Days since 08/01/95 - раздел Литература, Beyond Technical Analysis Figure 2.2 Sscp-500 Closing Data With Regression Using Terms...
Figure 2.2 SScP-500 closing data with regression using terms raised to the fifth power.
Est Close = C0 + (C1 x D)
Est Close=C0+(C1*D)+(C2*D2)+(C3*D3)+(C4*D4)+C5*D5)
Table 2.2 illustrates several interesting features about curve-fitting a data set. First, observe that the value of the constant Co is approximately the same for each equation. This implies that the simplest model, the constant C0, captures a substantial amount of information in the data set.
Then, notice that the absolute value of the constants decreases as the order of the term increases. In other words, in absolute value, Co is greater than C1, which is greater than C2 and on down the line. Therefore, the relative contribution of the higher-order polynomial terms becomes smaller and smaller. However, as you add the higher-order polynomial terms, the line takes on greater curvature and fits the data more closely, as seen in Figures 2.1 and 2.2.
20 Principles of Trading System Design
Table 2.2 Comparison of linear regression coefficients
|
| C0
| C1
| C2
| C3
| C4
| Cs
|
| Equation2.1
| 560.0865
| 0.537870
|
|
|
|
|
| Equation2.2
| 570.2379
| -1.94509
| 0.131279
| -0.00154
| -0.00003
| 0.0000006
|
This exercise illustrates many important ideas. First, any model you build for the data should be as simple as possible. In this case, the simple linear regression, with a slope and intercept, captured essentially all the information in the data. Second, adding complexity by adding higher-order terms (read rules) does improve the fit with the data. Thus, we pick up nuances in the data as we build more complex models. The probability that these nuances will repeat exactly is very small. Third, the purpose of our models is to describe how prices have changed over the test period. We used our data to directly calculate the linear regression coefficients. Thus, our model is hostage to the data set. There is no reason why these coefficients should accurately describe any future data. This means that over-fitted trading systems are unlikely to perform as well in the future.
Another example, a variant of the moving-average crossover system, illustrates why it makes sense to limit the number of rules. In the usual case, the dual moving average system has just two rules. For example, for the long entry the 3-day average should cross over the 65-day average and vice versa.
Now, consider a variant that uses more than two averages. For example, buy on the close if both the 3-day and the 4-day moving averages are above the 65-day average. Since there are two "short" averages, this gives us four rules, two each for long and short trades. Using more and more "short" averages rapidly increases the number of rules. For example, if the 3-, 4-, 5-, 6-, and 7-day moving averages should all be above the 65-day average for the long entry, ten rules would apply.
Consider 10 years of Swiss franc continuous contract data, from January 1, 1985, through December 31, 1994, without any initial stop, but allowing $100 for slippage and commissions. The number of rules is varied from 2 to 128 to explore the effects of increasing the number of rules. As the number of rules increases, the number of trades decreases, as shown in Figure 2.3. This illustrates the fact that as you increase the number of rules, you need more data to perform reliable tests.
Rule 2: A Small Number of Rules21
Все темы данного раздела:
Developing New Trading Systems 73
Introduction 73 The Assumptions behind Trend-Following Systems 74
The 65sma-3cc Trend-Following System 75 Effect of Initial Money Management Stop 88 Adding Filter to the 65sma-3cc Syste
Selected Bibliography 253 Index 255 About the Disk 261
Preface
This is a book about designing, testing, and implementing trading systems for the futures and equities markets. The book begins by developing trading systems and ends by def
Introduction
Хорошая система торговли удовлетворяет вашу индивидуальность. К счастью, самый быстрый способ находить каждый - через процесс испытания(суда) и ужаса(террора). Любое проверяющее система программное
РАЗВИТИЕ И ВНЕДРЕНИЕ ТОРГОВЫХ СИСТЕМ
На предмете. Привлекательная особенность - то большинство материала, первоначальное или новое. Эта книга разделена на две половины по четыре главы каждая. Первая часть посвящена проектированию торг
The Usual Disclaimer
Throughout the book, a number of trading systems are explored as examples of the art of designing and testing trading systems. This is not a recommendation that you trade these systems. I do not c
What Is a Trading System?
