About the Society
Papers, Posters, Syllabi
Submit an Item
Polmeth Mailing List
Below results based on the criteria 'prediction'
Total number of records returned: 4
Bayesian Combination of State Polls and Election Forecasts
In February of 2008, SurveyUSA polled 600 people in each state and asked who they would vote for in either head-to-head match-up: Obama vs. McCain, and Clinton vs. McCain. Here we integrate these polls with prior information; how each state voted in comparison to the national outcome in the 2004 election. We use Bayesian methods to merge prior and poll data, weighting each by its respective information. The variance for our poll data incorporates both sampling variability and variability due to time before the election, estimated using pre-election poll data from the 2000 and 2004 elections. The variance for our prior data is estimated using the results of the past nine presidential elections. The union of prior and poll data results in a posterior distribution predicting how each state will vote, in turn giving us posterior intervals for both the popular and electoral vote outcomes of the 2008 presidential election. Lastly, these posterior distributions are updated with the most recent poll data as of August, 2008.
Seven Deadly Sins of Contemporary Quantitative Political Analysis
philosophy of science
A combination of technological change, methodological drift and a certain degree of intellectual sloth and sloppiness, particularly with respect to philosophy of science,has allowed contemporary quantitative political analysis to accumulate a series of dysfunctional habits that have rendered a great deal of contemporary research more or less scientifically useless. The cure for this is not to reject quantitative methods -- and the cure is most certainly not a postmodernist nihilistic rejection of all systematic method -- but rather to return to some fundamentals, and take on some hard problems rather than expecting to advance knowledge solely through the ever-increasing application of fast-twitch muscle fibers to computer mice. In this paper, these "seven deadly sins" are identified as 1. Kitchen sink models that ignore the effects of collinearity; 2. Pre-scientific explanation in the absence of prediction; 3. Reanalyzing the same data sets until they scream; 4. Using complex methods without understanding the underlying assumptions; 5. Interpreting frequentist statistics as if they were Bayesian; 6. Linear statistical monoculture at the expense of alternative structures; 7. Confusing statistical controls and experimental controls. The answer to these problems is solid, thoughtful, original work driven by an appreciation of both theory and data. Not postmodernism. The paper closes with a review of how we got to this point from the perspective of 17th through 20th century philosophy of science, and provides suggestions for changes in philosophical and pedagogical approaches that might serve to correct some of these problems.
Automated Production of High-Volume, Near-Real-Time Political Event Data
natural language processing
This paper summarizes the current state-of-the-art for generating high-volume, near-real-time event data using automated coding methods, based on recent efforts for the DARPA Integrated Crisis Early Warning System (ICEWS) and NSF-funded research. The ICEWS work expanded by more than two orders of magnitude previous automated coding efforts, coding of about 26-million sentences generated from 8-million stories condensed from around 30 gigabytes of text. The actual coding took six minutes. The paper is largely a general ``how-to'' guide to the pragmatic challenges and solutions to various elements of the process of generating event data using automated techniques. It also discusses a number of ways that this could be augmented with existing open-source natural language processing software to generate a third-generation event data coding system.
Kernel Regularized Least Squares: Moving Beyond Linearity and Additivity Without Sacrificing Interpretability
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 classification problems without relying on linearity or additivity assumptions. The method constructs a flexible hypothesis space that uses kernels as radial basis functions and finds the best fitting surface in this space by minimizing a complexity-penalized least squares problem. We provide an accessible explanation of the method and argue that it is well suited for social science inquiry because it avoids strong parametric assumptions and still allows for simple interpretation in ways analogous to OLS or other members of the GLM family. We also extend the method in several directions to make it more effective for social inquiry. In particular, we (1) derive new estimators for the pointwise marginal effects and their variances, (2) establish unbiasedness, consistency, and asymptotic normality of the KRLS estimator under fairly general conditions, (3) develop an automated approach to chose smoothing parameters, and (4) provide companion software. We illustrate the use of the methods through several simulations and a real-data example.