Most of us are using insufficient data for testing

Discussions about the testing and simulation of mechanical trading systems using historical data and other methods. Trading Blox Customers should post Trading Blox specific questions in the Customer Support forum.
Moto moto
Roundtable Knight
Roundtable Knight
Posts: 427
Joined: Mon Jun 01, 2009 4:12 am
Location: once again in the UK

Post by Moto moto »

The Zurich Axioms....a highly recommended book. Simple....but the best things are.
AFJ - check out Electroniclocal now you have more time(he is a day trader, but he mixes discretion with algos) and while yes he sells stuff, he has a lot of other interesting info as well.

Plus whats wrong with just investing a proportion of your money with a LTTF....I could not make a business of it (no PHD, no sales and marketing, no seed capital to make it work well enough) so I just give it to others and trade shorter term discretionary strategies.....diversify, diversify, diversify - then watch it closely.
Work out which one makes you worry more, then increase the size in it if it also makes the most money.
(still wont stop me wanting to stick a fork n Corzines eye)
:wink:
Chris67
Roundtable Knight
Roundtable Knight
Posts: 1052
Joined: Tue Dec 16, 2003 2:12 pm
Location: London

Post by Chris67 »

well said AFJ
But I do think that people like Curtis were not stupid as if you remember he said - always expect the un-expected and then you will never be wrong !!!

We are at a real crossroads arent we - it really looks and feels like TF is in trouble - but we just aint gonna know for a few more years - i suspect this may be the calm before the storm !!! but as you say diversification works
I also think if you can stomach it TF will continue to work but not in an investor friendly fashion - i.e. there could be short burts of extreme profitability followed by 18 months of crap
watch this space .. and AFJ thanks for a very thought provoking and important post
C
rhc
Roundtable Knight
Roundtable Knight
Posts: 464
Joined: Tue Nov 18, 2008 8:46 pm
Location: Oz

Post by rhc »

sluggo wrote:I greatly enjoyed The Zurich Axioms by Max Gunther.
Here's a laugh.
The outspoken, Mr. Victor Neiderhoffer reckons;
The Zurich Axioms by Max Gunther is one of the worst books ever written . . . . . . A totally worthless book
http://www.dailyspeculations.com/wordpress/?p=428

He didn't even say "one of the worst financial books". Simply just, "one of the worst books" . . . presumably encompassing all books ever written.??!! Wow, what a statement.

******
Also I should add that this book exists as a 'pdf' in the public domain.
A quick google search should find it for those that are interested in a loose leaf format
Moto moto
Roundtable Knight
Roundtable Knight
Posts: 427
Joined: Mon Jun 01, 2009 4:12 am
Location: once again in the UK

Post by Moto moto »

Victor is a speculator, statistician and from what i can gather great at focusing on a specific area of expertise....and when he does not he gets into trouble.
The book is for generalists, everyday rules of thumb that are most likely wrong when applied for speculation and statistical analysis, but can be helpful to keep a grounding of thought for keeping out of too much trouble for longer term wealth generation/captial maintenance.
I think if you mix the two - then yes (it along with many others) should be thrown out.......but its a romance novel not a how to fix a nuclear reactor manual.
If it gets classed as the worst book written it must be good. :lol:
stopsareforwimps
Roundtable Knight
Roundtable Knight
Posts: 199
Joined: Sun Oct 10, 2010 1:47 am
Location: Melbourne Australia

Post by stopsareforwimps »

Moto moto wrote:Victor is a speculator...
Not everyone may be aware that Victor's long term compound rate of return is -100%. His investment approach seemed to be counter-trend. Such a strategy can result in smooth returns followed by catastrophic drawdowns.

His books are very entertaining and possibly informative as well. I particularly liked "Education of a Speculator".

Victor took exception at a female relation's description of him as a 'commodity gambler' but perhaps she was right.
Last edited by stopsareforwimps on Sat Mar 17, 2012 4:23 am, edited 1 time in total.
rhc
Roundtable Knight
Roundtable Knight
Posts: 464
Joined: Tue Nov 18, 2008 8:46 pm
Location: Oz

Post by rhc »

In the very first sentence of this thread, Trading Leech wrote:Are most of us using sufficient data for testing? I'm starting to doubt it.
and then further down
babelproofreader wrote:If you don't have enough data for back testing, why not create it?
Another alternative to creating new data/overcoming the problem of limited data is to use the very handy ‘Random portfolio Blox’
(2 versions available – Original version & Altered version)
I have used both versions on many occasions in my testing and have found them to be very Very useful.

The author of the original version, user ‘nickmar’ says;
How about the use of randomized portfolios instead of synthetic data as a means of testing system robustness
Read more here if you are interested;
viewtopic.php?p=22315#22315
Post Reply