Anastasios Panagiotelis

Pair Copula Constructions for Multivariate Discrete Data

Multivariate discrete response data can be found in diverse fields, including econometrics, finance, biometrics, and psychometrics. Our contribution, through this study, is to introduce a new class of models for multivariate discrete data based on pair copula constructions (PCCs) that has two major advantages. First, by deriving the conditions under which any multivariate discrete distribution can be decomposed as a PCC, we show that discrete PCCs attain highly flexible dependence structures. Second, the computational burden of evaluating the likelihood for an m-dimensional discrete PCC only grows quadratically with m. This compares favorably to existing models for which computing the likelihood either requires the evaluation of 2 m terms or slow numerical integration methods. We demonstrate the high quality of inference function for margins and maximum likelihood estimates, both under a simulated setting and for an application to a longitudinal discrete dataset on headache severity. This article has online supplementary material.

Bayesian skew selection for multivariate models

We develop a Bayesian approach for the selection of skew in multivariate skew t distributions constructed through hidden conditioning in the manners suggested by either Azzalini and Capitanio (2003) or Sahu et al. (2003). We show that the skew coefficients for each margin are the same for the standardized versions of both distributions. We introduce binary indicators to denote whether there is symmetry, or skew, in each dimension. We adopt a proper beta prior on each non-zero skew coefficient, and derive the corresponding prior on the skew parameters. In both distributions we show that as the degrees of freedom increases, the prior smoothly bounds the non-zero skew parameters away from zero and identifies the posterior. We estimate the model using Markov chain Monte Carlo (MCMC) methods by exploiting the conditionally Gaussian representation of the skew t distributions. This allows for the search through the posterior space of all possible combinations of skew and symmetry in each dimension. We show that the proposed method works well in a simulation setting, and employ it in two multivariate econometric examples. The first involves the modeling of foreign exchange rates and the second is a vector autoregression for intra-day electricity spot prices. The approach selects skew along the original coordinates of the data, which proves insightful in both examples.

Model selection for discrete regular vine copulas

Discrete vine copulas provide a flexible modeling framework for high-dimensional data and have significant computational advantages over competing methods. A vine-based multivariate probability mass function is constructed from bivariate copula building blocks and univariate marginal distributions. However, even for a moderate number of variables, the number of alternative vine decompositions is very large and additionally there is a large set of candidate bivariate copula families that can be used as building blocks in any given decomposition. Together, these two issues ensure that it is infeasible to evaluate all possible vine copula models. Instead, two greedy algorithms for automatically selecting vine structures and component pair-copula building blocks are introduced. The algorithms are tested in a simulation study that is itself driven by real world data from online retail. Both algorithms select vines that provide accurate estimates of the joint probabilities. Using three different f-divergences as criteria, the proposed algorithms outperform a Gaussian copula benchmark, especially for data with high dependence. Finally, the selection algorithm is applied to data from the General Social Survey and outperforms a Gaussian copula benchmark using both in-sample and out-of-sample criteria.

From Amazon to Apple: Modeling Online Retail Sales, Purchase Incidence and Visit Behavior

In this study, we propose a multivariate stochastic model for Web site visit duration, page views, purchase incidence, and the sale amount for online retailers. The model is constructed by composition from carefully selected distributions and involves copula components. It allows for the strong nonlinear relationships between the sales and visit variables to be explored in detail, and can be used to construct sales predictions. The model is readily estimated using maximum likelihood, making it an attractive choice in practice given the large sample sizes that are commonplace in online retail studies. We examine a number of top-ranked U.S. online retailers, and find that the visit duration and the number of pages viewed are both related to sales, but in very different ways for different products. Using Bayesian methodology, we show how the model can be extended to a finite mixture model to account for consumer heterogeneity via latent household segmentation. The model can also be adjusted to accommodate a more accurate analysis of online retailers like apple.com that sell products at a very limited number of price points. In a validation study across a range of different Web sites, we find that the purchase incidence and sales amount are both forecast more accurately using our model, when compared to regression, probit regression, a popular data-mining method, and a survival model employed previously in an online retail study. Supplementary materials for this article are available online.

Bayesian Inference for the One-Factor Copula Model

ABSTRACT We develop efficient Bayesian inference for the one-factor copula model with two significant contributions over existing methodologies. First, our approach leads to straightforward inference on dependence parameters and the latent factor; only inference on the former is available under frequentist alternatives. Second, we develop a reversible jump Markov chain Monte Carlo algorithm that averages over models constructed from different bivariate copula building blocks. Our approach accommodates any combination of discrete and continuous margins. Through extensive simulations, we compare the computational and Monte Carlo efficiency of alternative proposed sampling schemes. The preferred algorithm provides reliable inference on parameters, the latent factor, and model space. The potential of the methodology is highlighted in an empirical study of 10 binary measures of socio-economic deprivation collected for 11,463 East Timorese households. The importance of conducting inference on the latent factor is motivated by constructing a poverty index using estimates of the factor. Compared to a linear Gaussian factor model, our model average improves out-of-sample fit. The relationships between the poverty index and observed variables uncovered by our approach are diverse and allow for a richer and more precise understanding of the dependence between overall deprivation and individual measures of well-being.

When Did It Go Wrong? The Case of Greek Sovereign Debt

This chapter analyses the fiscal stance of the Greek public sector over the period 2001–2016. It distinguishes between three periods: 2001–2006, during which the Greek economy attained much larger growth rates than most EU countries but despite that the general government primary deficit was on average about 2 percentage points higher than the EU-28 average; 2007–2009, during which the primary fiscal deficit soared, reaching a record value of 10.1% in 2009; finally, 2010–2016, during which the Greek economy entered a long phase of fiscal consolidation and by 2014 the fiscal budget even experienced a small primary surplus. What factors contributed to more-than-average (relative to the EU countries) fiscal imbalances during the first phase, in spite of high economic growth? Was the 2009 fiscal deficit revenue or expenditure driven? How was fiscal consolidation achieved during the last phase? What implications does this bear for future economic growth rate and the ability of Greece to pay back its debt? The chapter concludes by providing some recommendations for future fiscal policy making and the way ahead.

Bayesian Rank Selection in Multivariate Regression

Estimating the rank of the coefficient matrix is a major challenge in multivariate regression, including vector autoregression (VAR). In this paper, we develop a novel fully Bayesian approach that allows for rank estimation. The key to our approach is reparameterizing the coefficient matrix using its singular value decomposition and conducting Bayesian inference on the decomposed parameters. By implementing a stochastic search variable selection on the singular values of the coefficient matrix, the ultimate selected rank can be identified as the number of nonzero singular values. Our approach is appropriate for small multivariate regressions as well as for higher dimensional models with up to about 40 predictors. In macroeconomic forecasting using VARs, the advantages of shrinkage through proper Bayesian priors are well documented. Consequently, the shrinkage approach proposed here that selects or averages over low rank coefficient matrices is evaluated in a forecasting environment. We show in both simulations and empirical studies that our Bayesian approach provides forecasts that are better than those of the most promising benchmark methods, dynamic factor models and factor augmented VARs.