Stadium_Waste-Descriptive_Analysis_5

Author

Jingyi Yang

Install Packages

library(skimr)
library(summarytools)
library(readxl)
library("readr")
library("tidyverse")

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ purrr     1.0.4
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.5.2     ✔ tibble    3.2.1
✔ lubridate 1.9.4     ✔ tidyr     1.3.1
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
✖ tibble::view()  masks summarytools::view()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(dplyr)

Import the Data

str(data)

tibble [1,396 × 69] (S3: tbl_df/tbl/data.frame)
 $ Conference                                                           : chr [1:1396] "Pac12" "Pac12" "Pac12" "Pac12" ...
 $ School                                                               : chr [1:1396] "Arizona State" "Arizona State" "Arizona State" "Arizona State" ...
 $ City                                                                 : chr [1:1396] "Tempe" "Tempe" "Tempe" "Tempe" ...
 $ State                                                                : chr [1:1396] "AZ" "AZ" "AZ" "AZ" ...
 $ Area Classification (0-Rural; 1-Urban)                               : num [1:1396] 0 0 0 0 0 0 0 0 0 0 ...
 $ Date                                                                 : chr [1:1396] "44813" "44822" "44830" "44844" ...
 $ Year                                                                 : num [1:1396] 2015 2015 2015 2015 2015 ...
 $ Opponent                                                             : chr [1:1396] "Cal Poly" "UNM" "USC" "Colorado" ...
 $ Tenure Year                                                          : num [1:1396] 1 1 1 1 1 1 1 2 2 2 ...
 $ S_Game                                                               : num [1:1396] 1 2 3 4 5 6 7 1 2 3 ...
 $ S_Trash (tons)                                                       : num [1:1396] 4.45 5.56 7.99 3.83 5.04 ...
 $ S_Recycle (tons)                                                     : num [1:1396] 3.34 3.09 2.88 3.67 5.34 3.7 5.39 2.13 1.19 6.45 ...
 $ S_Compost                                                            : num [1:1396] 0.15 0.8 0.8 1.4 1.6 2.37 0.6 0 1.6 0.8 ...
 $ S_Other (e.g. Food Donation, reuse)                                  : num [1:1396] 0 0 0 0 0 0 0 0 0 0 ...
 $ S_Waste Total                                                        : num [1:1396] 7.94 9.45 11.67 8.9 11.98 ...
 $ S_Diversion                                                          : num [1:1396] 0.44 0.412 0.315 0.57 0.579 ...
 $ T_Trash                                                              : num [1:1396] 0 0 0 0 0 0 0 1.2 1.53 2.76 ...
 $ T_Recycle                                                            : num [1:1396] 0 0 0 0 0 0 0 0.09 0 0.07 ...
 $ T_Organics                                                           : num [1:1396] 0 0 0 0 0 0 0 0 0 0 ...
 $ T_Waste Total                                                        : num [1:1396] 0 0 0 0 0 0 0 1.29 1.53 2.83 ...
 $ T_Diversion                                                          : num [1:1396] 0 0 0 0 0 ...
 $ Tot_Trash                                                            : num [1:1396] 4.45 5.56 7.99 3.83 5.04 ...
 $ Tot_Recycle                                                          : num [1:1396] 3.34 3.09 2.88 3.67 5.34 3.7 5.39 2.22 1.19 6.52 ...
 $ Tot_Compost                                                          : num [1:1396] 0.15 0.8 0.8 1.4 1.6 2.37 0.6 0 1.6 0.8 ...
 $ Tot_Waste Total                                                      : num [1:1396] 7.94 9.45 11.67 8.9 11.98 ...
 $ Tot_Diversion                                                        : num [1:1396] 0.44 0.412 0.315 0.57 0.579 ...
 $ Attendance                                                           : chr [1:1396] "46500" "43310" "61904" "44157" ...
 $ Game Time                                                            : POSIXct[1:1396], format: "1899-12-31 20:00:00" "1899-12-31 19:00:00" ...
 $ Game Weather                                                         : chr [1:1396] NA NA NA NA ...
 $ Game result (Win=1; Loss=0)                                          : chr [1:1396] "1" "1" "0" "1" ...
 $ Tailgate included                                                    : num [1:1396] 0 0 0 0 0 0 0 1 1 1 ...
 $ S_Per Capita Waste Generation (lbs)                                  : num [1:1396] 0.342 0.436 0.377 0.403 0.424 ...
 $ S_Per Capita Trash  (lbs)                                            : num [1:1396] 0.191 0.257 0.258 0.173 0.178 ...
 $ S_Per Capita Recycling (lbs)                                         : num [1:1396] 0.144 0.143 0.093 0.166 0.189 ...
 $ Per Capita Waste Diversion - All (S+T) (lbs)                         : num [1:1396] 0.15 0.18 0.119 0.23 0.246 ...
 $ Per Capita Compost - Stadium (lbs)                                   : num [1:1396] 0.00645 0.03694 0.02585 0.06341 0.0566 ...
 $ Per Capita Compost - All (lbs)                                       : num [1:1396] 0.00645 0.03694 0.02585 0.06341 0.0566 ...
 $ Per Capita Diversion (Stadium) (lbs)                                 : num [1:1396] 0.15 0.18 0.119 0.23 0.246 ...
 $ Total per capita waste generation [kg]                               : num [1:1396] 0.171 0.218 0.189 0.202 0.212 ...
 $ Stadium per capita waste generation [kg]                             : num [1:1396] 0.171 0.218 0.189 0.202 0.212 ...
 $ Total per capita waste Diversion [kg]                                : num [1:1396] 0.0751 0.0898 0.0594 0.1148 0.1228 ...
 $ Stadium per capita waste diversion [kg]                              : num [1:1396] 0.0751 0.0898 0.0594 0.1148 0.1228 ...
 $ Athletic Dept Profit                                                 : num [1:1396] 566524 566524 566524 566524 566524 ...
 $ Total Expenses                                                       : num [1:1396] 83873516 83873516 83873516 83873516 83873516 ...
 $ Student-Athlete Meals (Non-Travel)                                   : num [1:1396] NA NA NA NA NA ...
 $ Excess Transfers Back                                                : num [1:1396] 0 0 0 0 0 0 0 0 0 0 ...
 $ Total Coaching Severance                                             : num [1:1396] 2741105 2741105 2741105 2741105 2741105 ...
 $ Other Expenses                                                       : num [1:1396] 10642925 10642925 10642925 10642925 10642925 ...
 $ Medical                                                              : num [1:1396] 1846329 1846329 1846329 1846329 1846329 ...
 $ Competition Guarantees                                               : num [1:1396] 1552205 1552205 1552205 1552205 1552205 ...
 $ Recruiting                                                           : num [1:1396] 1174263 1174263 1174263 1174263 1174263 ...
 $ Game Expenses and Travel                                             : num [1:1396] 9375181 9375181 9375181 9375181 9375181 ...
 $ Facilities, Debt Service, and Equipment                              : num [1:1396] 14915036 14915036 14915036 14915036 14915036 ...
 $ Coaches Compensation                                                 : num [1:1396] 17775568 17775568 17775568 17775568 17775568 ...
 $ Non-Coaching Athletics Staff Compensation                            : num [1:1396] 12506364 12506364 12506364 12506364 12506364 ...
 $ Athletic Student Aid                                                 : num [1:1396] 11344540 11344540 11344540 11344540 11344540 ...
 $ Total Revenues                                                       : num [1:1396] 84440040 84440040 84440040 84440040 84440040 ...
 $ Other Revenue                                                        : num [1:1396] 3670889 3670889 3670889 3670889 3670889 ...
 $ Corporate Sponsorship, Advertising, Licensing                        : num [1:1396] 10279135 10279135 10279135 10279135 10279135 ...
 $ Donor Contributions                                                  : num [1:1396] 14770823 14770823 14770823 14770823 14770823 ...
 $ Competition Guarantees2                                              : num [1:1396] 0 0 0 0 0 ...
 $ Conference/NCAA Distributions, Media Rights, and Post-Season Football: num [1:1396] 25298010 25298010 25298010 25298010 25298010 ...
 $ Ticket Sales                                                         : num [1:1396] 1.1e+07 1.1e+07 1.1e+07 1.1e+07 1.1e+07 ...
 $ Institutional/Government Support                                     : num [1:1396] 9421830 9421830 9421830 9421830 9421830 ...
 $ Student Fees                                                         : num [1:1396] 9957302 9957302 9957302 9957302 9957302 ...
 $ Total Academic Spending (University-Wide)                            : num [1:1396] 1.11e+09 1.11e+09 1.11e+09 1.11e+09 1.11e+09 ...
 $ Total Football Spending                                              : num [1:1396] 27569960 27569960 27569960 27569960 27569960 ...
 $ Athletics Related Debt                                               : num [1:1396] 83075000 83075000 83075000 83075000 83075000 ...
 $ Annual Debt Service, Leases and Rental Fees on Athletic Facilities   : num [1:1396] 5020000 5020000 5020000 5020000 5020000 ...

