Home
Forums
New Posts
Illini Basketball
Illini Football
Sports Talk
Log in
Register
What's new
Menu
Log in
Register
Install the app
Install
Forums
Sports
Illini Basketball
Illinois 69, Ohio State 60 Postgame
JavaScript is disabled. For a better experience, please enable JavaScript in your browser before proceeding.
You are using an out of date browser. It may not display this or other websites correctly.
You should upgrade or use an
alternative browser
.
Reply to thread
Message
<blockquote data-quote="aaeismacgychel" data-source="post: 1853692" data-attributes="member: 748794"><p>This was part of a study attempting to understand whether the data that comes from the overtime period is statistically important when it comes to predicting future matchups against the same opponent and he found out that the score effects in those 5 minutes of overtime do show predictive behavior of the overall score effects in the future matchup. So in other words, having overtime data is more important to a predictive software than not having that data and as such it should not be omitted. </p><p></p><p>As for which portions of the games are most relevant, I actually don't believe he's done a full study analyzing the predictive nature of certain portions of games outside of this. One thing I can say is that the season worth of games of data's predictive value is way more important than that of any single game and a single game is more important than any specific time period within a game as we're talking about an order of magnitude more data points. So Kenpom isn't saying that OT is more predictive than the entire game, just that it is predictive in nature of score effects. Hope that clarifies things a bit better</p></blockquote><p></p>
[QUOTE="aaeismacgychel, post: 1853692, member: 748794"] This was part of a study attempting to understand whether the data that comes from the overtime period is statistically important when it comes to predicting future matchups against the same opponent and he found out that the score effects in those 5 minutes of overtime do show predictive behavior of the overall score effects in the future matchup. So in other words, having overtime data is more important to a predictive software than not having that data and as such it should not be omitted. As for which portions of the games are most relevant, I actually don't believe he's done a full study analyzing the predictive nature of certain portions of games outside of this. One thing I can say is that the season worth of games of data's predictive value is way more important than that of any single game and a single game is more important than any specific time period within a game as we're talking about an order of magnitude more data points. So Kenpom isn't saying that OT is more predictive than the entire game, just that it is predictive in nature of score effects. Hope that clarifies things a bit better [/QUOTE]
Verification
Post reply
Forums
Sports
Illini Basketball
Illinois 69, Ohio State 60 Postgame
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.
Accept
Learn more…