題 目: Doubly Constrained Factor Models: Estimation and Applications
主講人: 蔡恆修 博士 (中研院統計所)
時 間: 100年3月18日（星期五）上午 10:40 - 11：30
（上午10：20- 10：40茶會於統計所821室舉行）
地 點: 清大綜合三館837室
Abstract
Factor models have been widely used in recent years to improve the accuracy
of forecasting when many explanatory variables are available. However, the
models often encounter the difficulties of over-parameterization and factor
interpretation. In this paper, we first consider constrained factor analysis
to obtain a parsimonious factor model and propose likelihood ratio statistics
to test the adequacy of factor constraints. Real and simulated examples are
used to demonstrate the proposed analysis. In an application, we show that
the constrained factor analysis can provide a deeper understanding of
variations in monthly financial asset returns.
We then extend the constrained models to the doubly constrained factor models
by incorporating external information on both rows (e.g., subjects) and
columns (e.g., variables) of a data matrix. Maximum likelihood estimates and
likelihood ratio statistics of the proposed models are derived. Finally, we
consider the applications of doubly constrained factor models in economics
and finance. (This is a joint work with Ruey Tsay of the University of
Chicago).
--
※ 發信站: 批踢踢實業坊(ptt.cc)
◆ From: 140.113.114.213