The Underlying Return‐Generating Factors for REIT Returns: An Application of Independent Component Analysis
用独立成分分析（ICA）方法提取REIT收益的潜在因子，发现ICA能捕捉峰度特征，有助于开发应对极端事件的风险管理策略，补充传统均值-方差方法。
Multifactor approaches to real estate returns have emphasized a macro‐variables approach in preference to the latent factor approach originally used in arbitrage pricing theory. Use of high‐frequency data, trading strategies and growing emphasis on the risks of extreme events makes the macrovariable procedure problematic. This article explores an alternative to the principal components analysis approach: independent components analysis (ICA). ICA seeks independence and maximizes a chosen risk parameter. We apply an ICA procedure based on a kurtosis maximization algorithm to real estate investment trust (REIT) data. The results show that ICA successfully captures kurtosis characteristics of REIT returns, offering possibilities for developing of risk management strategies that are sensitive to extreme events and tail distributions, augmenting traditional mean–variance approaches.