Chicago Fanatics Message Board :: View topic - Predicting the tourney with stats, 2016 edition

A grad school friend and I do it every year, put in a couple of dollars and put it in my pool (if you are interested in joining my pool, it is cheap - $5, message me). It never wins, however, it can give you some general trends on who to like/avoid. We have data going back the last 15 years for all the teams that are in the tournament a some stats (Sagarin rating, sos, rpi, conference Sagarin, conference rpi, offensive and defensive statistics as well) to create a profile of winners and losers for each round based on the past 13 years of data. In the analysis when two teams fit the "winners" profile, we have two different decision rules for the tie breaker (absolute value of winning score, difference of winner profile score - loser profile score). The absolute value tends to be more liberal, while the difference score tends to be more conservative.

Over all trends: It predicted chalk early then goes a little haywire. Typically it tends to 'like' certain conferences and 'dislike' others. The liberal DR liked the Big Ten. The conservative DR really really liked the ACC.

Difference Score (liberal decision rule) Final Four: Maryland, Oregon, Xavier, & Purdue. Final: Purdue over Oregon

Absolute Value (conservative decision rule) Final Four: Miami, Oklahoma, North Carolina, Virginia. Final: Virginia over Miami

Author:	Psycory [ Thu Mar 17, 2016 10:13 am ]
Post subject:	Predicting the tourney with stats, 2016 edition
A grad school friend and I do it every year, put in a couple of dollars and put it in my pool (if you are interested in joining my pool, it is cheap - $5, message me). It never wins, however, it can give you some general trends on who to like/avoid. We have data going back the last 15 years for all the teams that are in the tournament a some stats (Sagarin rating, sos, rpi, conference Sagarin, conference rpi, offensive and defensive statistics as well) to create a profile of winners and losers for each round based on the past 13 years of data. In the analysis when two teams fit the "winners" profile, we have two different decision rules for the tie breaker (absolute value of winning score, difference of winner profile score - loser profile score). The absolute value tends to be more liberal, while the difference score tends to be more conservative. Over all trends: It predicted chalk early then goes a little haywire. Typically it tends to 'like' certain conferences and 'dislike' others. The liberal DR liked the Big Ten. The conservative DR really really liked the ACC. Difference Score (liberal decision rule) Final Four: Maryland, Oregon, Xavier, & Purdue. Final: Purdue over Oregon Absolute Value (conservative decision rule) Final Four: Miami, Oklahoma, North Carolina, Virginia. Final: Virginia over Miami

Author:	bigfan [ Thu Mar 17, 2016 10:19 am ]
Post subject:	Re: Predicting the tourney with stats, 2016 edition
Psycory wrote: A grad school friend and I do it every year, put in a couple of dollars and put it in my pool (if you are interested in joining my pool, it is cheap - $5, message me). It never wins, however, it can give you some general trends on who to like/avoid. We have data going back the last 15 years for all the teams that are in the tournament a some stats (Sagarin rating, sos, rpi, conference Sagarin, conference rpi, offensive and defensive statistics as well) to create a profile of winners and losers for each round based on the past 13 years of data. In the analysis when two teams fit the "winners" profile, we have two different decision rules for the tie breaker (absolute value of winning score, difference of winner profile score - loser profile score). The absolute value tends to be more liberal, while the difference score tends to be more conservative. Over all trends: It predicted chalk early then goes a little haywire. Typically it tends to 'like' certain conferences and 'dislike' others. The liberal DR liked the Big Ten. The conservative DR really really liked the ACC. Difference Score (liberal decision rule) Final Four: Maryland, Oregon, Xavier, & Purdue. Final: Purdue over Oregon Absolute Value (conservative decision rule) Final Four: Miami, Oklahoma, North Carolina, Virginia. Final: Virginia over Miami Have an equal nominal amount on each dog today.

Author:	Psycory [ Thu Mar 17, 2016 10:27 am ]
Post subject:	Re: Predicting the tourney with stats, 2016 edition
First round is almost all favorites except for a few 9s and 10s. In the early days of us doing this, we would see crazy 1st round upsets (first four years we would always have a 16 defeat a 1). What we would do is put a little on the 16 (with the points) that was predicted to win and we won all four years because the 1 wouldn't cover. But now that we have more data, it has become over all more conservative. We may start limiting it to data from the past 10 years (right now we have 20 years worth of data) because the older data may not reflect what is a good winner now.

Chicago Fanatics Message Board https://mail.chicagofanatics.com/

Predicting the tourney with stats, 2016 edition https://mail.chicagofanatics.com/viewtopic.php?f=101&t=99237	Page 1 of 1

Page 1 of 1	All times are UTC - 6 hours [ DST ]
Powered by phpBB® Forum Software © phpBB Group https://www.phpbb.com/