United States Member #73037 April 3, 2009 147 Posts Offline

Posted: July 21, 2009, 8:06 am - IP Logged

Morning all,

I've discovered a PDF file that has intrigued me. The problem is that I don't understand what all of the symbols mean or how to write them into computer language formulas . I'm not a mathmatician nor a computer science guy. Does anyone out there have the knowledge to assist with this?

Examples from the PDF I'm looking at:

A significance test of the null hypothesis H0:θ ∈ Θ0 against the alternative hypothesis H1 :θ ∈ Θ1 is based on an observable test statistic T and a rejection region R , with associated probabilities of type I error

α = P(T ∈ R|θ ∈ Θ0) (1)

and type II error

β = P(T ∉ R|θ ∈ Θ1) (2)

To avoid spurious significant results by over-testing, we can use multiple comparisons procedures such as the Bonferroni adjustment. This involves conducting each individual test with a specified size of α|k , which gives an overall size of testing

a k k-1 2 1 kk

αk = 1-(1- ---) =α- ------ α +K+(- ----) α ~α (5)

k 2k k

I'm afraid that a lot of this is "math A" and "math B" symbols and I couldn't figure out how to copy and paste the examples properly. I attempted the reconstruction from the PDF file. If anyone can understand this and is interested, I can send you the address of the PDF file so that it can be read through for a better understanding.

Please let me know... and thanks ahead of time for any interest.

I would like to adapt this to a Pick3 game to see what the results would be.

The only DUMB question is the one question you DID NOT ask...

Looks like rocket science to me, unless you're planning a trip to Mars, you don't need to understand it.

Not planning on Mars anytime in the future, but, while I'm not trying to be rude, I am attempting to comprehend, understand, and learn something new to me. I figured that someone here might be able to explain it to me in a way that I could understand it.

Thanks anyway for the response...

The only DUMB question is the one question you DID NOT ask...

I was searching for anything that explained "forward-backward" algorithms, how they worked, and how to set one up. The PDF I discovered has to do with "Bayesian" methods for lottery draws. It's based on a study of the U.K. National Lottery. I figured that I once I understood it, I could adapt it to U.S. style lotteries and see what the results might be.

I was hoping for someone that understands this stuff well enough to explain it to me. I'm in way over my head, that's why I asked.

Thank you for the response, at least my question isn't being ignored...

The only DUMB question is the one question you DID NOT ask...

NY United States Member #23835 October 16, 2005 3648 Posts Offline

Posted: July 21, 2009, 3:24 pm - IP Logged

"I was hoping for someone that understands this stuff well enough to explain it to me."

How good an explanation do you need? My background in statistics is limited and very much atrophied, so I don't understand it well, but maybe well enough to at least help you decide how much you want to pursue it.

In a nutshell (which is about all I can manage), it's simply about using complex statistics to test the conclusions you draw from analyzing data. Drawing conclusions is easy, but drawing valid and useful conclusions is a lot more difficult, so the conclusions need to be judged for validity. Applied to lottery games, you could simply do an empirical test by waiting to see if future results adhere to your conclusion(s). For other uses, such as medical analysis, you really want to evaluate the past results and draw valid conclusions. The type 1 and 2 errors refer to incorrectly accepting or rejecting the hypothesis.

A simple lottery example would be looking at some recent results and concluding that having more 11's than 20's is because 11's are actually more likely to occur, and taking that as your first hypothesis. There are many other possible explanations, so if there's was any risk in simply accepting the first hypothesis (or a benefit in finding a better hypothesis) it makes sense to compare it to other hypotheses. As for the details of the math behind it, you're welcome to take it as far as you want. At a guess, you'd be looking at a couple of semesters of advanced math, along with a couple of semesters of statistics, as a minimum. Personally, I'm happy with the hypothesis that lottery results are random for all practical purposes.

New Jersey United States Member #17843 June 28, 2005 71175 Posts Offline

Posted: July 21, 2009, 3:33 pm - IP Logged

Quote: Originally posted by KnuckleHead on July 21, 2009

Morning all,

I've discovered a PDF file that has intrigued me. The problem is that I don't understand what all of the symbols mean or how to write them into computer language formulas . I'm not a mathmatician nor a computer science guy. Does anyone out there have the knowledge to assist with this?

Examples from the PDF I'm looking at:

A significance test of the null hypothesis H0:θ ∈ Θ0 against the alternative hypothesis H1 :θ ∈ Θ1 is based on an observable test statistic T and a rejection region R , with associated probabilities of type I error

α = P(T ∈ R|θ ∈ Θ0) (1)

and type II error

β = P(T ∉ R|θ ∈ Θ1) (2)

To avoid spurious significant results by over-testing, we can use multiple comparisons procedures such as the Bonferroni adjustment. This involves conducting each individual test with a specified size of α|k , which gives an overall size of testing

a k k-1 2 1 kk

αk = 1-(1- ---) =α- ------ α +K+(- ----) α ~α (5)

k 2k k

I'm afraid that a lot of this is "math A" and "math B" symbols and I couldn't figure out how to copy and paste the examples properly. I attempted the reconstruction from the PDF file. If anyone can understand this and is interested, I can send you the address of the PDF file so that it can be read through for a better understanding.

