A computer calculated the returns that would have been experienced if certain price/volume patterns were the sole determining factor for buying and selling stocks over many years. Millions of potential patterns were analyzed. A few patterns were discovered that have fairly uniform returns year over year (positive mean and median returns for every calendar year analyzed) and have high ratios of winners to losers.
Statistical Trading is about following one of these patterns, performing every buy and every sell that the pattern indicates in the belief that there is a high probability that the past performance will be repeated in the future.
In order to reduce the risk of our recommendations unduly influencing stock
prices, we restrict our recommendations to stocks that typically trade over half
a million shares a day and have a market capitalization in excess of one billion
dollars. Back to Top 
The author of the program, Thomas Stone, has a B.A. in Theoretical Mathematics from
the University of Rochester, over 20 years' experience as a Software Engineer designing
computer programs for industry, and over 20 years experience as an investor. He wrote his
first stock pattern analysis program in 2002 and traded it successfully in his own
accounts. He subsequently wrote a second generation program that he now uses for trading
his accounts. The trading recommendations from this new program are offered on this site. Back to Top 
No account is made for any stock fundamentals by the program. The program philosophy
is that investor's beliefs in the future direction of a stock should be reflected in the
price/volume behavior of the stock. Back to Top 
The best patterns generally have at least 66%, ±4% winning trades with the return for
the average winner being 150% - 400%, depending on hold time, of the loss of the average loser. In other words,
the average gain is between one-and-a-half and three times as large as the average loss. Back to Top 
Assuming that you invested 5% of your portfolio into each recommendation, your account
would be valued at over $350,000 today (figures not adjusted for taxes, commissions, or
subscription fees). That is an average annualized return of over 35%. Back to Top 
We generally recommend that no less than
$5,000 be put into any one stock and that you invest no more than 14% of your portfolio
in any given stock. That means that no less than $35,000 should be committed to following
the recommendations. Back to Top 
A 35% annual return drops to about 30% if the portfolio size is $35,000. For a portfolio
of $200,000, a 35% return drops to 34.4%. Back to Top 
We should not lose sight of the name, Statistical Trading. The statement that 66% +/- 4% are winners implies that there is a very HIGH degree of confidence that there will be at least 30% losers. If the first two that you choose are losers, it could take quite a while to recover your initial losses.
In order to maximize the probability that your portfolio will realize close to the
statistically predicted return, you want to spread your investment across as many issues as
possible. Back to Top 
In statistical sampling there is a concept referred to as outliers. Outliers are samples that lie far away from most of the other samples. Going over the historical trades that would have been made in the last few years, there are a few that would have more than doubled and there are some that would have plunged by 40% or so before being sold.
The way to insulate yourself from the few trades that swing wildly is to diversify, diversify,
diversify. If you are investing 14% of you portfolio in every issue, your account value will vary
up and down much more than if you are investing less than 14%. Back to Top 
No! You should figure on an average holding time of 6-8 weeks. Once in a while there may be
a stock that is held only a day or two and sometimes a stock may be held a year or more. Back to Top 
If you invest 5% of your portfolio in each investment, you will average 5-7 buy or sell
orders per week. Back to Top 
No. The system will tailor its recommendations to you based on the information that
you supply in your profile, . Back to Top 
Then the subscription service offered here is not for you. Please contact us
and we will generate a unique pattern for you. We will need to know such things as
desired portfolio turnover rate, maximum number of issues to be held, desired minimum
percentage of winning trades, and other information. Our software algorithms use this
information for pattern generation and optimization. Please note that it takes
approximately 3-5 weeks to generate a pattern that meets all of our statistical criteria
and passes our performance tests. Back to Top 
The annualized return for a pattern is calculated by paper trading the pattern for the years
2001 through 2004. We take the total return that would have been realized and raise
that to the power of 0.25. This is the number we use for average annualized yield. Back to Top 
That is fine if you want to calculate the maximum annualized yield. That calculation
assumes that you are 100% invested 100% of the time. With the patterns used here,
that is not the case. Once in a while you will be 100% invested, but most of the time, not.
