New HEAVY Models for Fat-Tailed Realized Covariances and Returns

ABSTRACT

We develop a new score-driven model for the joint dynamics of fat-tailed realized covariance matrix observations and daily returns. The score dynamics for the unobserved true covariance matrix are robust to outliers and incidental large observations in both types of data by assuming a matrix-F distribution for the realized covariance measures and a multivariate Student's t distribution for the daily returns. The filter for the unknown covariance matrix has a computationally efficient matrix formulation, which proves beneficial for estimation and simulation purposes. We formulate parameter restrictions for stationarity and positive definiteness. Our simulation study shows that the new model is able to deal with high-dimensional settings (50 or more) and captures unobserved volatility dynamics even if the model is misspecified. We provide an empirical application to daily equity returns and realized covariance matrices up to 30 dimensions. The model statistically and economically outperforms competing multivariate volatility models out-of-sample. Supplementary materials for this article are available online.     

Australian demography at the millennium

This paper looks backwards over the last ten years to see what topics might concern Australian demographers in the future. The possibility of convergence or ’sameness’ is considered, but not proven. The main areas considered are historical demography, mortality, fertility, marriage, fertility regulation, internal migration, international migration, human resources, ageing, forecasting, the family life cycle, policy, and gender.     

Some remarks on the paper by A. Okore, 'Rural-urban fertility differentials in Southern Nigeria: An assessment of some available evidence'

Abstract In his paper Okore(1) critically examines the view of Olusanya and Ekanem that, partly because of shorter periods of breastfeeding and abstinence associated with 'modernization', urban fertility exceeds rural. Unfortunately, the proponents of this view have produced very few hard data on durations of breast-feeding and abstinence.(2).     

A neo-classical education transitions approach: A corrected tale for three cohorts

Analysts have regarded education transitions research as revealing late stage educational egalitarianism in the United States (e.g., Stolzenberg, 1994) and as sufficiently robust to guide policymakers (e.g., Hout, 2007). However, critics suggest parameter estimates are contaminated by selection bias (e.g., De Graaf & Ganzeboom, 1993), key parameter differences are unidentified (e.g., Cameron & Heckman, 1998), cross-transition comparisons are faulty, and the data are inappropriate. Useful modifications have been offered, (e.g., [Breen and Jonsson, 2000], [Hauser and Andrew, 2006] and [Lucas, 2001]), but analysts have yet to comprehensively address the challenges critics pose. In response, we propose a neo-classical education transitions approach that uses fuller sets of data and models that explicitly address the primary threats to proper inference. Using this approach we re-assess the educational attainment process for a baby boomer cohort, a Generation X cohort, and a Generation Y cohort. All cohorts fail to replicate the waning coefficients pattern. Methodologically, the study responds to criticisms in a way that offers methods for continued cross-national comparative research. Substantively, the study undermines confidence that standard education transitions research can provide policy guidance and the claim of late stage egalitarianism in the United States educational attainment process.