Understanding multi-asset factor models: Factor exposure interpretation

Field lab: Business project

Specification and testing of multiplicative time-varying GARCH models with applications

In this article, we develop a specification technique for building multiplicative time-varying GARCH models of Amado and Teräsvirta (2008, 2013). The variance is decomposed into an unconditional and a conditional component such that the unconditional variance component is allowed to evolve smoothly over time. This nonstationary component is defined as a linear combination of logistic transition functions with time as the transition variable. The appropriate number of transition functions is determined by a sequence of specification tests. For that purpose, a coherent modelling strategy based on statistical inference is presented. It is heavily dependent on Lagrange multiplier type misspecification tests. The tests are easily implemented as they are entirely based on auxiliary regressions. Finite-sample properties of the strategy and tests are examined by simulation. The modelling strategy is illustrated in practice with two real examples: an empirical application to daily exchange rate returns and another one to daily coffee futures returns.

Experimental design for mixed models with application to population pharmacokinetic studies

experimental design, mixed model, random coefficient regression model, population pharmacokinetics, approximate design

Well-posedness and invariant measures for HJM models with deterministic volatility and Lévy noise

We give sufficient conditions for existence, uniqueness and ergodicity of invariant measures for Musiela's stochastic partial differential equation with deterministic volatility and a Hilbert space valued driving Lévy noise. Conditions for the absence of arbitrage and for the existence of mild solutions are also discussed.

Factors associated with latent tuberculosis among asylum seekers in Switzerland: a cross-sectional study in Vaud County.

BACKGROUND: Screening and treatment of latent tuberculosis infection (LTBI) in asylum seekers (AS) may prevent future cases of tuberculosis. As the screening with Interferon Gamma Release Assay (IGRA) is costly, the objective of this study was to assess which factors were associated with LTBI and to define a score allowing the selection of AS with the highest risk of LTBI. METHODS: In across-sectional study, AS seekers recently arrived in Vaud County, after screening for tuberculosis at the border were offered screening for LTBI with T-SPOT.TB and questionnaire on potentially risk factors. The factors associated with LTBI were analyzed by univariate and multivariate regression. RESULTS: Among 393 adult AS, 98 (24.93%) had a positive IGRA response, five of them with active tuberculosis previously undetected. Six factors associated with LTBI were identified in multivariate analysis: origin, travel conditions, marital status, cough, age and prior TB exposure. Their combination leads to a robust LTBI predictive score. CONCLUSIONS: The prevalence of LTBI and active tuberculosis in AS is high. A predictive score integrating six factors could identify the asylum seekers with the highest risk for LTBI.

The Estimation of Technical Efficiency Effects Models with an Example Applied to the Thai Manufacturing Sector

This paper does two things. First, it presents alternative approaches to the standard methods of estimating productive efficiency using a production function. It favours a parametric approach (viz. the stochastic production frontier approach) over a nonparametric approach (e.g. data envelopment analysis); and, further, one that provides a statistical explanation of efficiency, as well as an estimate of its magnitude. Second, it illustrates the favoured approach (i.e. the ‘single stage procedure’) with estimates of two models of explained inefficiency, using data from the Thai manufacturing sector, after the crisis of 1997. Technical efficiency is modelled as being dependent on capital investment in three major areas (viz. land, machinery and office appliances) where land is intended to proxy the effects of unproductive, speculative capital investment; and both machinery and office appliances are intended to proxy the effects of productive, non-speculative capital investment. The estimates from these models cast new light on the five-year long, post-1997 crisis period in Thailand, suggesting a structural shift from relatively labour intensive to relatively capital intensive production in manufactures from 1998 to 2002.

Stochastic Search Variable Selection in Vector Error Correction Models with an Application to a Model of the UK Macroeconomy

This paper develops methods for Stochastic Search Variable Selection (currently popular with regression and Vector Autoregressive models) for Vector Error Correction models where there are many possible restrictions on the cointegration space. We show how this allows the researcher to begin with a single unrestricted model and either do model selection or model averaging in an automatic and computationally efficient manner. We apply our methods to a large UK macroeconomic model.

What Belongs Where? Variable Selection for Zero-Inflated Count Models with an Application to the Demand for Health Care

This paper develops stochastic search variable selection (SSVS) for zero-inflated count models which are commonly used in health economics. This allows for either model averaging or model selection in situations with many potential regressors. The proposed techniques are applied to a data set from Germany considering the demand for health care. A package for the free statistical software environment R is provided.

