Jump to content

Chi Square & Other Tests of Statistical Significance


Recommended Posts

I'm probably the furthest thing away from a statistically competent person as you can get, so was looking for a little input. I've managed to gather somewhat useful data for all NBA regular season games dating back to the 2002/03 season inclusive. This equates to something like 8758 games. I've then set about finding good criteria for ATS (line) betting, looking for correlation by inputting parameters that make causative sense. Obviously whether I've found correlation or causation is going to be somewhat subjective. Anyway, I've so far managed to find 3 successful set of parameters, but in all cases the sample size is relative small, and in two games, microscopically so. My question, then, is what sort of statistical tests do I apply to test the strength/statistical significance of these criteria, and how do I interpret the results. I've been trying to read about Chi Square tests but it's only served to confused me. I understand what to put in for observed data, but I'm a bit loss as to what I put in for expected. Do I just multiply the total number of bets by the percentage implied by average odds? This is what I tried, but even if correct, I still don't understand the numbers that were returned to me :lol For the record (Format is Bets: Wins-Losses-Pushes): Criteria A -- 86: 50-34-2 Criteria B -- 51: 30-20-1 Criteria C -- 399: 227-168-4 I'm assuming all odds will average out at 1.952, the average odds for a line bet on Pinnacle. If anyone could shed some light using words my brain can understand, it would be greatly appreciated :ok

Link to comment
Share on other sites

Re: Chi Square & Other Tests of Statistical Significance say you have 100 bets with 60 winners and 40 losers you now have to estimate the bookies expected winners and losers. first find your average odds (say 2.00) then find your average overound (say 10%) multiply ave odds & ave overound (2.00 * 1.10 = 2.20) change above to a %age (1/2.2 = 0.45 ) multiply total bets by above result 100 * 0.45 = 45 winners therefore 55 losers now you have your factors to put in CHITEST in excell A1= 60 B1= 45 A2= 40 B2= 55 this should give you =CHITEST(A1:A2,B1:B2) result should be 0.002569 or 0.25% which equates to .25% luck or 99.75 good judgement :dude Dont bother with it myself but there you go. :ok

Link to comment
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

×
×
  • Create New...