Please let me know... and thanks ahead of time for any interest.

I would like to adapt this to a Pick3 game to see what the results would be.

When it comes to Statistics: Nothing is Simple: Maybe this will Help:

I was searching for anything that explained "forward-backward" algorithms, how they worked, and how to set one up. The PDF I discovered has to do with "Bayesian" methods for lottery draws. It's based on a study of the U.K. National Lottery. I figured that I once I understood it, I could adapt it to U.S. style lotteries and see what the results might be.

I was hoping for someone that understands this stuff well enough to explain it to me. I'm in way over my head, that's why I asked.

Thank you for the response, at least my question isn't being ignored...

Honduras Member #20982 August 29, 2005 4715 Posts Offline

Posted: July 21, 2009, 4:39 pm - IP Logged

LOoking at your formula, i noticed some stuff on it that i did in Statistic class but do i remember what it was? the answer is no...

A lot of PDF files relating to the lottery and showing mathematics on it have to do with Statistic...And is not much statistic but probability class..YOu see probability class is the next step after statistics...

If you REALLY, really, REALLY want to understand probability or statistics buy yourself a statistic texbook but make sure is the older edition...They cost like 5 dollars on ebay...They got other websites that sell older editions of statistic class textbook...And you can begin reading them, the texbooks are like 200 or 250 pages...

if you understand the statistic class texbooks and probability class texbooks you can understand most of the PDF files that deal with lotteries and have mathematical formulas on them...

The Forex trades: 1.6 Trillion dollars EVERY day, that´s more than the GDP of the Carribbean Central America, COMBINED. Enough to feed every crook out there for centuries...To all Geniuses & Powers Countries of the World the Planet needs breakthroughs in all Medicine, Veterinary, Biology related fields, Psychology, Population Psychology/Sociology..They need to genetically ingeneer new plants species/types to give more variety of plants and thus have more resources for combating diseases¨

United States Member #73037 April 3, 2009 147 Posts Offline

Posted: July 21, 2009, 5:07 pm - IP Logged

Thanks everybody for the suggestions and directions, and yes, the other algorithm post is mine. I'm still trying to decifer it... without much luck I need to add. But, nothing good every comes without learning something new...

I understand that all of you have more knowledge and experience than I, but, as I was recently told, new ideas are welcome. I believe that I'm looking at this from a different direction. Maybe it'll work, maybe not. All it requires is the time to look into it.

Thank you all again.

The only DUMB question is the one question you DID NOT ask...

Honduras Member #20982 August 29, 2005 4715 Posts Offline

Posted: July 21, 2009, 5:46 pm - IP Logged

Quote: Originally posted by pumpi76 on July 21, 2009

LOoking at your formula, i noticed some stuff on it that i did in Statistic class but do i remember what it was? the answer is no...

A lot of PDF files relating to the lottery and showing mathematics on it have to do with Statistic...And is not much statistic but probability class..YOu see probability class is the next step after statistics...

If you REALLY, really, REALLY want to understand probability or statistics buy yourself a statistic texbook but make sure is the older edition...They cost like 5 dollars on ebay...They got other websites that sell older editions of statistic class textbook...And you can begin reading them, the texbooks are like 200 or 250 pages...

if you understand the statistic class texbooks and probability class texbooks you can understand most of the PDF files that deal with lotteries and have mathematical formulas on them...

unfortunately i don't live in the USA other wise i'd have had my library of texbooks and read them all...

The Forex trades: 1.6 Trillion dollars EVERY day, that´s more than the GDP of the Carribbean Central America, COMBINED. Enough to feed every crook out there for centuries...To all Geniuses & Powers Countries of the World the Planet needs breakthroughs in all Medicine, Veterinary, Biology related fields, Psychology, Population Psychology/Sociology..They need to genetically ingeneer new plants species/types to give more variety of plants and thus have more resources for combating diseases¨

I looked at the sites, now need to figure out which ones to get.

I realize that what I'm attempting to do is different than everyone else, but, if what everyone else was doing always worked, the lotteries would cease due to the amount of continuious winners...

Lotteries are for the most part chance, but if an edge can be discovered...

The only DUMB question is the one question you DID NOT ask...

New Jersey United States Member #17843 June 28, 2005 71175 Posts Offline

Posted: July 22, 2009, 12:25 pm - IP Logged

Quote: Originally posted by KnuckleHead on July 21, 2009

Thanks everybody for the suggestions and directions, and yes, the other algorithm post is mine. I'm still trying to decifer it... without much luck I need to add. But, nothing good every comes without learning something new...

I understand that all of you have more knowledge and experience than I, but, as I was recently told, new ideas are welcome. I believe that I'm looking at this from a different direction. Maybe it'll work, maybe not. All it requires is the time to look into it.

Thank you all again.

Understanding the Notation used in the Formulas will go a long way toward understanding the Formulas: