Search

Nationwide opinions and international attitudes toward climate and environmental change are receiving increasing attention in both scientific and political communities. An often used way to measure these attitudes is by large-scale social surveys. However, the assumption for a valid country comparison, measurement invariance, is often not met, especially when a large number of countries are being compared. This makes a ranking of countries by the mean of a latent variable potentially unstable, and may lead to untrustworthy conclusions. Recently, more liberal approaches to assessing measurement invariance have been proposed, such as the alignment method in combination with Bayesian approximate measurement invariance. However, the effect of prior variances on the assessment procedure and substantive conclusions is often not well understood. In this article, we tested for measurement invariance of the latent variable “willingness to sacrifice for the environment” using Maximum Likelihood Multigroup Confirmatory Factor Analysis and Bayesian approximate measurement invariance, both with and without alignment optimization. For the Bayesian models, we used multiple priors to assess the impact on the rank order stability of countries. The results are visualized in such a way that the effect of different prior variances and models on group means and rankings becomes clear. We show that even when models appear to be a good fit to the data, there might still be an unwanted impact on the rank ordering of countries. From the results, we can conclude that people in Switzerland and South Korea are most motivated to sacrifice for the environment, while people in Latvia are less motivated to sacrifice for the environment.

The concept of free energy has its origins in 19th century thermodynamics, but has recently found its way into the behavioral and neural sciences, where it has been promoted for its wide applicability and has even been suggested as a fundamental principle of understanding intelligent behavior and brain function. We argue that there are essentially two different notions of free energy in current models of intelligent agency, that can both be considered as applications of Bayesian inference to the problem of action selection: one that appears when trading off accuracy and uncertainty based on a general maximum entropy principle, and one that formulates action selection in terms of minimizing an error measure that quantifies deviations of beliefs and policies from given reference models. The first approach provides a normative rule for action selection in the face of model uncertainty or when information processing capabilities are limited. The second approach directly aims to formulate the action selection problem as an inference problem in the context of Bayesian brain theories, also known as Active Inference in the literature. We elucidate the main ideas and discuss critical technical and conceptual issues revolving around these two notions of free energy that both claim to apply at all levels of decision-making, from the high-level deliberation of reasoning down to the low-level information processing of perception., publishedVersion

We develop methods for robust Bayesian inference in structural vector autoregressions (SVARs) where the parameters of interest are set-identified using external instruments, or 'proxy SVARs'. Set-identification in these models typically occurs when there are multiple instruments for multiple structural shocks. Existing Bayesian approaches to inference in proxy SVARs require researchers to specify a single prior over the model's parameters, but, under set-identification, a component of the prior is never revised. We extend the robust Bayesian approach to inference in set-identified models proposed by Giacomini and Kitagawa (2018) - which allows researchers to relax potentially controversial point-identifying restrictions without having to specify an unrevisable prior - to proxy SVARs. We provide new results on the frequentist validity of the approach in proxy SVARs. We also explore the effect of instrument strength on inference about the identified set. We illustrate our approach by revisiting Mertens and Ravn (2013) and relaxing the assumption that they impose to obtain point identification.

In our laboratory experiment, subjects, in sequence, have to predict the value of a good. The second subject in the sequence makes his prediction twice: first ("first belief"), after he observes his predecessor's prediction; second ("posterior belief"), after he observes his private signal. We find that the second subjects weigh their signal as a Bayesian agent would do when the signal confirms their first belief; they overweight the signal when it contradicts their first belief. This way of updating, incompatible with Bayesianism, can be explained by the Likelihood Ratio Test Updating (LRTU) model, a generalization of the Maximum Likelihood Updating rule. It is at odds with another family of updating, the Full Bayesian Updating. In another experiment, we directly test the LRTU model and find support for it.