If your average cash position throughout the year were 20%, then you would realize less than 80%
of the calculated maximum annualized yield. Our pattern generating algorithms account
for average cash holdings when optimizing the patterns. Back to Top 
When the computer finds a winning pattern, it does so based on testing historical data for a limited a collection of stocks, testing to see what trades would have been executed if every buy and sell signal from a pattern had been executed on the market. We then simply look at the number of those trades that would have been winning trades compared to the total number of trades, that is our percentage of winning trades.
Determining the interval is a bit more complicated. Odds are properly expressed as
some percentage plus or minus some amount, such as 60% ± 5%. That tells us that the
true odds are actually somewhere between 55% and 65%. This is also based on confidence
level. On this site we use a 95% confidence level. The formula for the interval is
± 1.644854 * √((percentage winners)(percentage losers)/(number of trades))
Thus a 60% success rate with 100 trades would have a confidence interval of ± 8.1%, whereas if
there had been 1000 trades, the confidence interval would be ± 2.5%.
Since there is a 95% confidence level that the actual odds are within the confidence interval,
our computers search for patterns that would have generated many trades. We are basing
our buys and our sells on the notions that these patterns will repeat in the future, so the more
frequently they appeared, the greater confidence we have that they will continue to appear. Back to Top 
If you follow the buy/sell recommendations issued to you, it would be reasonable to expect your
portfolio value to increase year over year. It would not be reasonable to expect your
portfolio value to increase every month. The statistics on this site are computed
from the date of purchase to the date of sale; no account is taken for stock valuations between
these dates. If you look at charts of the stocks on the Past Recommendations page, you
will see that many of them saw valuations below the purchase price prior to being sold.
The chart on the home page shows how the portfolio value would have changed month to month during
2001 using one of our more conservative patterns. Although the portfolio would have
realized an 80% year over year return, it would have suffered declines in the months of February,
June, August, and September. In fact, the portfolio would have suffered a decline of
approximately 15% from August 1st through October 1st. Back to Top 
No! The returns on this site were calculated by averaging the last four years of returns
that any pattern would have realized had it been followed. This means that some years
have returns that are higher than the average and some years have returns that are lower than
the average. Back to Top 
If you trade in a cash account then you are subject to Federal Reserve Regulation T, which covers credits granted by brokers. Funds from sales take 3 days to clear. If these funds are used to buy and sell another security within those 3 days, then a violation of this regulation has occurred
Some of the patterns are more prone to causing these violations than others. If you indicate that you are trading in a cash account then you will be assigned patterns that, historically, have not produced Regulation T violations. We do not guarantee that the assigned pattern will not cause a violation; it is the responsibility of the subscriber to follow all applicable federal and state regulations.
If you have any questions regarding the regulations that you are subject to, you should
contact your broker. Back to Top 
First, we recommend using an online discount broker. You will be trading on our buy/sell recommendations, not on the advice of a broker.
Second, make every buy and every sell that the web site sends to you. We will not send you more recommendations than your current maximum holding limit allows.
Third, we recommend that you divide your remaining cash by the remaining number of issues you can purchase and round the result to the nearest 50 shares. Thus, if you have $60,000 remaining and your maximum holdings allows you to purchase 10 more issues, then you will divide $6,000 by the share price and round down to the nearest 50 shares.
We have prepared an Excel spreadsheet that you can use for this purpose. Back to Top 
As our computers evolve better, higher yielding, patterns, you may be reassigned one of
these new patterns. When that happens, all new buy recommendations will come from the
newly assigned pattern. Back to Top 
No. Buys will be sent to you as they are generated by the pattern assigned to you.
You may receive four or five buys in the first week or none for many weeks. The market
conditions at the time that you subscribe will usually determine the rate at which you receive
notifications. Back to Top 
No. Part of your subscription is advice to stay in cash. Cash is a position.
If your profile has you set to hold a maximum of 12 stocks but the pattern has notified you
to sell all but 3 stocks, that means that according to the statistics for the pattern, you
should be 75% in cash in order to maximize your overall return. Back to Top 