Markov Switching Dynamics in REIT Returns: Univariate and Multivariate Evidence on Forecasting Performance
研究了房地产投资信托（REIT）收益的预期回报、方差和风险回报比中的马尔可夫转换机制，并与股票和债券进行比较，发现1972-2008年间该模型优于其他时间序列模型，且多变量分析需设定四个独立状态。
We document the presence of Markov switching regimes in expected returns, variances and the implied reward‐to‐risk ratio of real estate investment trust (REIT) returns and compare them to properties of stocks and bonds. Our evidence suggests that regime switching techniques are more successful over the period 1972–2008 than other time‐series models are. When the analysis is extended to a multivariate setting in which REIT, stock and bond returns are modeled jointly, we find that the data call for the specification of four separate regimes. These result from the absence of synchronicity among the regimes that characterize univariate REIT, stock and bond returns.