J.-P. Montagner,1 C. Larmat,2 Y. Capdeville,1 M. Fink,3 H. Phung,1 B. Romanowicz,4 E. Clévédé1 and H. Kawakatsu5 1Seismology Laboratory, Institut de Physique du Globe UMR-CNRS 7154, 1 rue Jussieu 75238 Paris Cedex 05, France. E-mail: [email protected] 2L.A.N.L., Los Alamos, NM, USA 3Institut Langevin, ESPCI ParisTech, CNRS, 1 rue Jussieu, 75005 Paris, France 4Seismology Lab., U.C. Berkeley, Berkeley,...

Using a Smooth Transition Conditional Correlation model with Google search data as transition variable, I investigate correlation dynamics between set of crypto-currencies. A major change in the after 2017 bubble burst is explained by attention subsequently surrounding cryptocurrencies. searches are found to be good predictor cryptocurrencies and could provide useful input portfolio management.

This paper introduces new ways to construct probability integral transforms of random vectors that complement the approach of Diebold, Hahn, and Tay (1999) for evaluating multivariate conditional density forecasts. Our approach enables us to “scan” multivariate densities in various different ways. A simple bivariate normal example is given that illustrates how “scanning” a multivariate density ...