My backtested system consistently beats the S&P500

Quote from StockTrader1985:

Hey guys,

I usually stick to trading currencies, but a few days ago I decided to run a backtest on a system that's based on value investing. Using objective criteria over the first 100 stocks that fit the criteria, I ran the backtest over every year from 1998 through 2006, annually. Although I have saved the results in an excel spreadsheet, here's a quick breakdown of the results:

1) My system returned an average of 11.98% over almost 9 and half years, while the S&P returned an average of 4.64% over the same period of time

2) My total return over the period is 187.46%, while the S&P returned 52.75%

My question is, how do I verify that this backtest is legitimate? Are there statistical tests that I can run to ensure that the system's success would also apply to today's markets?

And lastly, if I am confident in my system, how do I setup a managed fund so that I can trade other people's money?

Thanks
More...
================
Stocky-T-85;.
a]Does that include slippage, comissions???????[most s&p 500 numbers do not, ouch]

b] Even though 1998 ,99 uptrends & the bear market following were MUCH better than average trends, at least you tested both bull/bear. Wish real time results matched backtest;but
sounds like its worth trading ,small start anyway.

c] See if it 's validated or violates by any or many principles in 3 top trader books by Jack Schwager
and Curtis Faith, WAY of the TURTLE book .:cool:

Plans of the diligent tend only to advantage.
 
Just a quick observation -

Is it based on small caps or large companies?

You have to calculate the return on a risk adjusted basis to mean anything or at least calculate some portfolio performance statistics like - alpha.

If you're going to try to manage OPM you should know how.
 
Dear Stocktrader1985,

I don't know your system but make sure you have accounted for survivorship bias in your backtesting.

"Survivorship bias is the tendency for failed companies to be excluded from performance studies due to the fact that they no longer exist. It often causes the results of studies to skew higher because only companies which were successful enough to survive until the end of the period are included."

riskette. mba
 
Quote from murray t turtle:

================
Stocky-T-85;.
a]Does that include slippage, comissions???????[most s&p 500 numbers do not, ouch]

b] Even though 1998 ,99 uptrends & the bear market following were MUCH better than average trends, at least you tested both bull/bear. Wish real time results matched backtest;but
sounds like its worth trading ,small start anyway.

c] See if it 's validated or violates by any or many principles in 3 top trader books by Jack Schwager
and Curtis Faith, WAY of the TURTLE book .:cool:

Plans of the diligent tend only to advantage.
More...

Thanks for the response

1) no, it does not include slippage and comissions. However, I've always been under the impression that slippage doesn't make a huge deal when backtesting equities. I'm assuming that I'm purchasing 100 stocks at the beginning of every year. What percent of the reported annual returns will commission and slippage eat out o?

2) I know 98 was the worst year for me in the backtest, and the only way I can explain that is because, like I said, my system is based on value investing models which look for stocks that are undervalued by the market. The great bull market of those years weren't due to undervalued stocks, but stocks that were actually overvalued but were still being pushed forward by the market. Of course, this is what eventually led to the stock market bubble. Therefore, my system doesn't detect these stocks, so I miss out. But on the whole, I am able to buy conservative stocks that are, based on probability, expected to go up rather than down (in case you're wondering, I don't short any stocks in the backtest)

3) Not familiar with the TURTLE book, or these "principles" that you speak of. Could you elaborate?
 
Quote from blackchip:

Just a quick observation -

Is it based on small caps or large companies?

You have to calculate the return on a risk adjusted basis to mean anything or at least calculate some portfolio performance statistics like - alpha.

If you're going to try to manage OPM you should know how.
More...

1) Large cap, in fact one requirement is that the company's market cap must be at least a billion. I ran the system over small cap, and although I beat the s&p500, the results weren't as great as the large-cap test. However, since the two tests are mutually exclusive, I think that should add legitimacy to my system. What do you guys think?

2) how do you calculate return on risk adjusted basis? are you talking about drawdown, or standard deviation?

also, are there any objective tests I can run based on the stock's balance sheet and/or income statement? like I said, I'm looking for something objective

EDIT: I will also be running the tests on foreign equities in the near future. I will keep you all updated
 
Quote from riskette:

Dear Stocktrader1985,

I don't know your system but make sure you have accounted for survivorship bias in your backtesting.

"Survivorship bias is the tendency for failed companies to be excluded from performance studies due to the fact that they no longer exist. It often causes the results of studies to skew higher because only companies which were successful enough to survive until the end of the period are included."

riskette. mba
More...

definetly don't have surviorship bias. when selecting stocks for each year in the past, I go through the list of stocks available at that point in time to make the decision, along with their financial data
 
You must log in or register to reply here.
Back
Top