A trading system is a set of rules that defines conditions required to initiate and exit a trade. Usually, most trading systems have many parts, such as entry, exit, risk control, and money manage
Comparison: Discretionary versus Mechanical System Trader
Table 1.1 compares two extremes in trading: a discretionary trader and a 100% mechanical system trader. Discretionary traders use all inputs that seem relevant to the trade: fundamental data, techn
Discretionary Trader 100% Mechanical System Trader
Subjective
Objective
Many rules
Few rules
Emotional
Unemotional
Varies
Why Should You Use a Trading System?
The most important reason to use a trading system is to gain a "statistical edge." This often-used term simply means that you have tested the system, and the profit of the average trade—
Robust Trading Systems: TOPS COLA
A robust trading system is one that can withstand a variety of market conditions across many markets and time frames. A robust system is not overly sensitive to the actual values of the parameters
How Do You Implement a Trading System?
Begin with a trading system you trust. After sufficient testing, you can determine the risk control strategy necessary for that system. The risk control strategy specifies the number of contracts p
Who Wins? Who Loses?
Tewles, Harlow, and Stone (1974) report a study by Blair Stewart of the complete trading accounts of 8,922 customers in the 1930s. That may seem like a long time ago, but the human psychology of fe
Beyond Technical Analysis
The usual advice for technical traders is a collection of rules with many exceptions and exceptions to the exceptions. The trading rules are difficult to test and the observations are hard to quan
Introduction
This chapter presents some basic principles of system design. "You should try to understand these issues and adapt them to your preferences.
First, assess your trading beliefs—these b
What Are Your Trading Beliefs?
You can trade only what you believe; therefore, your beliefs about price action must be at the core of your trading system. This will allow the trading system to reflect your personality, and you a
Six Cardinal Rules
Once you identify your strongly held trading beliefs, you can switch to the task of building a trading system around those beliefs. The six rules listed below are important considerations in tradin
Rule 1: Positive Expectation
A trading system that has a positive expectation is likely to be profitable in the future. The expectation here refers to the dollar profit of the average trade, including all available winning an
Rule 2: A Small Number of Rules
This book deals with deterministic trading systems using a small number of rules or variables. These trading systems are similar to systems people have developed for tasks such as controlling a che
More rules need more data
2 4 8 12 16 24 32 48 64 96 128 Number of rules
Rule 3: Robust Trading Rules
Robust trading rules can handle a variety of market conditions. The performance of such systems is not sensitive to small changes in parameter values. Usually, these rules are profitable over mult
Number of rules
Figure 2.5 Adding more rules delayed entries and exits, increasing maximum intraday drawdown. Note that the horizontal scale is not linear.
today's high + 1 point on a buy
Number of rules
Figure 2.6 Increasing the number of rules decreased profits in the U.S. bond market from January 1, 1975 through June 30, 1995. Note that the horizontal scale is not linear.
Delay (» of days) after crossover
Figure 2.7 The effect on profits of changing the number of days of delay in accepting a crossover signal of a 3-day SMA by 12-day SMA system is highly dependent on the delay.
Here must be a Figure.
Figure 2.8 The August 1995 crude oil contract with curve-fitted system
profitable trades. As many as 87 percent of all trades (20 out of 23) were profitable. A second clue
Rule 4: Trading Multiple Contracts
Multiple contracts allow you to make larger profits when you are right. However, the drawdowns are larger if you are wrong. You are betting that with good risk control, the overall profits w
Rule 5: Risk Control, Money Management, and Portfolio Design
All traders have accounts of finite size as well as written or unwritten guidelines for expected performance over the immediate future. These performance guidelines have a great influence over the
Equity Curve: 3SF vs SF+TY+CT
-3SF
-SUM
Time (months)
Figure 2.11 This contrived jagged equity curve has a standard error of 2.25. The perfectly smooth equity curve has an SE of zero. The standard deviation of monthly returns is 33 pe
Rule 6: Fully Mechanical System
The simplest answer to why a system must be mechanical is that you cannot test a discretionary system over historical data. It is impossible to
Summary37
for
Summary
This chapter developed a checklist for narrowing your trading beliefs. You should narrow your beliefs down to five or less to build effective trading systems around them.