In recent years there has been increasing concern about the identification of parameters in dynamic stochastic general equilibrium (DSGE) models. Given the structure of DSGE models it may be difficult to determine whether a parameter is identified. For the researcher using Bayesian methods, a lack of identification may not be evident since the posterior of a parameter of interest may differ from its prior even if the parameter is unidentified. We show that this can even be the case even if the priors assumed on the structural parameters are independent. We suggest two Bayesian identification indicators that do not suffer from this difficulty and are relatively easy to compute. The first applies to DSGE models where the parameters can be partitioned into those that are known to be identified and the rest where it is not known whether they are identified. In such cases the marginal posterior of an unidentified parameter will equal the posterior expectation of the prior for that parameter conditional on the identified parameters. The second indicator is more generally applicable and considers the rate at which the posterior precision gets updated as the sample size (T) is increased. For identified parameters the posterior precision rises with T, whilst for an unidentified parameter its posterior precision may be updated but its rate of update will be slower than T. This result assumes that the identified parameters are -consistent, but similar differential rates of updates for identified and unidentified parameters can be established in the case of super consistent estimators. These results are illustrated by means of simple DSGE models.

"In diesem Beitrag untersuchen die Autoren das Abstimmungsverhalten der Länder bei namentlichen Abstimmungen im Bundesrat im Zeitraum von der deutschen Wiedervereinigung 1990 bis zum Ende der Regierung Gerhard Schröders 2005. Sie gehen der Frage nach, ob und wenn ja, wann und in welchem Ausmaß der Bundesrat parteipolitisiert ist. Analytisch geht es um die Frage, wie ein durch originär sachpolitische Interessen motiviertes Verhalten von einem solchen unterschieden werden kann, das sich ausschließlich am strategischen Wettbewerb der Parteien um Wählerstimmen orientiert. Die Autoren entwickeln dazu eine Analysemethode, mit welcher der Zusammenhang zwischen sachpolitischen Länder- respektive Parteiinteressen und parteipolitischer Motivation, also etwa dem Druck, der durch die Parteilager ausgeübt wird, aufgelöst werden kann." (Autorenreferat), "The article analyzes the roll call voting behavior of German Länder governments in the Bundesrat from 1990 to 2005. The authors examine if, when, and to what extent the German Bundesrat is dominated by federal party politics rather than by an appropriate conflict of policy interest between states and state governments. They develop and apply a method to separate the effect of policy preferences and of parties' politics on the voting behavior of Länder governments." (author's abstract)

In this paper, I review the literature on the formulation and estimation of dynamic stochastic general equilibrium (DSGE) models with a special emphasis on Bayesian methods. First, I discuss the evolution of DSGE models over the last couple of decades. Second, I explain why the profession has decided to estimate these models using Bayesian methods. Third, I briefly introduce some of the techniques required to compute and estimate these models. Fourth, I illustrate the techniques under consideration by estimating a benchmark DSGE model with real and nominal rigidities. I conclude by offering some pointers for future research.

In dieser Arbeit wird ein statistisches Bayes-Verfahren mit dem Ziel der Fallzahlreduzierung in einer neu geplanten klinischen Studie untersucht. Hierzu wird ein meta-analytisch prädiktiver Bayes-Ansatz angewandt um Ergebnisse aus historischen Studien an Erwachsenen und Kindern zu extrapolieren. Mittels bayesianischer Metaanalysen wird die a-posteriori prädiktive Verteilung eines zukünftigen Studieneffekts aus historischen Daten bestimmt. Diese wird in eine Anzahl Patienten umgerechnet, die in einer neuen Studie eingespart werden können. Im Rahmen der hierarchischen Modelle wird untersucht, welche hyper a-priori Verteilungen für die Interstudienvarianz geeignet sind. Anhand reeller Beispiele wird die Effektivität der Methodik untersucht. Besonders wird die Situation bei Vorliegen von wenigen früheren Studien analysiert. In Simulationen wird die Mindestanzahl historischer Studien bestimmt, ab der die Anwendung dieser Methode bzw. die Extrapolation historischer Resultate sinnvoll ist.

In this paper, I apply three methods to estimate the output gap for Vietnam to support the conduct of monetary policy of the State Bank: the Hodrick-Prescott Filter, the production function approach and Bayesian estimation. I then compare the results obtained from these approaches and discuss their advantages and disadvantages to choose the optimal method for the estimation of the output gap for the State Bank of Vietnam. For the Bayesian approach, my paper closedly relies on the paper of Tim Willems (2011) with some modifications to fit the situation of Vietnam. The output gap estimated by Bayesian method appears to be the most consistent with the economic developments of Vietnam.

