Goplerud, Max. 2015. "The First Time is (Mostly) the Charm: Special Advisers as Parliamentary Candidates and Members of Parliament." Parliamentary Affairs. 68(2):332-351. [publisher's version]
Goplerud, Max. 2014. "Appendix 1: Methodology" and "Appendix 2: Further Work on the Distribution and Tenure of Special Advisers" in Special Advisers: Who They Are, What They Do and Why They Matter, (eds.) Ben Yong and Robert Hazell. Oxford: Hart. [data on special advisers, 1979-2013]
My working papers are available below.
Goplerud, Max. "Modelling Heterogeneity Using Bayesian Structured Sparsity." [draft]
How to estimate heterogeneity, e.g. the effect of some variable differing across observations, is a key question in political science. Methods for doing so make simplifying assumptions about the underlying nature of the heterogeneity to draw reliable inferences. This paper allows a common way of simplifying complex phenomenon (placing observations with similar effects into discrete groups) to be integrated into regression analysis. The framework allows researchers to (i) use their prior knowledge to guide which groups are permissible and (ii) appropriately quantify uncertainty. The paper does this by translating work on "structured sparsity" from a penalized likelihood approach into a Bayesian prior and deriving theoretical results on posterior propriety and inference. It shows that this method outperforms state-of-the-art methods for estimating heterogeneous effects when the underlying heterogeneity is grouped and more effectively identifies groups of observations with different effects in observational data.
Goplerud, Max. "Fast and Accurate Estimation of Hierarchical Models using Variational Algorithms." [draft]
Hierarchical models are commonly used in political science to address unobserved heterogeneity and model dependencies between observations. Inference for these models is typically conducted by maximum likelihood estimation or fully Bayesian analysis. Both methods can be slow on even moderately sized datasets, especially for non-linear models. This paper addresses this by deriving new algorithms for finding the maximum likelihood estimate using fast variational Expectation Maximization (EM), leveraging recent advances in data augmentation. These algorithms outperform existing variational methods on simulated data and closely recover the point estimates of "gold standard" methods on both simulated and actual datasets. I also provide a method for calculating approximate standard errors that has reasonable performance. I re-examine two papers in detail and show that simple extensions (e.g. adding an additional random effect) dramatically increase the computational cost for existing methods but only lead to modest increases for the variational approach.
Goplerud, Max and Daniel M. Smith. "Electoral Rules, Legislative Institutions, and Responsible Party Government."
Among the key features of "responsible party government" is contestation between government and opposition and accountability of cabinet ministers to parliament. However, the institutional determinants of this model of legislative organization are ambiguous. We use extensive data covering millions of committee speeches in Japan to document how new electoral incentives following a party-strengthening electoral system reform to the lower chamber of parliament immediately shifted legislative behavior toward responsible party government: speeches by ministers increased, speeches by unelected bureaucrats decreased, and discursive accountability between ministers and opposition legislators increased. Notably, this behavioral shift also occurred in the upper chamber, which was not directly subject to the electoral reform. Subsequent administrative reforms expanding junior ministerial roles and placing explicit limits on bureaucratic participation reinforced the effects in both chambers. These findings shed new light on the institutional underpinnings of responsible party government in general, as well as its progressive development in Japan.
Goplerud, Max, Shiro Kuriwaki, Marc Ratkovic, and Dustin Tingley. "Sparse Multilevel Regression (and Poststratification (sMRP))." [draft]
Multilevel models have long played an important role in a variety of social sciences. We extend this framework by bring to bear recent developments in the machine learning literature to allow for considerable flexibility. We introduce a sparse regression framework that covers both the linear case as well as a logit model for binary outcome data. We leverage recent computational tricks based on data-augmentation to dramatically speed up estimation times with equal or better performance compared to existing approaches. We apply our model in the context of multilevel modelling with post-stratification which has become a common tool for survey researchers.