한국 주식시장에서 마코위츠 포트폴리오 선정 모형의 입력 변수의 정확도에 따른 투자 성과 연구

Markowitz’s portfolio selection model is used to construct an optimal portfolio which has minimum variance, whilesatisfying a minimum required expected return. The model uses estimators based on analysis of historical data toestimate the returns, standard deviations, and correlation coefficients of individual stocks being considered forinvestment. However, due to the inaccuracies involved in estimations, the true optimality of a portfolio constructedusing the model is questionable. To investigate the effect of estimation inaccuracy on actual portfolio performance,we study the changes in a portfolio’s realized return and standard deviation as the accuracy of the estimations foreach stock’s return, standard deviation, and correlation coefficient is increased. Furthermore, we empirically analyzethe portfolio’s performance by comparing it with the performance of active mutual funds that are being traded in theKorean stock market and the KOSPI benchmark index, in terms of portfolio returns, standard deviations of returns,and Sharpe ratios. Our results suggest that, among the three input parameters, the accuracy of the estimated returnsof individual stocks has the largest effect on performance, while the accuracy of the estimates of the standard deviationof each stock’s returns and the correlation coefficient between different stocks have smaller effects. In addition, itis shown that even a small increase in the accuracy of the estimated return of individual stocks improves the portfolio’sperformance substantially, suggesting that Markowitz’s model can be more effectively applied in real-life investmentswith just an incremental effort to increase estimation accuracy.