On the limitations of comparing mean square forecast errors

Linear models are invariant under non-singular, scale-preserving linear transformations, whereas mean square forecast errors (MSFEs) are not. Different rankings may result across models or methods from choosing alternative yet isomorphic representations of a process. One approach can dominate others for comparisons in levels, yet lose to another for differences, to a second for cointegrating vectors and to a third for combinations of variables. The potential for switches in ranking is related to criticisms of the inadequacy of MSFE against encompassing criteria, which are invariant under linear transforms and entail MSFE dominance. An invariant evaluation criterion which avoids misleading outcomes is examined in a Monte Carlo study of forecasting methods.     

Structure of astacin and implications for activation of astacins and zinc-ligation of collagenases.

Astacin, a digestive zinc-endopeptidase from the crayfish Astacus astacus L., is the prototype for the 'astacin family', which includes mammalian metallo-endopeptidases and developmentally regulated proteins of man, fruitfly, frog and sea urchin. Here we report the X-ray crystal structure of astacin, which reveals a deep active-site cleft, with the zinc at its bottom ligated by three histidines, a water molecule and a more remote tyrosine. The third histidine (His 102) forms part of a consensus sequence, shared not only by the members of the astacin family, but also by otherwise sequentially unrelated proteinases, such as vertebrate collagenases. It may therefore represent the elusive 'third' zinc ligand in these enzymes. The amino terminus of astacin is buried forming an internal salt-bridge with Glu 103, adjacent to His 102. Astacin pro-forms extended at the N terminus, as observed for some 'latent' mammalian astacin homologues, did not exhibit this 'active' conformation, indicating an activation mechanism reminiscent of trypsin-like serine proteinases.     

Influence of hydrochlorothiazide on the pain threshold and on the antinociceptive activity of morphine,in rats

Summary Hydrochlorothiazide, acutely injected in rats, has a weak analgesic activity per se and potentiates and prolongs the antinociceptive effect of morphine.This work was supported in part by grants from Consiglio Nazionale delle Ricerche, and by Ministero della Pubblica Istruzione, Roma.     

Forecast accuracy after pretesting with an application to the stock market

In econometrics, as a rule, the same data set is used to select the model and, conditional on the selected model, to forecast. However, one typically reports the properties of the (conditional) forecast, ignoring the fact that its properties are affected by the model selection (pretesting). This is wrong, and in this paper we show that the error can be substantial. We obtain explicit expressions for this error. To illustrate the theory we consider a regression approach to stock market forecasting, and show that the standard predictions ignoring pretesting are much less robust than naive econometrics might suggest. We also propose a forecast procedure based on the ‘neutral Laplace estimator’, which leads to an improvement over standard model selection procedures. Copyright © 2004 John Wiley & Sons, Ltd.