Attn: Sigma Hunters

General TSP Discussion.

Moderator: Aitrus

User avatar
fordest
Posts: 605
Joined: Wed Sep 26, 2012 3:48 pm

Attn: Sigma Hunters

Post by fordest »

In your quest for the highest Mean/StD. ratio, how low of a mean are you willing to take?

I found a 10.06 But the mean is 28.6: 16252

The best >30 I have made so far was a 7.75: 16366
100% in the daily system since August 2, 2017.
Following strategy (current pick) #88676. 2020 real life has been following #110838

User avatar
onerepmax
Posts: 138
Joined: Tue Aug 08, 2017 9:29 am

Re: Attn: Sigma Hunters

Post by onerepmax »

It seems like the sweet spot is 28-31% mean.

User avatar
mhende2
Posts: 87
Joined: Wed Oct 12, 2016 12:32 pm

Re: Attn: Sigma Hunters

Post by mhende2 »

Take a look at 16198.
2004-2016 Mean 30.59, SD 4.88, CAGR 30.50, Total Comp Rtn 4,053.84
2005 Lowest Total 25.99
2010 Highest Total 39.31
2017 YTD 21.53

If that's correct, it's sure low enough SD and very consistent return to satisfy me.
In investing, what is comfortable is rarely profitable.
-Robert Arnott

User avatar
fordest
Posts: 605
Joined: Wed Sep 26, 2012 3:48 pm

Re: Attn: Sigma Hunters

Post by fordest »

mhende2 wrote:Take a look at 16198.
2004-2016 Mean 30.59, SD 4.88, CAGR 30.50, Total Comp Rtn 4,053.84
2005 Lowest Total 25.99
2010 Highest Total 39.31
2017 YTD 21.53

If that's correct, it's sure low enough SD and very consistent return to satisfy me.


Yes. That one is amazing. The one in my sig is almost the same except a couple days in May. Slightly higher return and lower StD to date this year. So with the rest of the year identical to 16198 it'll be slightly better come January.
100% in the daily system since August 2, 2017.
Following strategy (current pick) #88676. 2020 real life has been following #110838

User avatar
evilanne
Posts: 2067
Joined: Thu May 14, 2015 6:52 pm

Re: Attn: Sigma Hunters

Post by evilanne »

Removing the move to F in November (a week longer in C), I came up with the following from 3 of the strategies mentioned above:
16384 (7.08) --->16447 (7.63)
16198 (7.21) --->16450 (8.40)
16366 (7.75) --->16448 (9.17) (Mean=29.35)
# in Parenthesis=Sigma though 2016. The change results in lower mean & lower Standard Deviation but higher Sigma -- seems counter intuitive but given how the market has performed this year and the uncertainty of the F Fund with proposed Fed actions, it might be worth the risk especially when looking at the higher sigma.

User avatar
Ofsthun01
Posts: 127
Joined: Thu Dec 04, 2014 6:57 pm

Re: Attn: Sigma Hunters

Post by Ofsthun01 »

I must have missed something. What's sigma?
Your Free Financial Advisor. Zero trading costs
https://www.wisebanyan.com/referral/92F0PFFWI

Dela444
Posts: 19
Joined: Tue Jun 07, 2016 8:54 am

Re: Attn: Sigma Hunters

Post by Dela444 »

I READ HERE THE OTHER DAY ABOUT #16013. MEAN 29 SD 4.8 :D

JoeMurphy
Posts: 10
Joined: Sat Apr 01, 2017 8:42 am

Re: Attn: Sigma Hunters

Post by JoeMurphy »

My question as well.

ksmoly04
Posts: 66
Joined: Thu Oct 06, 2016 2:08 pm

Re: Attn: Sigma Hunters

Post by ksmoly04 »

JoeMurphy wrote:My question as well.

Ofsthun01 wrote:I must have missed something. What's sigma?


Please refer to this [url="http://tspcenter.com/forums/viewtopic.php?f=14&t=14940"]topic[/url]. 12squared provides a thorough discussion on sigma, which is simply the result of mean/standard deviation. His discussion on its application to the various daily strategies and how reliable the strategy is outstanding.
Daily Seasonal Since: August 23, 2017
Current Strategy: 16198 / 7.21σ

User avatar
TopComm
Posts: 78
Joined: Thu Jun 03, 2010 7:02 pm

Re: Attn: Sigma Hunters

Post by TopComm »

Ofsthun01 wrote:I must have missed something. What's sigma?


Sigma (σ) is the number of standard deviations away from the mean. It is determined by dividing the mean by the standard deviation. From a risk perspective, you can determine how risky a strategy is by the sigma calculation:
1σ = 32% of the returns will be outside 1σ (higher or lower) 16% chance of a loss
2σ = 4.5% of the returns will be outside 2σ (higher or lower) 2.25% chance of a loss
3σ = 1 year out of 370 years may be a loss
4σ = 1 year out of 15,787 years may be a loss
5σ = 1 year out of 1,744,278 years may be a loss
6σ = 1 year out of 506,797,346 years may be a loss
7σ = 1 year out of 390,682,215,445 years may be a loss

Age of the Earth 4.5 Billion years
Age of the Universe 13.7 Billion years
7σ = 390 Billion years

So any 7σ should be pretty safe from a loss. BTW since I've been on Fantasy TSP, I've had three years with a loss. This should be way better than what I was doing.

