Estimating the ideological positions of political actors is an important step toward answering a number of substantive questions in political science. Survey scales provide useful data for such estimation, but also present a challenge, as respondents tend to interpret the scales differently. The Aldrich–McKelvey model addresses this challenge, but the existing implementations of the model still have notable shortcomings. Focusing on the Bayesian version of the model (BAM), the analyses in this article demonstrate that the model is prone to overfitting and yields poor results for a considerable share of respondents. The article addresses these shortcomings by developing a hierarchical Bayesian version of the model (HBAM). The new version treats self-placements as data to be included in the likelihood function while also modifying the likelihood to allow for scale flipping. The resulting model outperforms the existing Bayesian version both on real data and in a Monte Carlo study. An R package implementing the models in Stan is provided to facilitate future use.

Dynamic Network Actor Models (DyNAMs) assume that an observed sequence of relational events is the outcome of an actor-oriented decision process consisting of two decision levels. The first level represents the time until an actor initiates the next relational event, modeled by an exponential distribution with an actor-specific activity rate. The second level describes the choice of the receiver of the event, modeled by a conditional multinomial logit model. The DyNAM assumes that the parameters are constant over the actors and the context. This homogeneity assumption, albeit statistically and computationally convenient, is difficult to justify, e.g., in the presence of unobserved differences between actors or contexts. In this paper, we extend DyNAMs by including random-effects parameters that vary across actors or contexts and allow controlling for unknown sources of heterogeneity. We illustrate the model by analyzing relational events among the users of an online community of aspiring and professional digital and graphic designers.

Ensuring descriptive representation of racial minorities without packing minorities too heavily into districts is a perpetual difficulty, especially in states lacking voter file race data. One advance since the 2010 redistricting cycle is the advent of Bayesian Improved Surname Geocoding (BISG), which greatly improves upon previous ecological inference methods in identifying voter race. In this article, we test the viability of employing BISG to redistricting under two posterior allocation methods for race assignment: plurality versus probabilistic. We validate these methods through 10,000 redistricting simulations of North Carolina and Georgia’s congressional districts and compare BISG estimates to actual voter file racial data. We find that probabilistic summing of the BISG posteriors significantly reduces error rates at the precinct and district level relative to plurality racial assignment, and therefore should be the preferred method when using BISG for redistricting. Our results suggest that BISG can aid in the construction of majority-minority districts during the redistricting process.

This paper derives a new set of results that provide corrective measures of overall technical inefficiency that either have been ignored or wrongly assumed in the literature. Using directional distance functions, we argue that overall technical inefficiency is not only a function of input and output technical inefficiencies as previous studies claim but also of the interaction between them. The derivation of the interactive effects between input and output technical inefficiencies (IEIOs) solves the arbitrary decomposition of overall technical inefficiency into input and output components. We also show that the IEIO depends on the choice of the directional vector and whether quantities and prices are taken into consideration. Using exogenous and endogenous directional vectors, we prove these results theoretically and empirically using the US commercial banking data set. Using Bayesian estimation with the monotonicity conditions imposed at each observation, we estimate input and output technical inefficiencies separately using directional input and output distance functions with the three commonly used directional vectors; the unit value, the observed input−output, and the optimal directional vectors. The overall technical inefficiency is estimated using systems of equations to incorporate the interactive effect equation and to address the endogeneity of inputs and outputs. Consistent with the theoretical results, we find significant evidence of the IEIO which has a negative effect on the overall technical inefficiency. This result is robust to alternative directional vectors and model specifications, suggesting that the adjustability of both inputs and outputs is required for the improvement of the efficiency of the US commercial banks.

The purpose of this paper is to focus directly on the phase shift. For one thing, we ask whether a New Keynesian sticky-price model economy can account for both countercyclical prices and procyclical inflation. We present findings in which the price level is countercyclical and the inflation rate is procyclical. We proceed to use the model economy as an identification mechanism. What set of individual shocks are necessary to account for the phase shift? That set contains the price markup shock. Next, we ask what set of shocks are sufficient to account for the phase shift. This set contains three elements: the price markup and wage markup shocks along with the government spending shock. The results are important as a building block. We infer that price stickiness is an important model feature; without price stickiness, we are in the real business cycle economies that Cooley and Hansen studied. But, it raises further questions. For instance, is price stickiness of the Calvo form—the one used here—necessary to explain the phase shift?

Information about the ideological positions of different political actors is crucial in answering questions regarding political representation, polarization, and voting behavior. One way to obtain such information is to ask survey respondents to place actors on a common ideological scale, but, unfortunately, respondents typically display a set of biases when performing such placements. Key among these are rationalization bias and differential item functioning (DIF). While Aldrich–McKelvey (AM) scaling offers a useful solution to DIF, it ignores the issue of rationalization bias, and this study presents Monte Carlo simulations demonstrating that AM-type models thus can give inaccurate results. As a response to this challenge, this study develops an alternative Bayesian scaling approach, which simultaneously estimates DIF and rationalization bias, and therefore performs better when the latter bias is present.

Experiments should be designed to facilitate the detection of experimental measurement error. To this end, we advocate the implementation of identical experimental protocols employing diverse experimental modes. We suggest iterative nonparametric estimation techniques for assessing the magnitude of heterogeneous treatment effects across these modes. And we propose two diagnostic strategies—measurement metrics embedded in experiments, and measurement experiments—that help assess whether any observed heterogeneity reflects experimental measurement error. To illustrate our argument, first we conduct and analyze results from four identical interactive experiments: in the lab; online with subjects from the CESS lab subject pool; online with an online subject pool; and online with MTurk workers. Second, we implement a measurement experiment in India with CESS Online subjects and MTurk workers.

The empirical importance of news shocks—anticipated future shocks—in business cycle fluctuations has been explored by using only actual data when estimating models augmented with news shocks. This paper additionally exploits forecast data to identify news shocks in a canonical dynamic stochastic general equilibrium model. The estimated model shows new empirical evidence that technology news shocks are a major source of fluctuations in US output growth. Exploiting the forecast data not only generates more precise estimates of news shocks and other parameters in the model, but also increases the contribution of technology news shocks to the fluctuations.

In this paper we estimate a New-Keynesian dynamic stochastic general equilibrium (NK DSGE) model with heterogeneity in price and wage setting behavior. In a recent study, Coibion and Gorodnichenko develop a DSGE model, in which firms follow four different types of price setting schemes: sticky prices, sticky information, rule-of-thumb, or flexible prices. We enrich Coibion and Gorodnichenko framework by incorporating heterogeneity in nominal wage setting behavior among households. We solve this DSGE model and estimate it using Bayesian techniques for the US economy from 1955 to 2008. The estimation results show the relevance of heterogeneity in wage setting among households. More importantly, we identify qualitative and quantitative business cycle features allowed by the heterogeneity in wage rigidity, such as the persistence in price and wage inflation, which a standard NK model with only Calvo-type wage rigidity fails to achieve. We also show that modeling wage-rigidity heterogeneity—as opposed to standard Calvo wages—amplifies the macroeconomic output fluctuations resulting from a technology shock while it mitigates the output fluctuations following a monetary tightening.

This paper tries to infer and compare the evolution of the Federal Reserve’s (unobserved) inflation target series by estimating a monetary model under the alternative assumptions of rational expectations or subjective expectations and learning. In the estimated model that assumes that economic agents have rational expectations, the implied inflation target displays large shifts over time: it starts at 2% in the early 1960s, it rises to 8% in the 1970s, and it falls to 4% and 2% in the 1980s and 1990s. When the assumption of rational expectations is relaxed in favor of learning by the policymaker, the inferred target is, instead, remarkably stable over time. The target assumes values between 2% and 3% over the whole postwar sample. The findings suggest changing beliefs and learning by the Federal Reserve as major endogenous causes of the perceived variation in the inflation target. When the model is allowed to take the central bank’s evolving beliefs into account, the joint evolution of US inflation, output, and monetary policy decisions can be explained without requiring large exogenous changes in the inflation target.

Aircraft accidents are extremely rare in the aviation sector. However, their consequences can be very dramatic. One of the most important problems is runway excursions, when an aircraft exceeds the end (overrun) or the side (veer-off) of the runway. After performing exploratory analysis and hypothesis tests, a Bayesian-network-based approach was considered to provide information from risk scenarios involving landing procedures. The method was applied to a real database containing key variables related to landing operations on three runways. The objective was to analyse the effects over runway overrun excursions of failing to fulfil expert recommendations upon landing. For this purpose, the most influential variables were analysed statistically, and several scenarios were built, leading to a runway ranking based on the risk assessed.

We introduce a Bayesian approach to conduct inferential analyses on dyadic data while accounting for interdependencies between observations through a set of additive and multiplicative effects (AME). The AME model is built on a generalized linear modeling framework and is thus flexible enough to be applied to a variety of contexts. We contrast the AME model to two prominent approaches in the literature: the latent space model (LSM) and the exponential random graph model (ERGM). Relative to these approaches, we show that the AME approach is (a) to be easy to implement; (b) interpretable in a general linear model framework; (c) computationally straightforward; (d) not prone to degeneracy; (e) captures first-, second-, and third-order network dependencies; and (f) notably outperforms ERGMs and LSMs on a variety of metrics and in an out-of-sample context. In summary, AME offers a straightforward way to undertake nuanced, principled inferential network analysis for a wide range of social science questions.

Benhabib et al. [(2001) Journal of Economic Theory 96, 40–69] argue that there exists a deflation steady state when the zero lower bound on the nominal interest rate is considered in a Taylor-type monetary policy rule. This paper estimates a medium-scale DSGE model with a deflation steady state for the Japanese economy during the period from 1999 to 2013, when the Bank of Japan conducted a zero interest rate policy and the inflation rate was almost always negative. Although the model exhibits equilibrium indeterminacy around the deflation steady state, a set of specific equilibria is selected by Bayesian methods. According to the estimated model, positive shocks to households’ preferences and wage markup, and a negative shock to monetary policy do not necessarily have an inflationary effect, in contrast to a standard model with a targeted-inflation steady state. An economy in the deflation equilibrium could experience unexpected volatility because of sunspot fluctuations, but it turns out that sunspot shocks have a limited effect on Japan’s output fluctuations and rather contribute to stabilizing the economy after the global financial crisis.

Many bilateral relationships requiring mutual agreement produce observable networks that are symmetric (undirected). However, the unobserved, asymmetric (directed) network is frequently the object of scientific interest. We propose a method that probabilistically reconstructs the latent, asymmetric network from the observed, symmetric graph in a regression-based framework. We apply this model to the bilateral investment treaty network. Our approach successfully recovers the true data generating process in simulation studies, extracts new, politically relevant information about the network structure inaccessible to alternative approaches, and has superior predictive performance.

This paper creates a multinomial framework for ideal point estimation (mIRT) using recent developments in Bayesian statistics. The core model relies on a flexible multinomial specification that includes most common models in political science as “special cases.” I show that popular extensions (e.g., dynamic smoothing, inclusion of covariates, and network models) can be easily incorporated whilst maintaining the ability to estimate a model using a Gibbs Sampler or exact EM algorithm. By showing that these models can be written and estimated using a shared framework, the paper aims to reduce the proliferation of bespoke ideal point models as well as extend the ability of applied researchers to estimate models quickly using the EM algorithm. I apply this framework to a thorny question in scaling survey responses—the treatment of nonresponse. Focusing on the American National Election Study (ANES), I suggest that a simple but principled solution is to treat questions as multinomial where nonresponse is a distinct (modeled) category. The exploratory results suggest that certain questions tend to attract many more invalid answers and that many of these questions (particularly when signaling out particular social groups for evaluation) are masking noncentrist (typically conservative) beliefs.

At the microlevel, comparative public opinion data are abundant. But at the macrolevel—the level where many prominent hypotheses in political behavior are believed to operate—data are scarce. In response, this paper develops a Bayesian dynamic latent trait modeling framework for measuring smooth country–year panels of public opinion even when data are fragmented across time, space, and survey item. Six models are derived from this framework, applied to opinion data on support for democracy, and validated using tests of internal, external, construct, and convergent validity. The best model is reasonably accurate, with predicted responses that deviate from the true response proportions in a held-out test dataset by 6 percentage points. In addition, the smoothed country–year estimates of support for democracy have both construct and convergent validity, with spatiotemporal patterns and associations with other covariates that are consistent with previous research.

Recent empirical research stresses the importance of foresight in tax policy analyses, because failing to model foresight adequately leads to two types of biases: a bias that relates to a mismatch of information sets in the presence of foresight, and one that arises when time variation in foresight is ignored. This paper incorporates tax foresight into a framework of time-varying structural vector autoregression models with stochastic volatility to account for both types of biases. This reveals the effects of changing degrees of tax foresight on U.S. tax policy. Two findings stand out: First, anticipated and unanticipated tax shocks show considerable time variations, suggesting that some tax reforms were more anticipated than others. Second, the time-varying bias reveals that tax foresight was higher during the 1980s and 1990s than during the 1960s and 1970s. The results compare well with the literature and find support in documented U.S. tax episodes.

This paper assesses the empirical relevance of financial frictions in the Euro Area (EA) and the United States (US). It provides a comprehensive set of comparisons between two models: (i) a Smets and Wouters (SW) [F. Smets and R. Wouters, Shocks and frictions in US business cycles: A Bayesian DSGE approach, American Economic Review 97(3), 586–606 (2007)] model with financial frictions originating in nonfinancial firms and (ii) a SW model with frictions originating in financial intermediaries. The introduction of financial frictions in either way improves the models' fit compared to a standard SW model, and the empirical comparisons reveal that the latter model outperforms the former both in the euro area and in the United States. Two main factors explain this result: first, the magnitude of the financial accelerator effect, and second, the role of the investment-specific technology shock in affecting financial variables.

The Hardy–Weinberg (HW) principle explains how random mating (RM) can produce and maintain a population in equilibrium, that is, with constant genotypic proportions. When proportions diverge from HW form, it is of interest to estimate the fixation index F, which reflects the degree of divergence. Starting from a sample of genotypic counts, a mixed procedure gives first the orthodox estimate of gene frequency q and then a Bayesian estimate of F, based on a credible prior distribution of F, which is described here.

We present a demonstration of a Bayesian spatial probit model for a dichotomous choice contingent valuation method willingness-to-pay (WTP) questions. If voting behavior is spatially correlated, spatial interdependence exists within the data, and standard probit models will result in biased and inconsistent estimated nonbid coefficients. Adjusting sample WTP to population WTP requires unbiased estimates of the nonbid coefficients, and we find a $17 difference in population WTP per household in a standard vs. spatial model. We conclude that failure to correctly model spatial dependence can lead to differences in WTP estimates with potentially important policy ramifications.