本研究是根據Phillips and Shi (2018) 提出的PSY泡沫檢測模型，針對台灣航運股票長榮、陽明與萬海進行泡沫檢測，並依據泡沫檢測結果建構投資做多與做空之投資策略。本研究以泡沫開始日買進股票，泡沫結束日賣出股票作為做多策略。以泡沫結束日賣出股票賣出股票，並於泡沫結束日一週後、二週後與三週後買回作為做空策略。再以技術分析指標MACD作為對照，以MACD直方圖由負翻正時買進股票，MACD直方圖由正翻負時賣出股票作為做多策略。以MACD直方圖由正翻負時賣出股票，MACD直方圖由負翻正時買進股票做為空方策略。比較PSY泡沫偵測模型與MACD指標分別在做多與做空投資策略下表現。實證結果發現，在做多策略下，採用PSY泡沫偵測模型，勝率較MACD指標為高，但整體報酬與IRR則較MACD指標為低，而做空策略下，採用PSY勝率、整體報酬與IRR皆優於MACD指標。

This study is based on the PSY bubble detection model proposed by Phillips and Shi (2018) to detect bubbles in Taiwan shipping stocks Evergreen, Yang Ming, and Wan Hai, and to construct investment strategies for long position and short position based on the bubble detection results. In this study, the long investment strategy is to buy stocks at the beginning of the bubble and sell stocks at the end of the bubble. The short selling strategy is to sell stocks at the end of the bubble and buy back after one week, two weeks and three weeks at the end of the bubble. Using the MACD as a technical analysis indicator, buy stocks when the MACD histogram turns from negative to positive and sell stocks when the MACD histogram turns from positive to negative as a long strategy. The short side strategy is to sell stocks when the MACD histogram turns from positive to negative and to buy stocks when the MACD histogram turns from negative to positive. The performance of the PSY bubble detection model and MACD indicator are compared under long and short investment strategies respectively. The results show that the PSY bubble detection model has a higher winning rate than the MACD under the long strategy, but a lower overall return and IRR than the MACD, while the PSY winning rate, overall return and IRR are better than the MACD under the short strategy.

1.前言…………………………………………………………1
2.文獻回顧…………………………………………………3
3.研究方法……………………………………………………5
4.實證結果……………………………………………………9
5.結論……………………………………………………………19
參考文獻………………………………………………………21

1.Harvey, D. I., Leybourne, S. J., Sollis, R., & Taylor, A. R. (2016). Tests for explosive financial bubbles in the presence of non-stationary volatility. Journal of Empirical Finance, 38, 548-574.
2.Milunovich, G., Shi, S., & Tan, D. (2019). Bubble detection and sector trading in real time. Quantitative Finance, 19(2), 247-263.
3.Phillips, P. C., & Shi, S. (2019). Detecting financial collapse and ballooning sovereign risk. Oxford Bulletin of Economics and Statistics, 81(6), 1336-1361.
4.Phillips, P. C. B., Shi, S., & Caspi, I. (2018). Real-Time Monitoring of Asset Markets with R. R Foundation for Statistical Computing. Vienna, Austria. URL: https://CRAN. R-project. org/package= psymonitor.
5.Phillips, P. C., Shi, S., & Yu, J. (2015). Testing for multiple bubbles: Historical episodes of exuberance and collapse in the S&P 500. International economic review, 56(4), 1043-1078.
6.Phillips, P. C., Shi, S., & Yu, J. (2015). Testing for multiple bubbles: Limit theory of real‐time detectors. International Economic Review, 56(4), 1079-1134.
7.Phillips, P. C., & Shi, S. (2020). Real time monitoring of asset markets: Bubbles and crises. In Handbook of statistics (Vol. 42, pp. 61-80). Elsevier.
8.Phillips, P. C., Wu, Y., & Yu, J. (2011). Explosive behavior in the 1990s Nasdaq: When did exuberance escalate asset values?. International economic review, 52(1), 201-226.