Studies - Posted on Saturday, January 2, 2010, 11:14 PM GMT +1

3 Comments


Jan Saturday 2

How To Make Millions (in %) Trading The SPYDER – Holiday Effects

As promised this will be the second part of How To Make Millions (in %) Trading The SPYDER – Seasonalities (I). The second part will deal with potential edges provided on the long and/or short side of the market shortly before or (immediately) following exchange holidays, in order to evaluate if – and to what extent- these periodical events had – and probably will have in the future – a (significant) impact on the direction and magnitude of the next session’s change.

Please take into account that the dates presented below and their respective performance figures do NOT reflect the index’ performance on the the session itself, but the next session’s performance instead, means if -and to what extent- the respective date (periodical event) would’ve provided a favorable opportunity for going long or short on the close targeting a higher/lower close on the then following session.

You’ll find two new stats in my performance tables:

1)  Distr. of Returns (in %): Distribution of Returns, means all sessions for the respective index (S&P 500) are ranked – from best to the worst – by their daily performance (e.g. the best performing session with + 11.58% gets rank 18,100 which equals the total number of sessions within the given time frame, the  worst performing session with -20.46% gets rank 1). Then – for every trade executed for a given setup – I check which index ‘rank‘ the trade would’ve achieved (means it’s position in the descending order of daily index performances). At the end all ranks for a given setup are added, and the median ‘rank‘ will be determined. The higher the median rank (percentage-wise), the better, means the distribution of daily returns for the respective setup would be (significantly) skewed to the right.

Just to give an example: Look at Table I below. Setup 3 shows a median rank of 71.19%, means one half of the trades taken show daily returns better than 71.19% than the daily returns of the benchmark index (buy-and-hold approach). Or in other words: Almost one half of the trades taken by the setup show a performance falling into the top quartile of the respective index’ performance figures (the distribution of gains and losses is significantly positively skewed).

2) Top 10% Winners/Losers: Which percentage of the trades taken by the setup fall into the top (or worst) 10% of the best (worst) performing sessions of the respective index. The higher the percentage, the better.

Just to give an example: Look at Table I below. Setup 3 shows a Top 10% Winners percentage of 30%, which means 30% of the total number of trades taken (21 out of 70) fell into the top tenth part of the best performing index sessions (a disproportionally high percentage figure). Means the setup is able to catch the favorable big moves to a dispoportionately high extent, and (fortunately) participates in the worst performing index sessions (a negative daily return for the setup) to a dispoportionately small extent (7.14% instead of 10%).

xx

1. New Year’s Day (celebrated on January 1)

Table I below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the New Year’s Day (January 1) exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the New Year’ Day (setup 1), on the close of the session immediately preceding the New Year’s Day (setup 2), and on the close of the session immediately following the New Year’s Day (setup 3), for the time period between 01/01/1940 and 12/31/2009 (the last 70 years).

Table II below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the New Year’s Day (January 1) exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the New Year’ Day (setup 1), on the close of the session immediately preceding the New Year’s Day (setup 2), and on the close of the session immediately following the New Year’s Day (setup 3), for the time period between 01/01/1990 and 12/31/2009 (the last 20 years).

Interesting to note that setup 1 (going long on the close two sessions before the New Year’ Day) and setup 3 (going long on the close the session immediately following the New Year’ Day) show excellent long-term historical results (Profit Factor and Winning Percentage, with t-score exceeding the +1.645 mark for statistical significance), but only setup 3 stood the test of time with respect to the last 20 years (the most recent session on Dec. 31 confirmed those negative odds).

First conclusion with respect to the market model: The model will take a long position on close of the first session of a new year.

xx

2. Martin Luther King Jr. Day
(since 1998, celebrated on the 3rd Monday in January)

Table III below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the Martin Luther King Jr. Day exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the holiday (setup 1), on the close of the session immediately preceding the holiday (setup 2), and on the close of the session immediately following the holiday (setup 3), for the time period between 01/01/1998 and 12/31/2009 (the last 13 years).

It is difficult to read any statistically significant into something with 12 occurrences only (reflected by a t-score not exceeding the +1.645 mark for statistical significance despite positive performance figures).

Second conclusion with respect to the market model: The model will not take into account the Martin Luther King Jr. Day exchange holiday (at least for the time being).

xx

3. Washington’s Birthday/Presidents’ Day
(Lincoln’s Birthday, February 12, 1896-1953)
(Washington’s Birthday, February 22, since 1971 celebrated on the 3rd Monday)

Table IV below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the Presidents’ Day exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the holiday (setup 1), on the close of the session immediately preceding the holiday (setup 2), and on the close of the session immediately following the holiday (setup 3), for the time period between 01/01/1940 and 12/31/2009 (the last 70 years).

