Two Plus Two Older Archives  

Go Back   Two Plus Two Older Archives > General Poker Discussion > Poker Theory

Reply
 
Thread Tools Display Modes
  #1  
Old 03-29-2004, 02:43 PM
BruceZ BruceZ is offline
Senior Member
 
Join Date: Sep 2002
Posts: 1,636
Default Beware of StatKing!

Based on some data from lorinda in a post on the internet forum, I can see that StatKing does not compute bankroll and risk of ruin properly, and this feature should not be used. It apparently uses the same method described in GTAOT which is useless for this purpose. The bankroll it gives you for a 1% risk of ruin will actually give you a 6.7% risk of ruin.

For those of you using similar statistical software, please post data similar to lorinda's so that we can see if any other programs are affected.

As always, use the formulas from this thread for bankroll calculations.
Reply With Quote
  #2  
Old 03-29-2004, 04:40 PM
Inthacup Inthacup is offline
Senior Member
 
Join Date: Sep 2002
Location: Inthacup
Posts: 2,706
Default Re: Beware of StatKing!

Bruce, you are truly a man-beast when it comes to statistics. Kudos.


Cup
Reply With Quote
  #3  
Old 03-29-2004, 11:46 PM
Dov Dov is offline
Senior Member
 
Join Date: Oct 2003
Location: Chicago, IL
Posts: 277
Default Re: Beware of StatKing!

For us non-mathematicians, could someone please tell us how to create an excel spreadshhet formula for B = -(sigma^2/2u)ln(r) ?

Thanks in advance.

By the way, Bruce, your posts have inspired me to learn statistics. Thanks!
Reply With Quote
  #4  
Old 03-29-2004, 11:57 PM
DcifrThs DcifrThs is offline
Senior Member
 
Join Date: Aug 2003
Posts: 677
Default Re: Beware of StatKing!

[ QUOTE ]
For us non-mathematicians, could someone please tell us how to create an excel spreadshhet formula for B = -(sigma^2/2u)ln(r) ?

Thanks in advance.

By the way, Bruce, your posts have inspired me to learn statistics. Thanks!

[/ QUOTE ]

no problem...i can field this one for ya...at least i think my job as an economist for the government qualifies me for it lol...

in any case its just a substitution question you have. Sigma is the sample standard deviation you have calculated already. u is the win rate your hourly expectation and r is the amount of risk (in percents) you are willing to assume.

so in excel you link the standard deviation cell to sigma, win rate to u, and manually enter say a 1% risk of going broke.

hope this helps.
-Barron
Reply With Quote
  #5  
Old 03-30-2004, 12:31 AM
Homer Homer is offline
Senior Member
 
Join Date: Sep 2002
Posts: 5,909
Default Re: Beware of StatKing!

For us non-mathematicians, could someone please tell us how to create an excel spreadshhet formula for B = -(sigma^2/2u)ln(r) ?

Go to cell A1, type <font color="blue">Bankroll</font>
Go to cell A2, type <font color="blue">Standard Deviation</font>
Go to cell A3, type <font color="blue">Win Rate</font>
Go to cell A4, type <font color="blue">Risk of Ruin</font>

(Double-click on the vertical line between Column A and Column B to widen Column A)

Go to cell B1, type <font color="blue">=-(B2^2/(2*B3))*ln(B4)</font>
Go to cell B4, then click on Format -&gt; Cells -&gt; Number (Tab) -&gt; Percentage, and click OK

Then, you can mess around with it by entering different numbers for SD, WR and ROR in cells B2 through B4.

To verify that it's working, enter an SD of 11 in B2, a WR of 1 in B3 and an ROR of 1 (this should show up as 1.00%) in B4. Bankroll should then automatically compute and read out as 278.6128.

If you can't get it working, send me a PM and I can make a spreadsheet for you.

-- Homer
Reply With Quote
  #6  
Old 03-30-2004, 02:02 AM
MrFroggyX MrFroggyX is offline
Senior Member
 
Join Date: Nov 2003
Location: Sweden
Posts: 211
Default Re: Beware of StatKing!

Grst post homer!

But I have a few questions..

I use pokercharts to track my play and now i wonder which number I'm going to use for the Standard Devation

Is it:
1. Return Standard Devation (Standard devation from the mean return over the specifed dates)
or is it:
Win Rate Standard Devation (Standard devation from the mean win rate over the specifed dates)

I don't understand what the diffrence between them are?

Reply With Quote
  #7  
Old 04-01-2004, 11:46 AM
ZootMurph ZootMurph is offline
Senior Member
 
Join Date: Mar 2004
Posts: 151
Default Re: Beware of StatKing!

Can someone post the formula in Excel for the Risk of Ruin {r = exp(-2uB/sigma^2)} as well?

Thanks!
Reply With Quote
  #8  
Old 04-01-2004, 12:54 PM
BruceZ BruceZ is offline
Senior Member
 
Join Date: Sep 2002
Posts: 1,636
Default Re: Beware of StatKing!

Copy and paste Homer's cells B1-B4 to C1-C4. Type a number in for the bankroll in C1, instead of the equation that is there now. Then click in C4 and enter:

=exp(-2*C3*C1/C2^2)

C4 is the risk of ruin, and now you can vary the other 3 numbers.
Reply With Quote
Reply

Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump


All times are GMT -4. The time now is 07:19 PM.


Powered by vBulletin® Version 3.8.11
Copyright ©2000 - 2024, vBulletin Solutions Inc.