Sequential Monte Carlo (SMC) methods are widely used for filtering purposes of non-linear economic or financial models. Nevertheless the SMC scope encompasses wider applications such as estimating static model parameters so much that it is becoming a serious alternative to Markov- Chain Monte-Carlo (MCMC) methods. Not only SMC algorithms draw posterior distributions of static or dynamic parameters but additionally provide an estimate of the normalizing constant. The tempered and time (TNT) algorithm, developed in the paper, combines (off-line) tempered SMC inference with on-line SMC inference for estimating many slightly different distributions. The method encompasses the Iterated Batch Importance Sampling (IBIS) algorithm and more generally the Resample Move (RM) algorithm. Besides the number of particles, the TNT algorithm self-adjusts its calibrated parameters and relies on a new MCMC kernel that allows for particle interactions. The algorithm is well suited for efficiently back-testing models. We conclude by comparing in-sample and out-of-sample performances of complex volatility models.

We use a macro-finance model, incorporating macroeconomic and financial factors, to study the term premium in the U.S. bond market. Estimating the model using Bayesian techniques, we find that a single factor explains most of the variation in bond risk premiums. Furthermore, the model-implied risk premiums account for up to 40% of the variability of one- and two-year excess returns. Using the model to decompose yield spreads into an expectations and a term premium component, we find that, although this decomposition does not seem important to forecast economic activity, it is crucial to forecast inflation for most forecasting horizons.

We propose a method for conducting inference on impulse responses in structural vector autoregressions (SVARs) when the impulse response is not point identified because the number of equality restrictions one can credibly impose is not sufficient for point identification and/or one imposes sign restrictions. We proceed in three steps. We first define the object of interest as the identified set for a given impulse response at a given horizon and discuss how inference is simple when the identified set is convex, as one can limit attention to the set's upper and lower bounds. We then provide easily verifiable conditions on the type of equality and sign restrictions that guarantee convexity. These cover most cases of practical interest, with exceptions including sign restrictions on multiple shocks and equality restrictions that make the impulse response locally, but not globally, identified. Second, we show how to conduct inference on the identified set. We adopt a robust Bayes approach that considers the class of all possible priors for the non-identified aspects of the model and delivers a class of associated posteriors. We summarize the posterior class by reporting the "posterior mean bounds", which can be interpreted as an estimator of the identified set. We also consider a "robustified credible region" which is a measure of the posterior uncertainty about the identified set. The two intervals can be obtained using a computationally convenient numerical procedure. Third, we show that the posterior bounds converge asymptotically to the identified set if the set is convex. If the identified set is not convex, our posterior bounds can be interpreted as an estimator of the convex hull of the identified set. Finally, a useful diagnostic tool delivered by our procedure is the posterior belief about the plausibility of the imposed identifying restrictions.

Frequent problems in applied research preventing the application of the classical Poisson log-linear model for analyzing count data include overdispersion, an excess of zeros compared to the Poisson distribution, correlated responses, as well as complex predictor structures comprising nonlinear effects of continuous covariates, interactions or spatial effects. We propose a general class of Bayesian generalized additive models for zero-inflated and overdispersed count data within the framework of generalized additive models for location, scale, and shape where semiparametric predictors can be specified for several parameters of a count data distribution. As standard options for applied work we consider the zero-inflated Poisson, the negative binomial and the zero-inflated negative binomial distribution. The additive predictor specifications rely on basis function approximations for the different types of effects in combination with Gaussian smoothness priors. We develop Bayesian inference based on Markov chain Monte Carlo simulation techniques where suitable proposal densities are constructed based on iteratively weighted least squares approximations to the full conditionals. To ensure practicability of the inference, we consider theoretical properties like the involved question whether the joint posterior is proper. The proposed approach is evaluated in simulation studies and applied to count data arising from patent citations and claim frequencies in car insurances. For the comparison of models with respect to the distribution, we consider quantile residuals as an effective graphical device and scoring rules that allow us to quantify the predictive ability of the models. The deviance information criterion is used to select appropriate predictor specifications once a response distribution has been chosen. Supplementary materials for this article are available online.