Table V below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the Presidents’ Day exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the holiday (setup 1), on the close of the session immediately preceding the holiday (setup 2), and on the close of the session immediately following the holiday (setup 3), for the time period between 01/01/1990 and 12/31/2009 (the last 20 years).

Interesting to note that form a long-term and intermediate-term historical perspective, the session(s) immediately preceding Washington’s Birthday/Presidents’ Day show a negative bias.

Third conclusion with respect to the market model: The model will not take a long position on close of the the session(s) immediately preceding Washington’s Birthday/Presidents’ Day (at least if the market doesn’t show any other requirements met, e.g. significantly oversold market conditions).

xx

4. Good Friday

Table VI below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the Good Friday exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the holiday (setup 1), on the close of the session immediately preceding the holiday (setup 2), and on the close of the session immediately following the holiday (setup 3), for the time period between 01/01/1940 and 12/31/2009 (the last 70 years).

Table VII below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the Good Friday exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the holiday (setup 1), on the close of the session immediately preceding the holiday (setup 2), and on the close of the session immediately following the holiday (setup 3), for the time period between 01/01/1990 and 12/31/2009 (the last 20 years).

Interesting to note that setup 1 (going long on the close two sessions before the Good Friday exchange holiday) shows excellent long-term and intermediate-term historical results (Profit Factor and Winning Percentage, with t-score exceeding the +1.645 mark for statistical significance).

Fourth conclusion with respect to the market model: The model will take a long position on the close two sessions before the Good Friday exchange holiday.

xx

5. Memorial Day
(celebrated on May 30 before 1971)
(celebrated on the last Monday in May since 1971)

Table VIII below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the Memorial Day exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the holiday (setup 1), on the close of the session immediately preceding the holiday (setup 2), and on the close of the session immediately following the holiday (setup 3), for the time period between 01/01/1940 and 12/31/2009 (the last 70 years).

Table IX below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the Memorial Day exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the holiday (setup 1), on the close of the session immediately preceding the holiday (setup 2), and on the close of the session immediately following the holiday (setup 3), for the time period between 01/01/1990 and 12/31/2009 (the last 20 years).

From a long-term and intermediate-term historical perspective, performance figures are mixed, and the respective t-scores do not exceed the +/-1.645 mark for statistical significance.

Fifth conclusion with respect to the market model: The model will not take into account the Memorial Day exchange holiday (at least for the time being).

xx

6. Independence Day (celebrated on July 4)

Table X below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the Independence Day exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the holiday (setup 1), on the close of the session immediately preceding the holiday (setup 2), and on the close of the session immediately following the holiday (setup 3), for the time period between 01/01/1940 and 12/31/2009 (the last 70 years).

Table XI below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the Independence Day exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the holiday (setup 1), on the close of the session immediately preceding the holiday (setup 2), and on the close of the session immediately following the holiday (setup 3), for the time period between 01/01/1990 and 12/31/2009 (the last 20 years).

From a long-term and intermediate-term historical perspective, performance figures are mixed (long-term positive, but intermediate-term negative), and the respective t-scores do not exceed the +/-1.645 mark for statistical significance.

Sixth conclusion with respect to the market model: The model will not take into account the Independence Day exchange holiday (at least for the time being).

xx

7. Labor Day (celebrated on the 1st Monday in September)

Table XII below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the Labor Day exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the holiday (setup 1), on the close of the session immediately preceding the holiday (setup 2), and on the close of the session immediately following the holiday (setup 3), for the time period between 01/01/1940 and 12/31/2009 (the last 70 years).

Table XIII below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the Labor Day exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the holiday (setup 1), on the close of the session immediately preceding the holiday (setup 2), and on the close of the session immediately following the holiday (setup 3), for the time period between 01/01/1990 and 12/31/2009 (the last 20 years).

From a long-term and intermediate-term historical perspective, performance figures are mixed (long-term positive, but intermediate-term negative), and the respective t-scores do not exceed the +/-1.645 mark for statistical significance.

Seventh conclusion with respect to the market model: The model will not take into account the Labor Day exchange holiday (at least for the time being).

xx

8. Thanksgiving Day (celebrated on the 4th Thursday in November)

Table XIV below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the Thanksgiving Day exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the holiday (setup 1), on the close of the session immediately preceding the holiday (setup 2), and on the close of the session immediately following the holiday (setup 3), for the time period between 01/01/1940 and 12/31/2009 (the last 70 years).

Table XV below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the Thanksgiving Day exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the holiday (setup 1), on the close of the session immediately preceding the holiday (setup 2), and on the close of the session immediately following the holiday (setup 3), for the time period between 01/01/1990 and 12/31/2009 (the last 20 years).

