The value of multivariate model sophistication: An application to pricing Dow Jones Industrial Average options

We assess the predictive accuracies of a large number of multivariate volatility models in terms of pricing options on the Dow Jones Industrial Average. We measure the value of model sophistication in terms of dollar losses by considering a set of 444 multivariate models that differ in their specification of the conditional variance, conditional correlation, innovation distribution, and estimation approach. All of the models belong to the dynamic conditional correlation class, which is particularly suitable because it allows consistent estimations of the risk neutral dynamics with a manageable amount of computational effort for relatively large scale problems. It turns out that increasing the sophistication in the marginal variance processes (i.e., nonlinearity, asymmetry and component structure) leads to important gains in pricing accuracy. Enriching the model with more complex existing correlation specifications does not improve the performance significantly. Estimating the standard dynamic conditional correlation model by composite likelihood, in order to take into account potential biases in the parameter estimates, generates only slightly better results. To enhance this poor performance of correlation models, we propose a new model that allows for correlation spillovers without too many parameters. This model performs about 60% better than the existing correlation models we consider. Relaxing a Gaussian innovation for a Laplace innovation assumption improves the pricing in a more minor way. In addition to investigating the value of model sophistication in terms of dollar losses directly, we also use the model confidence set approach to statistically infer the set of models that delivers the best pricing performances.     

An application of a spatially distributed queuing model to an ambulance system

An application of a spatially distributed queuing model to an ambulance system is presented. The purpose of this research was to assess the usefulness of a variation of the “hypercube” queuing model developed specifically for modeling an ambulance system. The model was applied to the emergency medical system of Greenville County, South Carolina using historical data. Results indicate that the model provides reasonably accurate estimates of system performance measures when the input parameters can be accurately specified.     

The comparative forecast performance of univariate and multivariate models: an application to real interest rate forecasting

Does the use of information on the past history of the nominal interest rates and inflation entail improvement in forecasts of the ex ante real interest rate over its forecasts obtained from using just the past history of the realized real interest rates? To answer this question we set up a univariate unobserved components model for the realized real interest rates and a bivariate model for the nominal rate and inflation which imposes cointegration restrictions between them. The two models are estimated under normality with the Kalman filter. It is found that the error-correction model provides more accurate one-period ahead forecasts of the real rate within the estimation sample whereas the unobserved components model yields forecasts with smaller forecast variances. In the post-sample period, the forecasts from the bivariate model are not only more accurate but also have tighter confidence bounds than the forecasts from the unobserved components model.     

Model comparison of coordinate-free multivariate skewed distributions with an application to stochastic frontiers

We consider classes of multivariate distributions which can model skewness and are closed under orthogonal transformations. We review two classes of such distributions proposed in the literature and focus our attention on a particular, yet quite flexible, subclass of one of these classes. Members of this subclass are defined by affine transformations of univariate (skewed) distributions that ensure the existence of a set of coordinate axes along which there is independence and the marginals are known analytically. The choice of an appropriate m-dimensional skewed distribution is then restricted to the simpler problem of choosing m univariate skewed distributions. We introduce a Bayesian model comparison setup for selection of these univariate skewed distributions. The analysis does not rely on the existence of moments (allowing for any tail behaviour) and uses equivalent priors on the common characteristics of the different models. Finally, we apply this framework to multi-output stochastic frontiers using data from Dutch dairy farms.     

Comparative analysis of labor market dynamics using Markov processes: An application to informality

This paper discusses a set of statistics for examining labor market dynamics in developing countries and offers a simple search model that informs their interpretation. It then employs panel data from Argentina, Brazil and Mexico to generate a set of preliminary stylized facts about patterns of sectoral transition and duration. Finally, it nests two competing views of the informal sector within the model and uses variation in the statistics across age and the business cycle to help discriminate between them. The results suggest that a substantial part of the informal sector, particularly the self-employed, corresponds to voluntary entry, although informal salaried work may correspond more closely to the standard queuing view, especially for younger workers.     