This chapter also
Introduction
This chapter examines many key system design issues. Now that you understand some basic principles of system design, you can consider more complex issues. And as you understand these issues, you c
Diagnosing Market Trends
You can design a profitable trading strategy if you can correctly and consistently diagnose whether a market is trending. In simple terms, the market exists in two states: trending and ranging. A
ADX Rising, RAVI Rising, Market (1/1/89-6/30/95) ADX>20 RAVI > 3
Coffee
30.2
43.3
Copper, high-grade
27.0
35.3
Cotton
29.2
To Follow the Trend or Not?
If you are not a large hedger or an institutional trader, you can follow either of two basic strategies when you design a trading system. You can be a trend follower, or you can take antitre
Profits of age of Winner Loser tive Drawdown
($) Trades Winners ($) ($) Losers ($)
Coffee
1,837
27,065
-11,215
To Optimize or Not to Optimize?
If you have a computer, you can easily set up a search to find the "optimum" values for a system over historical data. The results can be truly astonishing. Imagine your profits if you c
Length of Optimized 3 mo. 1990 6 mo. 1990 9 mo. 1990 12mo.1990 SMA Relative Relative Relative Relative Relative (days) Rank Rank Rank Rank Rank
Initial Stop: Solution or Problem?
Many traders have raised stop placement to an art form because it is not clear if the initial stop is a solution or a problem. The answer depends on your experiences. Often, the stop acts as a magn
Day CHBOC with varying initial stop
S
Changes In MIDD for 20-day CHBOC on Coffee
-20000
-22000
S
-24000
-26000
-28000
-30000
-32000
-34000
-36000
Changes In percent profitable trades, 20-day CHBOC on Coffee
>o o 10 o irt o io o io
t- r- cm cm co ro ^t -a-
Initial stop ($)
Cumulative frequency distribution average 10-day daily range in coffee
250 750 1250 1750 2250 2750 3250 3750 4250 4750 5250 Range ($)
Does Your Design Control Risks?
As you design your trading system, remind yourself that one of your key goals is to control the downside risk. You will quickly discover that risk is a many-splendored thing. This section br
Data! Handle with Care!
You have many choices when you select data for your system testing. You should therefore exercise great care in choosing your test data because they have a big influence on test results.
C
Profit MIDD of Wins Win/Loss Data Type ($) ($) Trades (%) Ratio
Actual with rollovers 17,963 -21,663 111 40 1.80
Continuous type 38/13 18,450 -24,813 79 31 2.74
Continuous type 49/25 20,413 -22,137 77 31 2.89
Continuous type 55/25 20,
Choosing Orders for Entries and Exits
You have three basic choices for orders that you use to initiate or exit your trades: market, stop, or limit orders. There are three philosophies at work here. One says to get your price, implying
Understanding Summary of Test Results
This discussion of the detailed summary of test results found in technical analysis programs uses in part the report from Omega Research's TradeStation™ software. The purpose of the summary is to s
British Pound 38/13-dally 02/13/75 - 7/10/95 Performance Summary: All Trades
Total net profit ($) 155,675.00
Gross profit ($) 266,918.75
Total number of trades 71
Number of winning trades 32
Largest winning trade
What the Performance Summary Does Not Show
The test summary leaves out some important information, highlighted below. You may wish to examine these factors in greater detail.