A long tradition suggests a fundamental distinction between situations of risk, where true objective probabilities are known, and unmeasurable uncertainties where no such probabilities are given. This distinction can be captured in a Bayesian model where uncertainty is represented by the agent's subjective belief over the parameter governing future income streams. Whether uncertainty reduces to ordinary risk depends on the agent's ability to smooth consumption. Uncertainty can have a major behavioral and economic impact, including precautionary behavior that may appear overly conservative to an outside observer. We argue that one of the main characteristics of uncertain beliefs is that they are not empirical, in the sense that they cannot be objectively tested to determine whether they are right or wrong. This can confound empirical methods that assume rational expectations.

This paper presents the MATLAB package DeCo (density combination) which is based on the paper by Billio, Casarin, Ravazzolo, and van Dijk (2013) where a constructive Bayesian approach is presented for combining predictive densities originating from different models or other sources of information. The combination weights are time-varying and may depend on past predictive forecasting performances and other learning mechanisms. The core algorithm is the function DeCo which applies banks of parallel Sequential Monte Carlo algorithms to filter the time-varying combination weights. The DeCo procedure has been implemented both for standard CPU computing and for graphical process unit (GPU) parallel computing. For the GPU implementation we use the MATLAB parallel computing toolbox and show how to use general purpose GPU computing almost effortlessly. This GPU implementation provides a speed up of the execution time of up to seventy times on a standard CPU MATLAB implementation on a multicore CPU. We show the use of the package and the computational gain of the GPU version through some simulation experiments and empirical applications.

This paper provides an overview of the panel VAR models used in macroeconomics and finance. It discusses what are their distinctive features, what they are used for, and how they can be derived from economic theory. It also describes how they are estimated and how shock identification is performed, and compares panel VARs to other approaches used in the literature to deal with dynamic models involving heterogeneous units. Finally, it shows how structural time variation can be dealt with and illustrates the challanges that they present to researchers interested in studying cross-unit dynamics interdependences in heterogeneous setups.

Accurate prediction of risk measures such as Value at Risk (VaR) and Expected Shortfall (ES) requires precise estimation of the tail of the predictive distribution. Two novel concepts are introduced that offer a specific focus on this part of the predictive density: the censored posterior, a posterior in which the likelihood is replaced by the censored likelihood; and the censored predictive likelihood, which is used for Bayesian Model Averaging. We perform extensive experiments involving simulated and empirical data. Our results show the ability of these new approaches to outperform the standard posterior and traditional Bayesian Model Averaging techniques in applications of Value-at-Risk prediction in GARCH models.

In biostatistischen Guidelines wird zusätzlich zum Nachweis der statistischen Signifikanz eines Studienergebnisses gefordert, auch den Nachweis der klinischen Relevanz des entsprechenden Effekts zu erbringen. Die klinische Relevanz spielt eine bedeutende Rolle bei der Nutzenbewertung einer Therapie[for full text, please go to the a.m. URL], GMDS 2012; 57. Jahrestagung der Deutschen Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie e.V. (GMDS)

Many governments wish to assess the quality of their universities. A prominent example is the UK's new Research Excellence Framework (REF) 2014. In the REF, peer-review panels will be provided with information on publications and citations. This paper suggests a way in which panels could choose the weights to attach to these two indicators. The analysis draws in an intuitive way on the concept of Bayesian updating (where citations gradually reveal information about the initially imperfectly-observed importance of the research). Our study should not be interpreted as the argument that only mechanistic measures ought to be used in a REF.

Earnings forecasts can be useful for investment decisions. Research on earnings forecasts has focused on forecast performance in relation to firm characteristics, on categorizing the analysts into groups with similar behaviour and on the effect of an earnings announcement by thefirm on future earnings forecasts. In this paper we investigate the factors that determine the value of the forecast and also investigate to what extent the timing of the forecast can be modeled. We propose a novel methodology that allows for such an investigation. As an illustration we analyze within-year earnings forecasts for AMD in the period 1997 to 2011, where the data are obtained from the I/B/E/S database. Our empirical findings suggest clear drivers of the value and the timing of the earnings forecast. We thus show that not only the forecasts themselves are predictable, but that also the timing of the quotes is predictable to some extent.

