yes you've understood the weighting of correlations to trade sizes correctly.
the "brute force" approach you mentioned earlier is an apt description for what i would do if i were auto testing. just to see what kind of results i got back. for example, if you mess with the correlation threshold (T) while keeping time (t) for the table constant what results do you get back?
in this way you could also build a n-dimension lookup table of pairs, correlation, time and threshold for starters. it's impossible to do this thing manually but i would be interested to see if any patterns emerge in the result-sets.
for my purposes i would just stick with a 2d look up table with good values for T and t. for example would T follow a normal or skewed distribution curve?
the "brute force" approach you mentioned earlier is an apt description for what i would do if i were auto testing. just to see what kind of results i got back. for example, if you mess with the correlation threshold (T) while keeping time (t) for the table constant what results do you get back?
in this way you could also build a n-dimension lookup table of pairs, correlation, time and threshold for starters. it's impossible to do this thing manually but i would be interested to see if any patterns emerge in the result-sets.
for my purposes i would just stick with a 2d look up table with good values for T and t. for example would T follow a normal or skewed distribution curve?
Quoting RoBiKDislikedhi iso,
maybe i written too much, and it is hard to understand my point... sorry for that english is not my mother tongue so that is a small problem too. i will try to reduce it somehow.
first let me ask, if i understand your goal.
in simplified terms, you are trying to use the correlation tables to determine some weights for your possitions in different pairs, right?
let's assume you are doing it only for two currency pairs (with more pairs involved concurrently, the problem gets exponentially bigger)
you want to achieve that by trying different combinations of weights - directly derived from the corresponding correlation between the two currency pairs.
i'm missing one thing... let's suppose you make such tests (ussing weights from 0 to 1 with step 0.1), what do you do with the results? what exactly are the results? what values are you interested in? how do you want to compare them? how do you select the best one?
ok, i will wait for your answers, so i'm sure i understand your goals.
thank you
RoBiKIgnored