Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 444 - Recent Advances in Statistical Methodology for Big Data
Type: Contributed
Date/Time: Thursday, August 12, 2021 : 4:00 PM to 5:50 PM
Sponsor: IMS
Abstract #318243
Title: Simultaneous Inference for the Common and Idiosyncratic of the Dynamic Factor Model
Author(s): Yuanyuan Zhang* and Jiangyan Wang and Xinbing Kong
Companies: Soochow University and Nanjing Audit University and Nanjing Audit University
Keywords: Dynamic factor model; Empirical process; Dynamic principal component; Simultaneous confidence band
Abstract:

The dynamic principal component method can estimate the common and idiosyncratic components consistently. Based on the estimated common and idiosyncratic components, two empirical processes for distribution functions of the common and idiosyncratic components are constructed, respectively. We prove that these two empirical processes are oracle efficient when T=o(n) where n is the dimension and and T is the sample size. This validates that the decomposition of individual variables to common and idiosyncratic empirical processes on the dynamic factor model. Based on this oracle property, we construct simultaneous confidence bands (SCBs) for the distributions of the common and idiosyncratic components. Simulation and empirical studies verify that the estimated bands perform well in terms of coverage frequencies.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2021 program