Assessing inherent model bias: An application to native displacement in response to immigration

There is a long-standing debate among academics about the effect of immigration on native internal migration decisions. If immigrants displace natives this may indicate a direct cost of immigration in the form of decreased employment opportunity for native workers. Moreover, displacement would also imply that cross-region analyses of wage effects systematically underestimate the consequences of immigration. The widespread use of such area studies for the US and other countries makes it especially important to know whether a native internal response to immigration truly occurs. This paper introduces a microsimulation methodology to test for inherent bias in regression models that have been used in the literature. We show that some specifications have built biases into their models, thereby casting doubt on the validity of their results. We then provide a brief empirical analysis with a panel of observed US state-by-skill data. Together, our evidence argues against the existence of native displacement. This implies that cross-region analyses of immigration’s effect on wages are still informative.     

Innovation alignment and project network dynamics: An integrative model for change

Innovation research has predominantly focused on hierarchically organized firms competing within single markets. Recently, however, researchers have debated over whether the increasing use of project networks within and across industries promotes or stifles innovation. This paper discusses a model based on crossnational diffusion data from three technological innovations in three‐dimensional computer‐aided design (3D CAD) and related implementation data from 82 firms. From the data we induce a set of constructs that form the basis of a two‐stage model for understanding innovation in project networks. In the first stage of the model the alignment of an innovation to the existing allocation of work in a project network is ascertained. In the second stage, the implementation success and diffusion outcomes for innovations misaligned with the allocation of work are governed by the relational stability, accrual of interests, boundary permeability, and existence of an agent for project network change. In developing this integrative, two‐stage model we resolve the contradiction in the academic literature regarding the degree to which project network dynamics can promote or stifle innovation.     

A model of intraurban employment location: An application to Bogota, Colombia

A micro model is formulated to study the location behavior of manufacturing firms in urban areas. A bid-rent function is derived from the profit function and captures the firms' locational equilibrium situations. The theoretical model is extended to a multinomial logit specification and estimated using establishment survey results for Bogota, Colombia. The survey included information on (1) attributes of the establishment such as plant space, and (2) attributes of the plant site such as access to markets. The estimated model is capable of predicting the location choices of different types of firms.     

An empirical model of transfers within a federation, with an application to the European Union

We construct a stylized model of transfers within a federation and apply it to the European Union. Our approach differs from that of most of the existing literature in that we fix the preferences for redistribution of resources among a federation's members, rather than fix the current budgetary rules or modify them on the basis of assumed scenarios. The model is tested (successfully) by assessing its ability to predict the effects of the last (1995) enlargement on the European budget. We then use the estimated model to predict the reallocation of the Union's net transfers after the upcoming Eastern enlargement. Our estimates of transfers to the incoming member states exceed those of the rest of the literature. Our results can be interpreted in one of two ways: first, either the European Union, in its collective decision-making process (that in the future will include the five incoming countries as voting members), will institute new rules and programs to further reduce the regional disparities in income, or second, if the current rules and programs are maintained, then the Eastern enlargement would result in a reduction in the “depth” of the Union. The approach we introduce can be more generally applied to the analysis of other intergovernmental or international organizations.     

A Bayesian approach to bandwidth selection for multivariate kernel regression with an application to state-price density estimation

This paper presents a Bayesian approach to bandwidth selection for multivariate kernel regression. A Monte Carlo study shows that under the average squared error criterion, the Bayesian bandwidth selector is comparable to the cross-validation method and clearly outperforms the bootstrapping and rule-of-thumb bandwidth selectors. The Bayesian bandwidth selector is applied to a multivariate kernel regression model that is often used to estimate the state-price density of Arrow–Debreu securities with the S&P 500 index options data and the DAX index options data. The proposed Bayesian bandwidth selector represents a data-driven solution to the problem of choosing bandwidths for the multivariate kernel regression involved in the nonparametric estimation of the state-price density pioneered by Aït-Sahalia and Lo [Aït-Sahalia, Y., Lo, A.W., 1998. Nonparametric estimation of state-price densities implicit in financial asset prices. The Journal of Finance, 53, 499, 547.]     

An integer linear programming model of staff retention and termination based on multiattribute utility theory.

