I have corrected the gross oversight where I failed to apply a simple test for the effect that ordering has on the K-ratio.
It doesn't stand up too well, but the same thing would apply to all metrics that use linear regression I guess. Due to the semi-random nature of the markets, ordering of any magnitude isn't likely in the real world so perhaps it isn't a concern. I have uploaded K-ratio_v2.xls to the file section of this group. It has an additional worksheet for reordering - it doesn't have any instructions for that sheet - a knowledge of Excel is assumed: - open worksheet K-ratio long example re-ordered! - F9 to force a recalc - note the final equity and K-ratio metrics - copy column E and paste special as values into column F - use the toolbar icon to sort ascending and then descending and watch the above metrics change (sort on row F only - do not include the data columns next to row F). Note that equity outcome is independent of the GrowthFactor (Geomean/PowerFactor) order but that the K-ratio value changes with re-ordering. (the files aren't permanent - later I will take them down - maybe they will find a new home). Hope that helps add some clarity to evaluation metric discussion, particularly K-ratio. brian_z --- In [email protected], "brian_z111" <[EMAIL PROTECTED]> wrote: > > Grant & Gerry, > > I have added another worksheet to the K-ratio.xls file in the file > section of this group. > Instructions are included - you can change the inputs to 'stress > test' the K-ratio with different types of equity curves. > > I am confident the file allows us to form a reasonable view on the > strengths and weaknesses of the K, despite the fact that it is not > mathematically sophisticated. > > I find it a reliable metric. > I don't see any evidence that it is prone to time dependence. > I do find it a conservative metric - if the equity curve has above > ave variance the K forces us to find high growth systems. > > The corresponding weakness is that if the variance is extremely low > it can 'pass' very low growth systems. > > All in all a quite safe metric to use providing its benign weaknesses > are allowed for (I say benign because if a low growth/low variance > system is incorrectly selected the end result won't be a total > disaster). > > Anyway - the file will let you decide for yourself. > > brian_z > > > --- In [email protected], Grant Noble <gruntus@> wrote: > > > > > The K-ratio isn't worth the space it takes up: RRR is simpler. > > > > care to elaborate? > > > > gerryjoz wrote: > > > In an earlier post, expectancy was associated with profit factor. > > > It is more closely related to payoff ratio. > > > In Van Tharp's book, 2nd edition, "Trade your way...", page 204 et > > > seq, he calculates > > > Expectancy = average profit/ # trades > > > divided by average loss. > > > Payoff ratio is average profit/average loss, > > > so > > > Expectancy = payoff ratio/# trades. > > > --which can give very low numbers, and makes the concept rather > > > dubious if you are using it as an absolute value for comparing > systems > > > with different numbers of trades. It might be better to use > trades per > > > annum. > > > To be fair Van Tharp only gives that way of calculating > expectancy as > > > a default if the risk of a trade isn't able to be calculated > taking > > > into account a pre-determined proportion of equity. For that, you > need > > > to read the whole chapter. > > > Personally i find CAR/MDD, RRR more relevant, along with the raw > > > Payoff ratio. > > > > > > The K-ratio isn't worth the space it takes up: RRR is simpler. > > > > > > regards > > > Gerry > > > > > > > > > > > > > > > > > > ------------------------------------ > > > > > > Please note that this group is for discussion between users only. > > > > > > To get support from AmiBroker please send an e-mail directly to > > > SUPPORT {at} amibroker.com > > > > > > For NEW RELEASE ANNOUNCEMENTS and other news always check DEVLOG: > > > http://www.amibroker.com/devlog/ > > > > > > For other support material please check also: > > > http://www.amibroker.com/support.html > > > Yahoo! Groups Links > > > > > > > > > > > > > > >
