上財系列】金融實證方法（研究生）課件emp5

1、Simple technical trading rules and the stochastic properties of stock returns William Brock, Josef Lakonishock, and Blake Lebaron The Journal of Finance, 1992 Data Dow Jones Industrial Average (DJIA) Full sample: 1/1/1897-12/31/1986 Subperiod: 1/1/1897-7/30/1914 (closing of the stock exchange during

2、 the World War One) 1/1/1915-12/31/1938 (include turbulent times of depression) 1/1/1939-6/30/1962 (include the World War Two and ends in the data CRSP begins its daily price series) 7/1/1962-12/31/1986 (extensively researched) Summary statistics for daily and 10-day returns Technical trading rules

3、Two of the simplest and most widely used technical rules are investigated: moving average and trading range break-out (resistance and support levels). Buy (sell): short-period moving average rises above (or falls below) the long-period moving average rises. VMA(Variable-Length Moving average) 可變長度移動

4、平均規(guī)則 當S-天移動平均線的價格超過（低于） L-天移動平均線的價格至少B%時。 1-50，1-150，1-200，5-150和5-200； 以0和1作為預先指定的百分比。 Standard test for VMA FMA(Fixed-Length Moving average) 固定長度移動平均規(guī)則 當短期移動平均線從下面（上面）超過 （低于）長期移動平均線時。當信號發(fā) 出后，FMA規(guī)則發(fā)出的信號持續(xù)一個固 定天數。 1-50，1-150，1-200，5-150，和2-200； 以10天作為預先指定的固定天數。 Standard test for FMA TRB(trading rang

5、e break-out,交易區(qū) 間突破,支撐阻力分析方法) A buy signal is generated when the price penetrates the resistance level. The resistance level is defined as the local maximum. A sell signal is generated when the price penetrates the support level which is the local minimum price. In accordance with the moving average

6、 strategy, Maximum (or minimum) prices were determined based on the past 50, 150, and 200 days. In addition, the rule is implemented with and without a one percent band. Standard test for TRB Bootstrap Methodology A random walk with a drift tt rb Simulation tests for 500 replications Bootstrap Metho

7、dology AR(1) 1ttt rbr Bootstrap Methodology GARCH-M: Garch in mean model Bootstrap Methodology EGARCH-M: exponeatial Garch Conclusion The recent studies on predictibility of equity returns from past returns suggest that the conclusion reached by many earlier studies that found technical analysis is

8、useless might have been premature. Overall our results provide strong support for the technical strategies that we explored. The returns obtained from buy (sell) signals are not likely to be generated by the four popular null models (random walk with a drift, AR(1), Garch-M, and E-Garch). SHCI：12/19

9、/199012/13/1996 N=20 SHCI: 19970101-20100204 (1, 50, 0.00) CAGR(B std(B sharpe(B std(1,50)=17.19%; sharpe(1,50)=0.9196 交易的盈虧 總交易次數：69；盈利次數：31；勝率：44.9% Profiting from Technical Analysis in Indian Equity Markets: Using Moving Averages Shyam Sundhar & Ram Kumar Kakani Mar. 2006 Displaced Moving Average

10、 (DMA,置 換移動平均線) Trading Rule The SMA is a lag indicator and the signals that break out from the rule, lag the trend. The DMA rule overcomes this issue by displacing today moving averages forward in time by say t days. 普通移動平均線以某種時間單位向后平移，以減少毛刺。 The simplistic assumption behind displacing todays actua

11、l moving average value forward in time is that the future periods actual moving average value that has not yet occurred will, in fact, be equal to todays moving average value. A BUY signal is generated when the current SMA is greater than the predicted moving average. Conversely, when the SMA falls

12、below the predicted value a SELL signal is closed. Data S&P CNX Nifty (印度NIFTY指數 ), BSE Sensex (孟買敏感30指數) as well as multiple individual stocks. J u l y 1 9 9 0 t o D e c e m b e r 2 0 0 5 approximating to around 3700 data points Mean, Deviation and Sharp Ratio on Nifty 50*11 七、相對強弱指標RSI The Relativ

13、e Strength Index (RSI) was developed by J. Welles Wilder in the 1970s. 計算公式 RSI=六日上漲幅度平均值 （六日上漲幅度平均值+六日下跌幅度平均值）100 參考基數：六日、12日、24日 研判準則： 超過80，賣出信號 低于20，買入信號 High probability ETF trading: 7 professional strategies to improve your ETF trading Larry Connors, Cesar Alvarez, 2009 Chapter six Multiple Day

14、s Up (MDU) and Multiple Days Down (MDD) Strategy Rules on the long side An ETF is trading above its 200-day moving average. The ETF closes below its 5-period moving average on the entry day. The ETF must drop 4 out of 5 past days. This means closing prices were lower than the day before for 4 out of

15、 the past 5 days. If this happen, we buy the ETF on the close today. Aggressive version-buy a second unit if prices close lower than your innitial entry price any time you are in the position. Our exit is on the close when the ETF closes above its 5- period simple moving average. Rules on the short

16、side The ETF closes under its 200-day moving average. The ETF closes higher 4 out of 5 past days. The ETF closes above its 5-period moving average. Aggressive version-short a second unit if prices close higher than your innitial entry price any time you are in the position. Exit when the ETF closes

17、under its 5-period MA. Shci: 19970101-20100204連續(xù)上漲和下跌天數 連續(xù)輸后的勝率 TPS What TPS does is combine time, price and scaling-in to give the highest percent correst on the ETFs of any strategy we have created or ever traded. Please remember again that there are literally thousands of variations which can be

18、traded with TPS. Rules on the long side An ETF is above its 200-day moving average. The 2-period RSI is below 25 for two days in a row. Buy 10% of your position on the close. If prices are lower on the close than your previous entry price, any day you are in a positon, buy 20% more of your position

19、(again you are averageing in). If prices are lower on the close than your previous entry price, any day you are in a positon, buy 30% more of your position. If prices are lower on the close than your previous entry price, any day you are in a positon, buy 40% more of your position. Using this 10%, 20%, 30% and 40% scaling-in approach (also known as 1-2-3-4) you are now have a full position in a very oversold ETF. Exit on the close when the 2-period RSI closes above 70. Rules on the short side An ETF is below its 200-day moving average. The 2-period RSI is above 75 for two da