Monday, October 16, 2017

2017 NCAA FBS Top 25 Ranking for Week 7

Below is the Top 25 ranked teams using the Complex Invasion College Football Production Model from the data provided at www.cfbstats.com.  According to the Complex Invasion College Football production model, Alabama is back on top as the most productive team in all of the Football Bowl Subdivision as of the end of last week. Links to the previous weeks rankings for this season are at the bottom of the page.

Rank Team
1 Alabama
2 Ohio State
3 Washington
4 Penn State
5 South Florida
6 Wisconsin
7 Oklahoma State
8 UCF
9 North Carolina State
10 Oklahoma
11 TCU
12 Miami (Florida)
13 Auburn
14 Georgia
15 Texas Tech
16 Michigan
17 Southern Mississippi
18 Stanford
19 USC
20 Minnesota
21 Texas A&M
22 Clemson
23 Arizona
24 Iowa State
25 Virginia

Previous 2017 Top 25 Rankings
2017 NCAA FBS Top 25 Rankings for Week #6
2017 NCAA FBS Top 25 Rankings for Week #5
2017 NCAA FBS Top 25 Rankings for Week #4
2017 NCAA FBS Top 25 Rankings for Week #3
2017 NCAA FBS Top 25 Rankings for Week #2

Wednesday, October 11, 2017

2017 MLB Pay and Performance

Last week I blogged about competitive balance in MLB.  Now I want to turn to the relationship between MLB payroll and MLB performance.  I have looked at this using USA Today MLB team payroll data in the past (2015 and 2016), but now I want to use data from spotrac.com for MLB.  I find that the data from spotrac is excellent and probably more accurate than the USA Today MLB team payroll data.  The data from spotrac starts in 2011, so I have a smaller time frame to work with, but I thought it would be good to see if the relationship between payroll and performance differs using a different set of MLB team payroll data.  If you are interested in doing this type of analysis, here is a step-by-step guide to payroll and performance analysis.

So, after collecting and organizing the 2011 through 2017 MLB team payroll and team performance data, I ran the regression on team performance using relative payroll as the independent variable.  I use a software package called Stata for the statistical analysis and found that relative payroll is positive and statistically significant with respect to MLB team performance, just like I have found in each previous time I have done this type of statistical analysis using data from USA Today.  The coefficient on relative payroll is 0.06868, which means that a one unit increase in relative payroll will lead to a 0.06868 increase in team winning percent.  In terms of wins, the regression results show that a one unit increase in relative payroll would result in just over 11 additional wins.  In order to get those wins, a MLB team would have to increase team payroll by one unit of relative payroll, which is the same thing as average payroll.  For the 2017 MLB season, that is an increase of $152,327,084 using data from spotrac.  So those approximately 11 wins would cost about $13,690,875 per win.  That is a rather costly amount to pay for each win.

Finally, the regression results show that while the relationship between MLB team performance and relative payroll is positive and statistically significant, the amount that relative payroll "explains" of MLB team performance is not that much.  In this case, using data from spotrac, the explanatory power of the regression is rather weak, with an adjusted r-squared equal to 0.127.  Another way of saying that is that relative payroll only "explains" 12.7% of MLB team performance.  I will let you decide if you think that is good enough.  But will state that there are other variables that explain a greater amount of MLB team performance than relative payroll.

Tuesday, October 10, 2017

Gary Andersen Departs as Head Football Coach at Oregon State

Gary Andersen has departed as head football coach at Oregon State University yesterday.  Andersen was under contract until 2021, but decided it was best for the program to leave now, with the Beavers currently 1-5, their only victory over FCS Portland State in their second game of the season.  So, here is a look at Oregon State since Andersen's arrival.

Below is a chart of offense, defense and total production of the Oregon State Beavers football program during Andersen's tenure as head football coach, along with who would be the lowest ranked team during this time period (in purple) and the average team (sky blue).   Oregon State has been below average each season under his tenure. All rankings in this blog come from my Complex Invasion College Football Production Model.  More details about the program under Andersen are after the chart below as well as a link to his contract.


Gary Andersen [2015 - 2017*]

2015
In head coach Andersen's first year at the helm of the Beavers football team, Oregon State  finished the regular season overall at 2-10 (bowl ineligible).  Oregon State played against a "tougher" strength of schedule (SOS) as compared to the "league" average SOS, meaning that Oregon State's SOS was between one and two standard deviations lower than the "league" average SOS.  The Beavers best game again was their victory over #60 ranked San Jose State (35-21), and their worst loss was to #87 ranked Colorado (13-17).  Oregon State had the #120 ranked team in total production with the #113 ranked offense and the #113 ranked defense from the Complex Invasion College Football Production Model.

2016
At the end of the regular season the Beavers were again bowl ineligible with a 4-8 win/loss record, while playing against an "average" strength of schedule (SOS) as compared to the "league" average SOS, meaning that UTEP had an SOS plus or minus one standard deviation of the "league" average SOS.  The Miners best win was over #98 ranked California (47-44) and their worst loss was to #70 ranked UCLA by a score of (24-38).  Oregon State had the #95 ranked team in total production with the #90 ranked offense and the #74 ranked defense from the Complex Invasion College Football Production Model.