An integer linear programming formulation was used to model several staffing alternatives available to the director of a recreation therapy department. The utility function of the decision maker was assessed using two attributes of effectiveness: performance and experience. Two utility approximations were obtained for each staff member based upon the average performance rating and number of years of experience both as a recreation therapist and at the facility. The utility obtained was viewed as a proxy for, and a comparative measure of, effectiveness, which considers the criteria of training and experience. The individuals who comprise the most effective combination of therapists, given staff reductions, were obtained by maximizing the sum of staff values. The first constraint set involved a budgetary constraint, coverage constraints, and an EEOC policy restriction. The coverage restriction and the budget were varied to reflect changes in the department resources. The model was validated with the department supervisor for the case of a one-position, 10% budget decrease.     

Small samples and collateral information: An application of the hyperparameter model

When time-series and cross-section data are available for estimating a linear relationship, the data may be pooled using a number of frameworks of varying degrees of restrictiveness. One possible framework which appears not to have been exploited in previous applied econometric work, but which may have some merit especially when the number of observations in the time-series or cross-section dimension is not very large, is the hyperparameter model of Lindley-Smith (1972). Under appropriate conditions the use of this framework enables one to obtain ‘improved’ Bayesian point estimates which yield predictions with smaller mean-square-error than those from ordinary least squares. The paper uses the hyperparameter framework to estimate a Cobb-Douglas production function using U.K. cross-sectional data. A cross-validation exercise is carried out to see how much of the potential of the Bayesian method is realised in practice.     

Election outcomes and economic conditions: An application of a logit model

In this paper the author examines the impact of macroeconomic conditions on the probability of the incumbent party winning a gubernatorial election. Using a sample of 265 gubernatorial elections held during the 1970–1988 period, the findings of this study indicate that the incumbent party’s probability of victory is not significantly affected by either state or national macroeconomic conditions. The author also finds that neither the unemployment rate nor per capita income growth affect the incumbent party’s probability of winning an election.     

Combining forecasts: An application to elections

We summarize the literature on the effectiveness of combining forecasts by assessing the conditions under which combining is most valuable. Using data on the six US presidential elections from 1992 to 2012, we report the reductions in error obtained by averaging forecasts within and across four election forecasting methods: poll projections, expert judgment, quantitative models, and the Iowa Electronic Markets. Across the six elections, the resulting combined forecasts were more accurate than any individual component method, on average. The gains in accuracy from combining increased with the numbers of forecasts used, especially when these forecasts were based on different methods and different data, and in situations involving high levels of uncertainty. Such combining yielded error reductions of between 16% and 59%, compared to the average errors of the individual forecasts. This improvement is substantially greater than the 12% reduction in error that had been reported previously for combining forecasts.     

Relational consumption and nonlinear dynamics in an overlapping generations model

In this paper, we show that incorporating the relational dimension into an otherwise standard OLG model and focusing on dynamic leisure externalities leads to dramatically different predictions. Here, we show that when the old perceive private and relational consumption as substitutable goods, a series of interesting dynamic outcomes—such as local indeterminacy, nonlinear phenomena (including chaotic dynamics) and even multiple equilibria with global indeterminacy—may arise. We also draw some welfare implications and relate them to the well-known “happiness paradox” arising within contemporary affluent societies.     

Adaptive learning and distributional dynamics in an incomplete markets model

Recent research shows that several DSGE models provide a closer fit to the data under adaptive learning. This paper extends this research by introducing adaptive learning in the model of Krusell and Smith (1998) with uninsurable idiosyncratic risks and aggregate uncertainty. A first contribution of this paper establishes that the equilibrium of this framework is stable under least-squares learning. The second contribution consists of showing that bounded rationality enhances the ability of this model to match the distribution of income in the US. Learning increases significantly the Gini coefficients because of the opposite effects on consumption of the capital-rich and of the capital-poor agent. The third contribution is an empirical exercise that shows that learning can account for increases in the income Gini coefficient of up to 25% in a period of 28 years. Overall, these findings suggest that adaptive learning has important distributional repercussions in this class of models.