User avatar
12squared
Posts: 675
Joined: Thu Dec 31, 2015 7:28 am

Re: Attn: Sigma Hunters

Post by 12squared »

Now that many high sigma strategies have been identified, it may make sense to base the choice on the minimal return, not the minimal Mean. In that case,
σX = (Mean - X) / SD
where X is the minimal acceptable return, or quality control "defect" limit.
When X = 0, σ0 = Mean / SD

For example, if I am retiring in 5 years and need to double my balance before then, I need an annual return of at least 15% per year (1.15^5 = 2.01), i.e. X = 15.
Given two strategies, having Means & SDs of 25 & 5 and 30 & 7.5, which is more likely to achieve this over the next 5 years?
σ15 = (30 - 15) / 7.5 = 2.00
σ15 = (25 - 15) / 5 = 2.00

Because σ15 is 2.0 for each, the likelihood of achieving 15% is the same. If instead we needed X of 20%, the 1st combination is better.
σ20 = (30 - 20) / 7.5 = 1.33
σ20 = (25 - 20) / 5 = 1.00

If we needed only 10%, the 2nd combination is better.
σ10 = (30 - 10) / 7.5 = 2.67
σ10 = (25 - 10) / 5 = 3.00
“The genius of investing is recognizing the direction of the trend – not catching the highs or the lows.”
- Dean Witter

"Put all your eggs in one basket and then watch that basket."
- Andrew Carnegie

User avatar
fordest
Posts: 605
Joined: Wed Sep 26, 2012 3:48 pm

Re: Attn: Sigma Hunters

Post by fordest »

I love this evolution that is going on here. So now, I can apply the minimum % I'd like to get. I will call mine 18%. We can now use TopComms table above with this change...

1σ = 32% of the returns will be outside 1σ (higher or lower) 16% chance of under 18%
2σ = 4.5% of the returns will be outside 2σ (higher or lower) 2.25% chance of under 18%
3σ = 1 year out of 370 years may be under 18%
4σ = 1 year out of 15,787 years may be under 18%

My strategy gives me σX of 3.
100% in the daily system since August 2, 2017.
Following strategy (current pick) #88676. 2020 real life has been following #110838

mmmmmbeer
Posts: 917
Joined: Wed May 11, 2016 11:00 am

Re: Attn: Sigma Hunters

Post by mmmmmbeer »

I'm pretty sure you've all switched to a different languange in this thread. Oe incomprehensible and silly.
Those who 'abjure' violence can do so only because others are committing violence on their behalf.

mhayes
Posts: 44
Joined: Sun Sep 17, 2017 2:20 pm

Re: Attn: Sigma Hunters

Post by mhayes »

I think we need to start learning their language if we want to succeed. :(

User avatar
Ofsthun01
Posts: 127
Joined: Thu Dec 04, 2014 6:57 pm

Re: Attn: Sigma Hunters

Post by Ofsthun01 »

12squared wrote:Now that many high sigma strategies have been identified, it may make sense to base the choice on the minimal return, not the minimal Mean. In that case,
σX = (Mean - X) / SD
where X is the minimal acceptable return, or quality control "defect" limit.
When X = 0, σ0 = Mean / SD

For example, if I am retiring in 5 years and need to double my balance before then, I need an annual return of at least 15% per year (1.15^5 = 2.01), i.e. X = 15.
Given two strategies, having Means & SDs of 25 & 5 and 30 & 7.5, which is more likely to achieve this over the next 5 years?
σ15 = (30 - 15) / 7.5 = 2.00
σ15 = (25 - 15) / 5 = 2.00

Because σ15 is 2.0 for each, the likelihood of achieving 15% is the same. If instead we needed X of 20%, the 1st combination is better.
σ20 = (30 - 20) / 7.5 = 1.33
σ20 = (25 - 20) / 5 = 1.00

If we needed only 10%, the 2nd combination is better.
σ10 = (30 - 10) / 7.5 = 2.67
σ10 = (25 - 10) / 5 = 3.00


If this is the kind of math they presented in school and illustrated this practical application, I may have paid more attention.
Your Free Financial Advisor. Zero trading costs
https://www.wisebanyan.com/referral/92F0PFFWI

Post Reply

Fund Prices2024-03-27

FundPriceDayYTD
G $18.14 0.01% 1.00%
F $19.09 0.26% -0.68%
C $82.11 0.87% 10.42%
S $82.19 1.48% 6.61%
I $42.68 0.56% 6.21%
L2065 $16.38 0.84% 8.36%
L2060 $16.38 0.84% 8.36%
L2055 $16.39 0.84% 8.36%
L2050 $32.73 0.71% 6.94%
L2045 $14.91 0.67% 6.56%
L2040 $54.37 0.63% 6.20%
L2035 $14.34 0.58% 5.77%
L2030 $47.66 0.53% 5.35%
L2025 $13.14 0.31% 3.40%
Linc $25.60 0.24% 2.79%

Live Charts

Pending Allocations

Under development. For now, you may view Pending Allocations by going to "fantasy TSP" and selecting "Leaderboard sort" of "Pending Allocations".