2017
Near the halfway mark of the regular season the Beavers are 1-5, while playing against a "much tougher" strength of schedule (SOS) as compared to the "league" average SOS, meaning that Oregon State's SOS is lower than two standard deviations of the "league" SOS.  The Beavers only victory to date was over FCS Portland State and their worst loss was to currently ranked #34 Minnesota by a score of (14-48).  At the time of Andersen's departure, Oregon State had the #123 ranked team in total production (that is the worst team), with the #116 ranked offense and the #118 ranked defense from the Complex Invasion College Football Production Model

Monday, October 9, 2017

2017 NCAA FBS Top 25 Ranking for Week 6

Below is the Top 25 ranked teams using the Complex Invasion College Football Production Model from the data provided at www.cfbstats.com.  According to the Complex Invasion College Football production model, Washington is now the most productive team in all of the Football Bowl Subdivision as of the end of last week. Links to the previous weeks rankings for this season are at the bottom of the page.

Rank Team
1 Washington
2 Alabama
3 Ohio State
4 Penn State
5 Washington State
6 Georgia
7 Clemson
8 Notre Dame
9 Wisconsin
10 Oklahoma
11 UCF
12 Virginia Tech
13 Auburn
14 Louisville
15 Wake Forest
16 Miami (Florida)
17 San Diego State
18 Oregon
19 TCU
20 Texas Tech
21 West Virginia
22 Michigan State
23 USC
24 Colorado State
25 Kansas State

Previous 2017 Top 25 Rankings
2017 NCAA FBS Top 25 Rankings for Week #5
2017 NCAA FBS Top 25 Rankings for Week #4
2017 NCAA FBS Top 25 Rankings for Week #3
2017 NCAA FBS Top 25 Rankings for Week #2

Friday, October 6, 2017

2017 MLB Competitive Balance

With the 2017 MLB regular season finished, let's take a look at competitive balance using the Noll-Scully measure of competitive balance.  The Noll-Scully uses the actual standard deviation of a league's winning percentage and compares it to a league if wins and losses were randomly determined in a statistical sense.  A Noll-Scully of 1.000 indicates wins and losses were randomly determined and thus the league is perfectly balanced in a competitive sense.  A Noll-Scully higher indicates that the league is less than perfectly balanced.  As the value increases the league is less competitive.

For the 2017 MLB regular season, we see that the American League had a competitive balance of 1.658 and the National League had a competitive balance of 1.897, meaning that the National League was less competitive than the American League.  Overall, MLB had a Noll-Scully of 1.783, which is slightly more competitive than the league average Noll-Sculy since 1982.

If you are interested in doing this on your own, here is a step-by-step guide to calculate the Noll-Scully measure of competitive balance using Microsoft Excel.  

Wednesday, October 4, 2017

2017 MLB Regular Season Attendance

Today I will look at regular season home attendance in MLB.  To do so I grabbed the data from ESPN. First thing to note is that overall regular season attendance has decreased by 488,645 fans from the 2016 regular season and the 2016 regular season dropped by about 600,000 fans from the 2015 season.  Yes, that is a million fewer people attended a MLB game in 2017 as compared to 2015.

The three largest attendance declines were Kansas City (-337,342), Pittsburgh (-329,574) and the New York Mets (-328,980), and the three largest attendance increases were Atlanta (484,338), Cleveland (456,471) and Colorado (351,126).

While total attendance and average attendance are lower this regular season as compared to the 2016 regular season, is it statistically different from the previous regular season?  We need a statistical tool to determine if attendance is different between the two regular seasons with some degree of confidence.  The statistical tool I use is a t-test as the means to perform the analysis.

A t-test looks at the differences between attendance for two regular seasons average home attendance and allows us to judge the difference between their means relative to the variability of their regular season average home attendance.  You can quickly perform a t-test in Microsoft Excel =t.test(...).  I choose to use a two tailed test, since regular season average home attendance can increase and decrease as compared to the previous regular season.

I am going to look at regular season average home attendance for the 2016 and 2017 MLB season, just like I did for the 2016 MLB regular season.  The reason I am looking at average attendance is that not all teams play the same number of home games from one season to the next and using the average is a much more accurate for comparing one season to another.

So after running the t-test between the 2016 and 2017 regular season home attendance using a paired t-test, a t-tests where the sample variance is assumed to be equal, and a t-test where the sample variance is not assumed to be unequal; in each case, the result of the t-test is that it fails to accept (rejects) that regular season average home attendance is different between the two seasons.

That might not be much consolation to the Royals, Pirates and Mets, but the decline in attendance is not significant as compared to the prior regular season.

Monday, October 2, 2017

2017 NCAA FBS Top 25 Ranking for Week 5

Below is the Top 25 ranked teams using the Complex Invasion College Football Production Model from the data provided at www.cfbstats.com.  According to the Complex Invasion College Football production model, Alabama is now the most productive team in all of the Football Bowl Subdivision as of the end of last week. Links to the previous weeks rankings for this season are at the bottom of the page.

Rank Team
1 Alabama
2 Washington
3 Penn State
4 Ohio State
5 Clemson
6 South Florida
7 Washington State
8 Oregon
9 Oklahoma
10 Louisville
11 Georgia
12 Wisconsin
13 Virginia Tech
14 Oklahoma State
15 Auburn
16 Wake Forest
17 TCU
18 Notre Dame
19 North Carolina State
20 Miami (Florida)
21 Kansas State
22 UCF
23 SMU
24 Texas A&M
25 Utah

Previous 2017 Top 25 Rankings
2017 NCAA FBS Top 25 Rankings for Week #4
2017 NCAA FBS Top 25 Rankings for Week #3
2017 NCAA FBS Top 25 Rankings for Week #2