Statistics and Data Science Seminar
Yue Yu
UIC
Dynamic Cluster-based Sliced Inverse Regression for Forecasting Microeconomics Variables
Abstract: Sliced Inverse Regression (SIR) proposed by Ker-Chau Li (1991) is a widely
used semiparametric technique to reduce the dimensions of regression
problems. But the microeconomics data are time dependent and usually highly
correlated. In our study, we use clustering methods along with SIR, in order
to reduce the multicollinearity and the difficulty of choosing the
dimensions. And the dynamic version of cluster SIR methods is used to
analyze the autoregressive model of the microeconomics data. Our simulation
result shows that the dynamic cluster SIR is superior, comparing with the
empirical accuracy of all the models in Stock and Watson's paper (2005) for
forecasting U.S. macroeconomic time series over a 30-year period.
Wednesday October 6, 2010 at 3:00 PM in SEO 636