Official Central Bank Interventions in the Foreign Exchange Markets: A DCC Approach with Exogenous Variables

This paper assesses the impact of official central bank interventions (CBIs) on exchange rate returns, their volatility and bilateral correlations. By exploiting the recent publication of intervention data by the Bank of England, this study is able to investigate fficial interventions by a total number of four central banks, while the previous studies have been limited to three (the Federal Reserve, Bundesbank and Bank of Japan). The results of the existing literature are reappraised and refined. In particular, unilateral CBI is found to be more successful than coordinated CBI. The likely implications of these findings are then discussed.

Spatial Interactions in Hedonic Pricing Models: The Urban Housing Market of Aveiro, Portugal

Spatial heterogeneity, spatial dependence and spatial scale constitute key features of spatial analysis of housing markets. However, the common practice of modelling spatial dependence as being generated by spatial interactions through a known spatial weights matrix is often not satisfactory. While existing estimators of spatial weights matrices are based on repeat sales or panel data, this paper takes this approach to a cross-section setting. Specifically, based on an a priori definition of housing submarkets and the assumption of a multifactor model, we develop maximum likelihood methodology to estimate hedonic models that facilitate understanding of both spatial heterogeneity and spatial interactions. The methodology, based on statistical orthogonal factor analysis, is applied to the urban housing market of Aveiro, Portugal at two different spatial scales.

Stability of Growth Models with Generalised Lag Structures

This paper considers the lag structures of dynamic models in economics, arguing that the standard approach is too simple to capture the complexity of actual lag structures arising, for example, from production and investment decisions. It is argued that recent (1990s) developments in the the theory of functional differential equations provide a means to analyse models with generalised lag structures. The stability and asymptotic stability of two growth models with generalised lag structures are analysed. The paper concludes with some speculative discussion of time-varying parameters.

Mixture of bivariate Poisson regression models with an application to insurance

In a recent paper Bermúdez [2009] used bivariate Poisson regression models for ratemaking in car insurance, and included zero-inflated models to account for the excess of zeros and the overdispersion in the data set. In the present paper, we revisit this model in order to consider alternatives. We propose a 2-finite mixture of bivariate Poisson regression models to demonstrate that the overdispersion in the data requires more structure if it is to be taken into account, and that a simple zero-inflated bivariate Poisson model does not suffice. At the same time, we show that a finite mixture of bivariate Poisson regression models embraces zero-inflated bivariate Poisson regression models as a special case. Additionally, we describe a model in which the mixing proportions are dependent on covariates when modelling the way in which each individual belongs to a separate cluster. Finally, an EM algorithm is provided in order to ensure the models’ ease-of-fit. These models are applied to the same automobile insurance claims data set as used in Bermúdez [2009] and it is shown that the modelling of the data set can be improved considerably.

Association of Lutzomyia longipalpis (Diptera: Psychodidae) population density with climate variables in Montes Claros, an area of American visceral leishmaniasis transmission in the state of Minas Gerais, Brazil

In the present paper, we evaluate the relationship between climate variables and population density of Lutzomyia longipalpis in Montes Claros, an area of active transmission of American visceral leishmaniasis (AVL) in Brazil. Entomological captures were performed in 10 selected districts of the city, between September 2002-August 2003. A total of 773 specimens of L. longipalpiswere captured in the period and the population density could be associated with local climate variables (cumulative rainfall, average temperature and relative humidity) through a mathematical linear model with a determination coefficient (Rsqr) of 0.752. Although based on an oversimplified statistical analysis, as far as the vector is concerned, this approach showed to be potentially useful as a starting point to guide control measures for AVL in Montes Claros.

Correcting Measurement Error Bias in Interaction Models with Small Samples

Several methods have been suggested to estimate non-linear models with interaction terms in the presence of measurement error. Structural equation models eliminate measurement error bias, but require large samples. Ordinary least squares regression on summated scales, regression on factor scores and partial least squares are appropriate for small samples but do not correct measurement error bias. Two stage least squares regression does correct measurement error bias but the results strongly depend on the instrumental variable choice. This article discusses the old disattenuated regression method as an alternative for correcting measurement error in small samples. The method is extended to the case of interaction terms and is illustrated on a model that examines the interaction effect of innovation and style of use of budgets on business performance. Alternative reliability estimates that can be used to disattenuate the estimates are discussed. A comparison is made with the alternative methods. Methods that do not correct for measurement error bias perform very similarly and considerably worse than disattenuated regression