We propose a Bayesian combination approach for multivariate predictive densities which relies upon a distributional state space representation of the combination weights. Several specifications of multivariate time-varying weights are introduced with a particular focus on weight dynamics driven by the past performance of the predictive densities and the use of learning mechanisms. In the proposed approach the model set can be incomplete, meaning that all models can be individually misspecified. A Sequential Monte Carlo method is proposed to approximate the filtering and predictive densities. The combination approach is assessed using statistical and utility-based performance measures for evaluating density forecasts. Simulation results indicate that, for a set of linear autoregressive models, the combination strategy is successful in selecting, with probability close to one, the true model when the model set is complete and it is able to detect parameter instability when the model set includes the true model that has generated subsamples of data. For the macro series we find that incompleteness of the models is relatively large in the 70's, the beginning of the 80's and during the recent financial crisis, and lower during the Great Moderation. With respect to returns of the S&P 500 series, we find that an investment strategy using a combination of predictions from professional forecasters and from a white noise model puts more weight on the white noise model in the beginning of the 90's and switches to giving more weight to the professional forecasts over time.

Due to their well-known indeterminacies, factor models require identifying assumptions to guarantee unique parameter estimates. For Bayesian estimation, these identifying assumptions are usually implemented by imposing constraints on certain model parameters. This strategy, however, may result in posterior distributions with shapes that depend on the ordering of cross-sections in the data set. We propose an alternative approach, which relies on a sampler without the usual identifying constraints. Identification is reached ex-post based on a Procrustes transformation. Resulting posterior estimates are ordering invariant and show favorable properties with respect to convergence and statistical as well as numerical accuracy.

This paper presents a model of the penalty-kick game between a soccer goalkeeper and a kicker, in which there is uncertainty about the kicker's type (and there are two possible types of kicker). To find a solution for this game we use the concept of Bayesian equilibrium, and we find that, typically, one of the kicker's types will play a mixed strategy while the other type will choose a pure strategy (or, sometimes, a restricted mixed strategy). The model has a simpler version in which the players can only choose between two strategies (right and left), and a more complex version in which they can also choose a third strategy (the center of the goal). Comparing the incomplete-information Bayesian equilibria with the corresponding complete-information Nash equilibria, we find that in all cases the expected scoring probability increases (so that, on average, the goalkeeper is worse off under incomplete information). The three-strategy model is also useful to explain why it could be optimal for a goal keeper never to choose the center of the goal (although at the same time there were some kickers who always chose to shoot to the center).

This paper presents the multiple imputation model for the imputation of the missing values of the Austrian Household Survey on Housing Wealth 2008. It is based on Bayesian inference and on the fully conditional specification approach. Both theoretical framework and model specification are discussed in detail and,finally, some results about the performance of our imputations are presented.

The supposed irrelevance of historical costs for rational decision making has been the subject of much interest in the economic literature. In this paper we explore whether individual decision making under risk is affected by the cost of the supplied information. Outside of the lab, it is difficult to disentangle the effect of the cost of information itself from the effect of self-selection by individuals who tend to gain the most from this information. We thus create an environment in the lab where subjects are offered additional, useful and identical information on the state of the world across treatments. By varying the cost of information we can distinguish between selection and sunk cost effects. We find a systematic effect of sunk costs on the manner in which subjects update their beliefs on the state of the world. Subjects over-weigh costly information relatively to free information, which results in a 'push' of beliefs towards the extremes. This shift does not necessarily lead to behavior more attuned with Bayesian updating.

In this paper we study the drivers of fluctuations in the Irish housing market by developing a dynamic stochastic general equilibrium (DSGE) model of Ireland as a member of the European Monetary Union (EMU). We estimate the model with Bayesian methods using time series for both Ireland and the rest of the EMU for the period from 1997:Q1 to 2008:Q2. We find that housing preference (demand) and technology shocks are the main drivers of fluctuations in house prices and residential investment. Moreover, we find that adding housing collateral does not improve the fit of our model to the data. A standard regression analysis shows that a good part of the variation of housing preference shocks is explained by unmodeled demand factors that have been considered in the empirical literature as important determinants of Irish house prices.

This paper conducts an empirical analysis of the heterogeneity of recessions in monthly U.S. coincident and leading indicator variables. Univariate Markovswitching models indicate that it is appropriate to allow for two distinct recession regimes, corresponding with ‘mild’ and ‘severe’ recessions. All downturns start with a mild decline in the level of economic activity. Contractions that develop into severe recessions mostly correspond with periods of substantial credit squeezes as suggested by the ‘financial accelerator’ theory. Multivariate Markov-switching models that allow for phase shifts between the cyclical regimes of industrial production and the Conference Board Leading Economic Index confirm these findings.

