The primary objective of this paper is to propose two nonlinear extensions for macroeconomic forecasting using large datasets. First, we propose an alternative technique for factor estimation, i.e., kernel principal component analysis, which allows the factors to have a nonlinear relationship to...

Dynamic correlation, Exogenous variables, DCCX, Macroeconomic Announcements, Diversification benefits. - In this dissertation, I analyze determinants of conditional correlations. Specifically, I propose the generalized DCCX model that facilitates the analysis of the effects of exogenous...