One simple ratio is the recovery factor (RF). RF is abso
A Reality Check
This section sounds a note of warning before you proceed: Test results are not what they seem. You should recognize that trading systems are designed with the benefit of hindsight. This is true bec
Introduction
A trading system is only as good as your market intuition. You can formulate and test virtually any trading system you can imagine with today's software. The previous chapters studied the b
The Assumptions behind Trend-Following Systems
The basic assumptions behind a simple trend-following system are as follows:
1. Markets trend smoothly up and down, and trends last a long time.
2. A close beyond a moving average
The 65sma-3cc Trend-Following System
This section discusses how to formulate and test a simple, nonoptimized, trend-following system that makes as few assumptions as possible about price action. It arbitrarily uses a 65-day simple mov
Distribution of Trade P&L for 65sma-3cc: 2400 trades
tOU
Comparing frequency distribution of 65sma-3cc trades to standard normal distribution
| 0.2
Frequency distribution of 65sma-3cc trades compared to a modified normal distribution
^-•-•^-T-OOOOOOOOOOOOOT-'-
Z (standard deviations)
Maximum favorable excursion of 1,565 losing trades of 65sma-3cc system
800 700 600 500 400 300 200 100 0
s
Maximum profit ($)
Figure 4.9 A histogram of maximum profit in 1,565 losing trades over 20 ye
Cumulative Frequency of winning trades, 65sma-3cc system
2000 3000 Maximum pro
Effect of Initial Money Management Stop
Since the initial test of the 65sma-3cc model was encouraging, we can now do more testing. The first item of business is to insert an initial money management stop into this model. Our detailed ana
Number of trades Increases and levels off.
•US Bond
-DM
750 1000 125
Volatility-based initial money management stop
Figure 4.13 The profits (upper line) increase as the initial money management stop is loosened. Eventually, the stop is too wide and profits begin to level off. The lower line is t
Profit and MIDD for LH as a function of initial MMS
Volatility-based initial MMS
Figure 4.14 The profits (upper line) increase as the initial money management stop is loosened. The lower line is the maximum intraday drawdown. Data are for the live hogs market.
Adding Filter to the 65sma-3cc System
So far, we have let the trading system generate pure signals without trying to filter the signals in any way. As we have seen, this system will generate many short-lived or "false" sign
Largest losing trade increases as MMS Increases
-1000
-2000
-3000
<s.
Volatility based initial MMS for Sugar
Figure 4.15 Largest losing trade for sugar using the 65sma-3cc trading system increases as the volatility-based initial money management stop increases.
also the short exi
Adding Exit Rules to the 65sma-3cc System
Selecting general and powerful exit rules is a difficult challenge in system design because the markets exhibit many different price patterns. One form of exit that is particularly easy to impleme
Channel Breakout-Pull Back Pattern
This section discusses a trading system based on a pattern observed in mature markets, that is, markets with a large volume of institutional activity. In these markets, the big players have a tend
An ADX Burst Trend-Seeking System
We have assumed that the market was about to trend in both the 65sma-3cc and the CB-PB systems, although we did not actually verify that the market was trending because it is difficult to measure t
A Trend-Antitrend Trading System
In this section we explore the trend-antitrend (T-AT) system, designed to switch automatically between an antitrend mode and a trend-following mode. You will like this system if you aggressively l
Gold-Bond Intermarket System
This section develops intermarket trading systems for trading negatively or positively correlated markets. We begin with a quick review of the difficulties of formulating intermarket models. The go
A Pattern for Bottom-Fishing
Market-specific systems work best on a particular market because they capture some unusual feature of that market. It is difficult to speculate why certain markets show signature patterns. We shoul
Time: 4/82-7/95
Figure 4.39 Equity curve for bottom-fishing pattern (9/82-7/95) with X = 1 and /= 0 (aggressive trades) for SScP-500 data with rollovers. Initial money management stop was $2,000.
Identifying Extraordinary Opportunities
Once or twice a year, the futures markets provide extraordinary opportunities for exceptional profits, and if you can take advantage of these opportunities, your account performance will improve s
Новости и инфо для студентов