Tactical asset allocation imbedded with investors' subjective views

Abstract

This paper walks through the tactical asset allocation literature and focusesespecially on the implementation of Black-litterman model on global equity indexportfolio. We found that Black-litterman is superior to traditional mean-varianceallocation model in terms of Sharpe ratio and avoiding corner points, even thoughour forecasting model is quite simple and forecasting power is low. Besides, weextended Black-litterman model in a way that one can put the business cycle viewsinto the market equilibrium model. We found that the added business cycle informationgreatly enhanced the performance of the portfolio in the out of sample test.Also we proposed an equity forecasting model based on the 6 month P/B MovingAverage and found that it is not worse than the interest rate surprise model whenit is applied to the SPX 500 index in the out of sample test.In addition, in our sensitivity analysis, we found that the tricky parameter isbest calibrated as 1/ m. As grows larger than 5, the Black-litterman modelbecomes dramatic in a way that the sharp ratio is exceptionally good while thereare many corner points in the allocated weights.Among others, the variance of investors views did not affect much of out of sample performance once and arefixed. Finally, the use of daily decayed data for estimating covariance matrix hadmuch larger impact on the traditional Mean-Variance model than on the Blacklittermanmodel, which is another evidence that Black-litterman has superioritiesover Mean-Variance model in terms of parameter robustness.