Quick Links You last visited December 7, 2016, 8:59 pm All times shown are Eastern Time (GMT5:00)  IonSaliu GeneratorS.Windsor, CT United States Member #4580 May 4, 2004 119 Posts Offline  Posted: February 24, 2005, 4:32 pm  IP Logged  
Quote: Originally posted by RJOh on February 24, 2005
Quote: Originally posted by Hyperdimension on February 24, 2005
Quote: My interest is based on a desire to find a formula for predicting the std.dev. for any set of lotto numbers.
Saliu,
Why you keep in secret the formula?
Hyperdimension, do you think Saliu is the only one to keep the good stuff to himself? People who want to share their best ideas usually write a book and sell it, even people who want to share some worthless ideas do it too. RJOh
RJohn, Selfrespecting scientists share their ideas with others in publications. Those whe claim they have a solution to a problem but refuse to demonstrate it are usually regarded as crack pots. The formula can have only marginal value if any. Deriving one would be an intellectual challenge and yield personal satisfaction. It would not help to win lottos, except to add another filter of marginal use. Bertil
  
East of Atlanta United States Member #6191 August 11, 2004 1389 Posts Offline  Posted: February 24, 2005, 5:23 pm  IP Logged  
I guess my little elevator just doesn't go all the way up cause I fail to understand what all the ruckuss is over the concept of standard deviation. For me, if I wanna know something like standard deviation or other unusual math related issues, I find a simple web search can turn up a good deal of information for example, a search for "standard deviation" in Yahoo gave me the following: Here is one formula for computing the standard deviation. A warning, this is for math geeks only! Writers and others seeking only a basic understanding of stats don't need to read any more in this chapter. Remember, a decent calculator and stats program will calculate this for you...
Terms you'll need to know x = one value in your set of data avg (x) = the mean (average) of all values x in your set of data n = the number of values x in your set of data
For each value x, subtract the overall avg (x) from x, then multiply that result by itself (otherwise known as determining the square of that value). Sum up all those squared values. Then divide that result by (n1). Got it? Then, there's one more step... find the square root of that last number. That's the standard deviation of your set of data.
Now, remember how I told you this was one way of computing this? Sometimes, you divide by (n) instead of (n1). It's too complex to explain here. So don't try to go figuring out a standard deviation if you just learned about it on this page. Just be satisified that you've now got a grasp on the basic concept.
The more practical way to compute it... In Microsoft Excel, type the following code into the cell where you want the Standard Deviation result, using the "unbiased," or "n1" method:
 =STDEV(A1:Z99) (substitute the cell name of the first value in your dataset for A1, and the cell name of the last value for Z99.)
Or, use...  =STDEVP(A1:Z99) if you want to use the "biased" or "n" method.
(acknowledgements to http://nilesonline.com/stats/stdev.shtml for this tidbit) Maybe I am just to simple to understand what the situation here is...but I do understand the concept of keeping it simple. Sir Metro A man who is good does the right thing when others are watching...a good man does the right thing even when no one is watching.   
S.Windsor, CT United States Member #4580 May 4, 2004 119 Posts Offline  Posted: February 24, 2005, 7:38 pm  IP Logged  
Quote: Originally posted by SirMetro on February 24, 2005
I guess my little elevator just doesn't go all the way up cause I fail to understand what all the ruckuss is over the concept of standard deviation. For me, if I wanna know something like standard deviation or other unusual math related issues, I find a simple web search can turn up a good deal of information for example, a search for "standard deviation" in Yahoo gave me the following: Here is one formula for computing the standard deviation. A warning, this is for math geeks only! Writers and others seeking only a basic understanding of stats don't need to read any more in this chapter. Remember, a decent calculator and stats program will calculate this for you...
Terms you'll need to know x = one value in your set of data avg (x) = the mean (average) of all values x in your set of data n = the number of values x in your set of data
For each value x, subtract the overall avg (x) from x, then multiply that result by itself (otherwise known as determining the square of that value). Sum up all those squared values. Then divide that result by (n1). Got it? Then, there's one more step... find the square root of that last number. That's the standard deviation of your set of data.
Now, remember how I told you this was one way of computing this? Sometimes, you divide by (n) instead of (n1). It's too complex to explain here. So don't try to go figuring out a standard deviation if you just learned about it on this page. Just be satisified that you've now got a grasp on the basic concept.
The more practical way to compute it... In Microsoft Excel, type the following code into the cell where you want the Standard Deviation result, using the "unbiased," or "n1" method:
 =STDEV(A1:Z99) (substitute the cell name of the first value in your dataset for A1, and the cell name of the last value for Z99.)
Or, use...
 =STDEVP(A1:Z99) if you want to use the "biased" or "n" method.
(acknowledgements to http://nilesonline.com/stats/stdev.shtml for this tidbit) Maybe I am just to simple to understand what the situation here is...but I do understand the concept of keeping it simple. Sir Metro A man who is good does the right thing when others are watching...a good man does the right thing even when no one is watching.
Sir Metro, Let me try to explain the problem. Calcuating the std.dev. for any set of five random out of ten is a simple task with a hand held calculator. The values can range from 1.58 to 4.18 but the 5/10 lotto type game has 252 combinations and their std.dev. does not form a bell curve and thus the mean will not be (1.58+4.18)/2=2.88. One can easily determine the mean std.dev. for all 252 individual combinations by generating all 252. The value will be 2.97. But there is no known formula for predicting tis value. If we go to the 5/15 lotto we must generate 3003 unique combinations, for the 5/20 we need 15504 combination and for the 5/25 we must get 53130 combinations it we wish to test every possible combination. With the proper software this might be done and each combination could then be tested for std.dev. and a mean could be established for the set. By testing 1000 random samples from any given lotto I hope to obtain the mean. Once I have the means I would get together with a professional and try to work out a general formula. I hope this explains in a nut shell what I'm trying to do. Such a project could possibly qualify for a master thesis or better, but I'm too old to enrole as a student. Bertil
  