Interesting to note that setup 1 (going long on the close two sessions before the Thanksgiving Day exchange holiday) and setup 2 (going long on the close the session immediately preceding the Thanksgiving Day exchange holiday) show excellent long-term and intermediate-term historical results (Profit Factor and Winning Percentage, with the long-term t-scores exceeding the +1.645 mark for statistical significance), while setup 3 (going long on the close the session immediately following the Thanksgiving Day exchange holiday) shows a significantly negative bias, long-term and intermediate-term.

Eighth conclusion with respect to the market model: The model will take a long position on the close two sessions before and on the close of the session immediately preceding the Thanksgiving Day exchange holiday, and no long position the session immediately following the Thanksgiving Day exchange holiday, at least if not any other criteria are met.

xx

9. Christmas Day (celebrated on December 25)

Table XVI below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the Christmas Day exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the holiday (setup 1), on the close of the session immediately preceding the holiday (setup 2), on the close of the session immediately following the holiday (setup 3), and on the close two sessions after the holiday (setup 4), for the time period between 01/01/1940 and 12/31/2009 (the last 70 years).

Table XVII below shows the S&P 500‘ historical performance (Cumulative Returns, Profit Factor, Win/Loss Ratio and the t-score vs. the Index) with respect to the Christmas Day exchange holiday, assumed one would’ve bought the S&P 500 on the close two sessions before the holiday (setup 1), on the close of the session immediately preceding the holiday (setup 2), on the close of the session immediately following the holiday (setup 3), and on the close two sessions after the holiday (setup 4), for the time period between 01/01/1990 and 12/31/2009 (the last 20 years).

Interesting to note that all of those sessions surrounding the Christmas Day exchange holiday show a significantly positive bias, long-term and intermediate term. High winning percentage, a high profit factor, a very low median losing trade and t-scores close to or exceeding the +1.645 mark for statistical significance.

Ninth conclusion with respect to the market model: The model will always take a long position on the close, between two session before until two session after the Christmas Day exchange holiday.

xx

______________________

Due to the fact the this posting is getting a bit long in the tooth again, it will be continued then dealing with the respective combination of favorable calendar days (tunr-of-the-month, FOMC announcement sessions, exchange holidays, …) .

For those interested in, the model’s signals will be posted from January 4, 2010 (next Monday) onward regularly shortly before the close (but even if posted shortly after the close, the SPY is still available for trading with good liquidity and narrow spreads of regularly $0.01) via Twitter Update by following a new Twitter account @Strategy_I . (making further improvements to the model – e.g. optimization of the short side and reducing the chance of overfitting – as well as introducing position sizing, leverage, abnormal market filters, implementing buy/sell stops and probably making the model ‘adaptive‘ will be an ongoing process in 2010)

But please be reminded that past performance is never an indication (leave alone a guarantee) for future performance, and for good reason the CFTA and NFA (COMPLIANCE RULE 2-29: USE OF PROMOTIONAL MATERIAL CONTAINING HYPOTHETICAL PERFORMANCE RESULTS) requires all members (which I’m not) to explicitly reference to limitations, risks, lack of liquidity, among others, and publish a respective disclaimer.

Successful trading,
Frank

________________________________

If you might want to be instantly notified about what’s happening in the markets and at TRADING THE ODDS, I encourage you to subscribe to my RSS Feed or Email Feed, and (or) follow me on Twitter.

xx

Disclaimer: No position in the securities mentioned in this post at time of writing.

The information on this site is provided for statistical and informational purposes only. Nothing herein should be interpreted or regarded as personalized investment advice or to state or imply that past results are an indication of future performance. The author of this website is not a licensed financial advisor and will not accept liability for any loss or damage, including without limitation to, any loss of profit, which may arise directly or indirectly from use of or reliance on the content of this website(s). Under no circumstances does this information represent an advice or recommendation to buy, sell or hold any security.

Add to Technorati Favorites

Comments (3)

 

  1. […] How To Make Millions (in %) Trading The SPYDER – Holiday Effects – TRADING THE ODDS (tags: seasonal trading) […]

  2. […] Trading Odds: Interesting to note that setup 1 (going long on the close two sessions before the New Year’ Day) and setup 3 (going long on the close the session immediately following the New Year’ Day) show excellent long-term historical results (Profit Factor and Winning Percentage, with t-score exceeding the +1.645 mark for statistical significance), but only setup 3 stood the test of time with respect to the last 20 years (the most recent session on Dec. 31 confirmed those negative odds). […]

  3. […] the holidays and rising optimism prior to Fed days as people “hope” for a handout. http://www.tradingtheodds.com/2010/01/how-to-make-millions-in-trading-the-spyder-%e2%80%93-holiday-e…When we look at market breadth– and its positive association with momentum/trend returns, […]

Leave a Reply

Your email address will not be published. Required fields are marked *