Rolling Standard Deviation?

[Sarge85]

I'm focusing more and more on tracking my results. I've been through the archives and essays and have figured out how to compute my SD, and feel like I know what I'm looking at.

My question is - How do I update my SD?

Should I just use a long "chain" of data and continue to update it-

OR

Should I use a "rolling" SD? I thought if I used a rolling 50 session (is 50 to low or high) SD it would reflect a more current picture of "how I'm playing now" effect.

While I don't have my intial SD numbers when I first started poker, I'm sure it would have been much higher than what it is now.

Comments-?

[Nottom]

You have to look at your play as a whole.

Winrate needs many thousands of hands to converge an a fairly reasonable approximation, SD converges faster but you still need to look at your total play so it isn't biased towards a current streak. It may be concievable to track a rolling average to see if you are improving, but it would have to be on a scale of 10's of thousands of hands or hundreds of hours to be meaningful.

[Mangatang]

Yeah, I think you need to use a rolling SD and winrate. Make sure to pick a significant amount of hands though, maybe like 5,000 or 10,000 hands, or maybe more.

Then you can see how you are improving or falling behind as time goes on. If all you did was keep a total average, once you get tens of thousands of hands, you will be late in catching any changes in your current play, because there is so much history in your sample dominating the average.

Still keep a total average though too. It should be worth it to compare the rolling average to the total average also.

Actually, at work, we use a time-weighted moving average to track product qualities (at an oil refinery). It is like using a rolling average, but instead of a finite number of samples to look back at, it still uses every single sample in the history, but it weights the more recent ones more heavily.

[rigoletto]

Do both. 50 sessions are a pretty short timespand but it'll help you pick up/confirm major changes in your regular games.

[Al_Capone_Junior]

Keep in mind the more samples you have the more accurate it is. I would not do the rolling method, I would keep it updated all the time. Use excel (not sure if stat king does this but it might).

al

[Sarge85]

[ QUOTE ]
Keep in mind the more samples you have the more accurate it is. I would not do the rolling method, I would keep it updated all the time. Use excel (not sure if stat king does this but it might).

al

[/ QUOTE ]

I agree, but I'm wondering if a more recent sample session would be more indicative of "how I'm doing now."

I'm quite new to statistics and accurate poker tracking skills.

I flip flop between $.50/$1.00 and $1.00/$2.00 regularly. Would I skew my data too much if I doubled my results of $.50/$1.00 sessions to use in my spreadsheet - or I am just better off using two separate sheets for the different limits.

[Al_Capone_Junior]

Use different spreadsheets for each limit, don't double it.

You can always calculate subsets of your data but still keep a running tab for all of it.

al