Run a backtest for all possible start months at once, and give composite
statistics. This removes seasonality effects from longer-hold screens and
can give a more accurate picture of their expected return.
Run the tester over the specified range of years. Available data
runs from 2003 through 2020 for most screens. You may
start at any month of the year, but other than January can only run
Stocks are picked from the screens every holding period (between
1 and 120 months) and held for that period.
Instead of selecting from the available screens, you may choose to
enter codes from any of the backtesters to
create hybrid tests. Simply copy the link listed at the top of a run and
paste into the form. Also see the backtester code
If you want to simulate actual trading, you can enter more parameters
in the trading simulator.
You may give your backtest a name for convenience. If you use
this backtest code in other testers, its name will be shown instead of
a full description.
Select to screen to test, and ranks on that screen.
The backtest is run twelve times, beginning in each month of the year.
Results are given for each start month, as well as a composite for all
months. Because of the delayed starts, you should run all-months
summaries for one year shorter than for other tests.