This paper invokes the axiomatic approach to explore the notion of growing awareness in the context of decision making under uncertainty. It introduces a new approach to modeling the expanding universe of a decision maker in the wake of becoming aware of new consequences, new acts, and new links between acts and consequences. New consequences or new acts represent genuine expansions of the decision maker's universe, while the discovery of new links between acts and consequences renders nonnull events that were considered null before the discovery. The expanding universe, or state space, is accompanied by extension of the set of acts. The preference relations over the expanding sets of acts are linked by a new axiom, dubbed act independence, which is motivated by the idea that decision makers have unchanging preferences over the satisfaction of basic needs. The main results are representation theorems and corresponding rules for updating beliefs over expanding state spaces and null events that have the flavor of "reverse Bayesianism".

Dynamic discrete choice models usually require a general specification of unobserved heterogeneity. In this paper, we apply Bayesian procedures as a numerical tool for the estimation of a female labor supply model based on a sample size which is typical for common household panels. We provide two important results for the practitioner: First, for a specification with a multivariate normal distribution for the unobserved heterogeneity, the Bayesian MCMC estimator yields almost identical results as a classical Maximum Simulated Likelihood (MSL) estimator. Second, we show that when imposing distributional assumptions which are consistent with economic theory, e.g. log-normally distributed consumption preferences, the Bayesian method performs well and provides reasonable estimates, while the MSL estimator does not converge. These results indicate that Bayesian procedures can be a beneficial tool for the estimation of dynamic discrete choice models.

We estimate and compare two models, the Generalized Taylor Economy (GTE) and the Multiple Calvo model (MC); that have been built to model the distributions of contract lengths observed in the data. We compare the performances of these models to those of the standard models such as the Calvo and its popular variant, using the ad hoc device of indexation. The estimations are made with Bayesian techniques for the US data. The results indicate that the data strongly favour the GTE.

We discuss Bayesian inferential procedures within the family of instrumental variables regression models and focus on two issues: existence conditions for posterior moments of the parameters of interest under a flat prior and the potential of Direct Monte Carlo (DMC) approaches for efficient evaluation of such possibly highly onelliptical posteriors. We show that, for the general case of m endogenous variables under a flat prior, posterior moments of order r exist for the coefficients reflecting the endogenous regressors’ effect on the dependent variable, if the number of instruments is greater than m+r, even though there is an issue of local non-identification that causes non-elliptical shapes of the posterior. This stresses the need for efficient Monte Carlo integration methods. We introduce an extension of DMC that incorporates an acceptance-rejection sampling step within DMC. This Acceptance-Rejection within Direct Monte Carlo (ARDMC) method has the attractive property that the generated random drawings are independent, which greatly helps the fast convergence of simulation results, and which facilitates the evaluation of the numerical accuracy. The speed of ARDMC can be easily further improved by making use of parallelized computation using multiple core machines or computer clusters. We note that ARDMC is an analogue to the well-known 'Metropolis-Hastings within Gibbs' sampling in the sense that one 'more difficult' step is used within an 'easier' simulation method. We compare the ARDMC approach with the Gibbs sampler using simulated data and two empirical data sets, involving the settler mortality instrument of Acemoglu et al. (2001) and father's education's instrument used by Hoogerheide et al. (2012a). Even without making use of parallelized computation, an efficiency gain is observed both under strong and weak instruments, where the gain can be enormous in the latter case.

We consider a standard social choice environment with linear utilities and independent, one-dimensional, private values. We provide a short and constructive proof that for any Bayesian incentive compatible mechanism there exists an equivalent dominant strategy incentive compatible mechanism that delivers the same interim expected utilities for all agents. We demonstrate the usefulness and applicability of our approach with several examples. Finally, we show that the equivalence between Bayesian and dominant strategy implementation breaks down when utilities are non-linear or when values are interdependent, multi-dimensional, or correlated.

