The analysis of time-series cross-sectional (TSCS) data has become increasingly popular in political science. Meanwhile, political scientists are also becoming more interested in the use of multilevel models (MLM). However, little work exists to understand the benefits of multilevel modeling when applied to TSCS data. We employ Monte Carlo simulations to benchmark the performance of a Bayesian multilevel model for TSCS data. We find that the MLM performs as well or better than other common estimators for such data. Most importantly, the MLM is more general and offers researchers additional advantages.

Logistic regression models have been used in political science for estimating ideal points of legislators and Supreme Court justices. These models present estimation and identifiability challenges, such as improper variance estimates, scale and translation invariance, reflection invariance, and issues with outliers. We address these issues using Bayesian hierarchical modeling, linear transformations, informative regression predictors, and explicit modeling for outliers. In addition, we explore new ways to usefully display inferences and check model fit.

We fit a multilevel logistic regression model for the mean of a binary response variable conditional on poststratification cells. This approach combines the modeling approach often used in small-area estimation with the population information used in poststratification (see Gelman and Little 1997, Survey Methodology 23:127–135). To validate the method, we apply it to U.S. preelection polls for 1988 and 1992, poststratified by state, region, and the usual demographic variables. We evaluate the model by comparing it to state-level election outcomes. The multilevel model outperforms more commonly used models in political science. We envision the most important usage of this method to be not forecasting elections but estimating public opinion on a variety of issues at the state level.

The Senate Budget Committee is a unique and potentially powerful institution in the US legislature. It was begun to help coordinate the federal budget making process in the US Senate. Long-term trends and short-term institutional dynamics have weakened the coordinating capacity of the committee to the point that the budget process was entirely ignored in 2011. This article explores these changes. It shows evidence for Democrats and Republicans on the committee moving further apart ideologically since the 1970s resulting in more partisanship and less deliberation on the committee. It also shows how a combination of a narrow Democratic majority on the committee along with a recent uptick in ideological heterogeneity among Democrats but without prospects for bipartisanship, resulted in no budget process in 2011.

Based on information available in July, we predicted that the Republicans would receive 52.9% of the total House vote and end up holding 229 seats, gaining control from the Democrats in the process (Bafumi, Erikson, and Wlezien 2010b). Our national vote forecast proved to be nearly correct, undershooting the actual Republican share (53.8%) by slightly less than one percentage point. Our seat forecast was a little less accurate. Although we did foresee the House changing hands, we did not predict such a large Republican windfall in seats—we forecast a “mere” swing of 50 seats, which was short of the actual outcome by about 13 seats. The Republican seat total of 242, however, was well within the 95% confidence interval (199 to 259).

In this article, we present a forecast of the 2010 midterm House election based on information available in early July 2010. We combine this forecast with a note of caution, explaining why electoral circumstances might lead our forecast to err. Finally, we present guidance regarding how to update the electoral forecast for 2010 based on new information that will become available leading up to Election Day.

We consider the relationship between the preferences of American voters and the preferences of the U.S. legislators who represent them. Using an Internet-based, national opinion survey in conjunction with legislator voting records from the 109th and 110th Congresses, we show that members of Congress are more extreme than their constituents, i.e., that there is a lack of congruence between American voters and members of Congress. We also show that when a congressional legislator is replaced by a new member of the opposite party, one relative extremist is replaced by an opposing extremist. We call this leapfrog representation, a form of representation that leaves moderates with a dearth of representation in Congress. We see evidence of leapfrog representation in states and House districts and in the aggregate as well: the median member of the 109th House was too conservative compared to the median American voter, yet the median of the 110th House was too liberal. Thus, the median American voter was leapfrogged when the 109th House transitioned to the 110th. Although turnover between the 109th and 110th Senates occurred at approximately the same rate as between the 109th and 110th Houses, the Senate appears to be a more moderate institution whose median member does not move as abruptly as that of the House.

One mystery of U.S. politics is why the president’s party regularly loses congressional seats at midterm. Although presidential coattails and their withdrawal provide a partial explanation, coattails cannot account for the fact that the presidential party typically performs worse than normal at midterm. This paper addresses the midterm vote separate from the presidential year vote, with evidence from generic congressional polls conducted during midterm election years. Polls early in the midterm year project a normal vote result in November. But as the campaign progresses, vote preferences almost always move toward the out party. This shift is not a negative referendum on the president, as midterms do not show a pattern of declining presidential popularity or increasing salience of presidential performance. The shift accords with “balance” theory, where the midterm campaign motivates some to vote against the party of the president in order to achieve policy moderation.

Voting power indexes such as that of Banzhaf are derived, explicitly or implicitly, from the assumption that all votes are equally likely (i.e., random voting). That assumption implies that the probability of a vote being decisive in a jurisdiction with n voters is proportional to 1/√n. In this article the authors show how this hypothesis has been empirically tested and rejected using data from various US and European elections. They find that the probability of a decisive vote is approximately proportional to 1/n. The random voting model (and, more generally, the square-root rule) overestimates the probability of close elections in larger jurisdictions. As a result, classical voting power indexes make voters in large jurisdictions appear more powerful than they really are. The most important political implication of their result is that proportionally weighted voting systems (that is, each jurisdiction gets a number of votes proportional to n) are basically fair. This contradicts the claim in the voting power literature that weights should be approximately proportional to √n.

In late August 2000, at APSA's Annual Meeting, a panel of politicalscientists offered forecasts for the 2000 presidential election.Although they differed in particulars, most of the forecasters'models incorporated a measure of economic growth plus thepresident's approval rating. Because the economy was prospering andPresident Clinton enjoyed phenomenal approval numbers for the eighthyear of office, the consensus prediction was a Democratic (Gore)victory by upwards of 6 percentage points. Although politicalscientists had offered forecasts before previous presidentialelections, these political scientists' predictions for 2000attracted more interest than usual. Their predictions drewexceptional interest both during the campaign, when nobody knew forsure how the election would turn out, and after, when theforecasters had to account for their mistakes.