems without manual specification searches or strong functional form assumptions. The flexible KRLS estimator learns the functional form from the data and thereby protects inferences against misspeci fication bias. Yet, it nevertheless allows for interpretability and inference in ways similar to ordinary regression models. In particular, KRLS provides closed-form estimates for the predicted values, variances, and the pointwise partial derivatives that characterize the marginal e ffects of each independent variable at each data point in the covariate space. The method is thus a convenient and powerful alternative to OLS and other GLMs for regression-based analyses.

Photo: Lunch at a training camp for local relief workers in eastern Burma