We analyze the behavior of experts who quote forecasts for monthly SKU-level sales data where we compare data before and after the moment that experts received different kinds of feedback on their behavior. We have data for 21 experts located in as many countries who make SKU-level forecasts for a variety of pharmaceutical products for October 2006 to September 2007. We study the behavior of the experts by comparing their forecasts with those from an automated statistical program, and we report the forecast accuracy over these 12 months. In September 2007 these experts were given feedback on their behavior and they received a training at the headquarters' office, where specific attention was given to the ins and outs of the statistical program. Next, we study the behavior of the experts for the 3 months after the training session, that is, October 2007 to December 2007. Our main conclusion is that in the second period the experts' forecasts deviated lesser from the statistical forecasts and that their accuracy improved substantially.

Divergent priors are improper when defined on unbounded supports. Bartlett's paradox has been taken to imply that using improper priors results in ill-defined Bayes factors, preventing model comparison by posterior probabilities. However many improper priors have attractive properties that econometricians may wish to access and at the same time conduct model comparison. We present a method of computing well defined Bayes factors with divergent priors by setting rules on the rate of diffusion of prior certainty. The method is exact; no approximations are used. As a further result, we demonstrate that exceptions to Bartlett's paradox exist. That is, we show it is possible to construct improper priors that result in well defined Bayes factors. One important improper prior, the Shrinkage prior due to Stein (1956), is one such example. This example highlights pathologies with the resulting Bayes factors in such cases, and a simple solution is presented to this problem. A simple Monte Carlo experiment demonstrates the applicability of the approach developed in this paper.

This paper introduces inventories in an otherwise standard Dynamic Stochastic General Equilibrium Model (DSGE) of the business cycle. Firms accumulate inventories to facilitate sales, but face a cost of doing so in terms of costly storage of intermediate goods. The paper's main contribution is to present a DSGE model with inventories that is estimated using Bayesian methods. Based on US data we show that accounting for inventory dynamics has a significant impact on parameter estimates and impulse responses. Our analysis also reveals that the contribution of structural shocks to variations in the observable variables changes significantly when we allow for inventories. Moreover, we find that inventories enter the Phillips curve as an additional and significant driving variable of inflation and make the inflation process less backward-looking.

Regression analyses of cross-country economic growth data are complicated by two main forms of model uncertainty: the uncertainty in selecting explanatory variables and the uncertainty in specifying the functional form of the regression function. Most discussions in the literature address these problems independently, yet a joint treatment is essential. We perform this joint treatment by extending the linear model to allow for multiple-regime parameter heterogeneity of the type suggested by new growth theory, while addressing the variable selection problem by means of Bayesian model averaging. Controlling for variable selection uncertainty, we confirm the evidence in favor of new growth theory presented in several earlier studies. However, controlling for functional form uncertainty, we find that the effects of many of the explanatory variables identified in the literature are not robust across countries and variable selections.

This paper investigates the robustness of determinants of economic growth in the presence of model uncertainty, parameter heterogeneity and outliers. The robust model averaging approach introduced in the paper uses a flexible and parsimonious mixture modeling that allows for fat-tailed errors compared to the normal benchmark case. Applying robust model averaging to growth determinants, the paper finds that eight out of eighteen variables found to be significantly related to economic growth by Sala-i-Martin et al. (2004) are sensitive to deviations from benchmark model averaging. For example, the GDP shares of mining or government consumption, are no longer robust or economically significant once deviations from the normal benchmark assumptions are allowed. The paper identifies outlying observations - most notably Botswana - in explaining economic growth in a cross-section of countries.

Experts can rely on statistical model forecasts when creating their own forecasts. Usually it is not known what experts actually do. In this paper we focus on three questions, which we try to answer given the availability of expert forecasts and model forecasts. First, is the expert forecast related to the model forecast and how? Second, how is this potential relation influenced by other factors? Third, how does this relation influence forecast accuracy? We propose a new and innovative two-level Hierarchical Bayes model to answer these questions. We apply our proposed methodology to a large data set of forecasts and realizations of SKU-level sales data from a pharmaceutical company. We find that expert forecasts can depend on model forecasts in a variety of ways. Average sales levels, sales volatility, and the forecast horizon influence this dependence. We also demonstrate that theoretical implications of expert behavior on forecast accuracy are reflected in the empirical data.

