The asymmetric response of conditional variances to positive versus negative news has
been traditionally modeled with threshold specifications that allow only two possible regimes: …

We analyze the predictive performance of various volatility models for stock returns. To
compare their performance, we choose loss functions for which volatility estimation is of …

… Gloria González-Rivera is associate professor and Steven M. Helfand assistant professor
in the Department of Economics at the University of California, Riverside. This article was …

… We will obtain the shape of g independently from location and scale. … Write the loglikelihood
function as in (lo), replacing g by g. 4. Perform the maximization of the log-likelihood function …

… Both of these instances could be viewed from the perspective of symbolic data: in Zellner
and Tobias (2000) the data is an interval-valued time series and in González-Rivera, Lee, and …

Current regression models for interval-valued data do not guarantee that the predicted lower
bound of the interval is always smaller than its upper bound. We propose a constrained …

… However, we will proceed by analyzing the full histogram because, as González-Rivera
and Arroyo [[8]] have shown, there are prediction gains from carrying information on many …

… G. González-Rivera acknowledges the financial support of the UCR University Scholar
award and the Academic Senate grants. J. Arroyo acknowledges the financial support of grant …

… Evaluating the score function under the null of linearity H 0 : g =0 , keeping λ fixed, and Ω |
g =0 =σ 2 I T , we can write the score functions in vectorized form as(15) s(g i )| λ 2 , g =0 =− λ …

… We consider two cases: (i) the density g of the errors is completely unknown and (ii) the
density g is known to be symmetric. In (ii) the tangent set contains only symmetric functions. In …