East of Atlanta United States Member #6191 August 11, 2004 1389 Posts Offline  Posted: February 24, 2005, 10:54 pm  IP Logged  
This is sadly amazing...I initially provided insight as to how to access an ActiveX code on somebody's web site and now I am being told about how to figure standard deviations and I didn't even ask...sheesh...punish me some more for trying to be helpful. Is it a full moon or something tonite??? Sir Metro I know not what I ask and I ask not what I know.   
midOhio United States Member #9 March 24, 2001 19828 Posts Offline  Posted: February 24, 2005, 11:59 pm  IP Logged  
Quote: Originally posted by Bertil on February 24, 2005
RJohn, Selfrespecting scientists share their ideas with others in publications. Those whe claim they have a solution to a problem but refuse to demonstrate it are usually regarded as crack pots. The formula can have only marginal value if any. Deriving one would be an intellectual challenge and yield personal satisfaction. It would not help to win lottos, except to add another filter of marginal use. Bertil
I've never thought of this forum as repository of ideas where self respecting scientists could share and demonstrate their theories and strategies for playing the lotteries as an intellectual challenge. Just my opinion. RJOh
* you don't need to buy more tickets, just buy a winning ticket *
  
S.Windsor, CT United States Member #4580 May 4, 2004 119 Posts Offline  Posted: February 25, 2005, 8:57 am  IP Logged  
Quote: Originally posted by RJOh on February 24, 2005
Quote: Originally posted by Bertil on February 24, 2005
RJohn, Selfrespecting scientists share their ideas with others in publications. Those whe claim they have a solution to a problem but refuse to demonstrate it are usually regarded as crack pots. The formula can have only marginal value if any. Deriving one would be an intellectual challenge and yield personal satisfaction. It would not help to win lottos, except to add another filter of marginal use. Bertil
I've never thought of this forum as repository of ideas where self respecting scientists could share and demonstrate their theories and strategies for playing the lotteries as an intellectual challenge. Just my opinion. RJOh
This forum is:"The place to discuss the strong ties between lotteries and math". Silly me, I did not know one must have money making as a primary interest to participate here. My reason is purely intellectual curiosity and a hope to meet up with likeminded souls. There is an outstanding book on the math of lotto: "How to win more" by N.Henze. But he does not discuss the problem of interest to me. However, H.Schneider does in a superficial way in his book:"Lottery numbers". He determined the std.dev. for two 6/49 lottos but limited his analysis to 50 draws. That is not a sufficient basis for a sound analysis. I wish to find a mathematically correct formula. Anybody can perform a test on any lotto with a few hundred or better yet thousand draws and obtain a practical range, that would help to eliminate the most unlikely selections, and thus serve as a filter,together with other filters. Another very good book about lotto math is:"The Lottery Book" by Don Catlin. All three books stress the absurdity of thinking one can find a formula for winning the jack pot. Bertil
  
United States Member #12495 March 15, 2005 76 Posts Offline  Posted: March 21, 2005, 12:28 am  IP Logged  
By reading through all the posters in this link, I got the impression that IonSaliu is right, and Bertil should bother him no further. If Bertil's stated interest is true, he would be interested in all combinations, not radom subsets. A loop program to cover all possibilities might take forever to run, but program by itself should be quite simple. I am wondering what is behind all that.   