During the Great Recession following the recent financial crisis large fiscal stimuli were implemented to counteract labor market sclerosis. We explore the effectiveness of various fiscal packages in a matching model featuring inefficient unemployment and a rich fiscal sector employing distortionary taxation and government debt. Results show that only stimuli directed toward the labor market, such as hiring subsidies, deliver large multipliers. Those policies can, indeed, abate the congestion externality, pervasive in the labor market. Various robustness checks confirm the results. The results obtained in the calibrated model are also confirmed through Bayesian estimation.

Exchange market pressure (EMP) measures the pressure on a currency to depreciate. It adds to the actual depreciation a weighted combination of policy instruments used to ward off depreciation, such as interest rates and foreign exchange interventions, where the weights are their effectiveness. The key difficulty in the literature is how to identify these weights. We exploit the persistence of pressure and add instruments based on currency crisis theories to identify the weights, and we propose a simple IV regression to estimate them. An application to the European Monetary System crisis in 1992-1993 shows that a one percentage point higher interest rate wards off a depreciation of about 0.2 percent.

This paper examines which macroeconomic and financial variables are most informative for the federal funds target rate decisions made by the Federal Open Market Committee (FOMC) from a forecasting perspective. The analysis is conducted for the FOMC decision during the period January 1990 - June 2008, using dynamic ordered probit models with a Bayesian endogenous variable selection methodology and real-time data for a set of 33 candidate predictor variables. We find that indicators of economic activity and forward-looking term structure variables as well as survey measures have most predictive ability. For the full sample period, in-sample probability forecasts achieve a hitrate of 90 percent. Based on out-of-sample forecasts for the period January 2001 - June 2008, 82 percent of the FOMC decisions are predicted correctly.

We present a statistical investigation on the domain of sex-related homicides. As general sociological and psychological theory on this specific type of crime is incomplete or even lacking, a data-driven approach is implemented. In detail, graphical modelling is applied to learn the dependency structure and several structure learning algorithms are combined to yield a skeleton corresponding to distinct Bayesian Networks. This graph is subsequently analysed and presents a distinction between an offender and a situation driven crime.

This paper analyzes the empirical performance of two alternative ways in which multi-factor models with time-varying risk exposures and premia may be estimated. The first method echoes the seminal two-pass approach advocated by Fama and MacBeth (1973). The second approach is based on a Bayesian approach to modelling the latent process followed by risk exposures and idiosynchratic volatility. Our application to monthly, 1979-2008 U.S. data for stock, bond, and publicly traded real estate returns shows that the classical, two-stage approach that relies on a nonparametric, rolling window modelling of time-varying betas yields results that are unreasonable. There is evidence that all the portfolios of stocks, bonds, and REITs have been grossly over-priced. On the contrary, the Bayesian approach yields sensible results as most portfolios do not appear to have been misspriced and a few risk premia are precisely estimated with a plausible sign. Real consumption growth risk turns out to be the only factor that is persistently priced throughout the sample.

Many decision problems in various fields of application can be characterized as diagnostic problems trying to assess the true state (of the world) of given cases. The investigation of assessment criteria improves the initial information according to observed signal outcomes, which are related to the possible states. Such sequential investigation processes can be analyzed within the framework of statistical decision theory, in which prior probability distributions of classes of cases are updated, allowing for a sorting of particular cases into ever smaller subclasses. However, receiving such information causes investigation costs. Besides the question about the set of relevant criteria, this defines two additional problems of statistical decision problems: the optimal stopping of investigations and the optimal sequence of investigating a given set of criteria. Unfortunately, no solution exists with which the optimal sequence can generally be determined. Therefore, the paper characterizes the associated problems and analyzes existing heuristics trying to approximate an optimal solution.

In der frequentistischen Statistik spielen Testprobleme und deren Lösung mit Hilfe von Signifikanztests eine zentrale Rolle. Die Bayes-Statistik wird dagegen üblicherweise weniger zur Lösung von Testproblemen eingesetzt, sondern ihre vorrangigen Anwendungsmöglichkeiten eher in der[for full text, please go to the a.m. URL], Mainz//2011; 56. Jahrestagung der Deutschen Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie (gmds), 6. Jahrestagung der Deutschen Gesellschaft für Epidemiologie (DGEpi)