Clean the data

Select the column

data_clean <- data %>% select(`Conference`, `School`, `Area Classification (0-Rural; 1-Urban)`, `Year`, `Tenure Year`, `S_Game`, `S_Diversion`, `Attendance`, `Game Time`,`Game result (Win=1; Loss=0)`,`Athletic Dept Profit`, `Total Expenses`, `Total Revenues`)
data_clean$`Game Time`=format(data_clean$`Game Time`, format = "%H:%M")
data_clean <- data_clean %>% mutate(`Game Time`= as.character(`Game Time`)) %>% mutate(`Area Classification (0-Rural; 1-Urban)`= as.character(`Area Classification (0-Rural; 1-Urban)`)) %>% mutate(`Attendance`= as.numeric(`Attendance`))

Warning: There was 1 warning in `mutate()`.
ℹ In argument: `Attendance = as.numeric(Attendance)`.
Caused by warning:
! NAs introduced by coercion

head(data_clean)

# A tibble: 6 × 13
  Conference School        Area Classification (0-R…¹  Year `Tenure Year` S_Game
  <chr>      <chr>         <chr>                      <dbl>         <dbl>  <dbl>
1 Pac12      Arizona State 0                           2015             1      1
2 Pac12      Arizona State 0                           2015             1      2
3 Pac12      Arizona State 0                           2015             1      3
4 Pac12      Arizona State 0                           2015             1      4
5 Pac12      Arizona State 0                           2015             1      5
6 Pac12      Arizona State 0                           2015             1      6
# ℹ abbreviated name: ¹`Area Classification (0-Rural; 1-Urban)`
# ℹ 7 more variables: S_Diversion <dbl>, Attendance <dbl>, `Game Time` <chr>,
#   `Game result (Win=1; Loss=0)` <chr>, `Athletic Dept Profit` <dbl>,
#   `Total Expenses` <dbl>, `Total Revenues` <dbl>

Convert the character variables to factor variables

cols_to_factor <- data_clean%>% select_if(is.character) %>% colnames() 
cols_to_factor

[1] "Conference"                            
[2] "School"                                
[3] "Area Classification (0-Rural; 1-Urban)"
[4] "Game Time"                             
[5] "Game result (Win=1; Loss=0)"

 data_clean <- data_clean %>% 
  mutate(`Game result (Win=1; Loss=0)` = na_if(`Game result (Win=1; Loss=0)`, "N/A")) %>%
          mutate(across(all_of(cols_to_factor), as.factor))

str(data_clean)

tibble [1,396 × 13] (S3: tbl_df/tbl/data.frame)
 $ Conference                            : Factor w/ 5 levels "ACC","Big10",..: 4 4 4 4 4 4 4 4 4 4 ...
 $ School                                : Factor w/ 31 levels "Arizona State",..: 1 1 1 1 1 1 1 1 1 1 ...
 $ Area Classification (0-Rural; 1-Urban): Factor w/ 2 levels "0","1": 1 1 1 1 1 1 1 1 1 1 ...
 $ Year                                  : num [1:1396] 2015 2015 2015 2015 2015 ...
 $ Tenure Year                           : num [1:1396] 1 1 1 1 1 1 1 2 2 2 ...
 $ S_Game                                : num [1:1396] 1 2 3 4 5 6 7 1 2 3 ...
 $ S_Diversion                           : num [1:1396] 0.44 0.412 0.315 0.57 0.579 ...
 $ Attendance                            : num [1:1396] 46500 43310 61904 44157 56534 ...
 $ Game Time                             : Factor w/ 56 levels "09:00","10:00",..: 51 44 47 44 47 13 15 51 44 44 ...
 $ Game result (Win=1; Loss=0)           : Factor w/ 2 levels "0","1": 2 2 1 2 1 2 2 2 2 2 ...
 $ Athletic Dept Profit                  : num [1:1396] 566524 566524 566524 566524 566524 ...
 $ Total Expenses                        : num [1:1396] 83873516 83873516 83873516 83873516 83873516 ...
 $ Total Revenues                        : num [1:1396] 84440040 84440040 84440040 84440040 84440040 ...

Descriptive Analysis

summary(data_clean)

 Conference                  School    Area Classification (0-Rural; 1-Urban)
 ACC  :230   Michigan           :143   0: 149                                
 Big10:598   Ohio State         :123   1:1247                                
 Big12: 78   UNC                :100                                         
 Pac12:221   Penn State         : 82                                         
 SEC  :269   Tennessee          : 77                                         
             Colorado University: 59                                         
             (Other)            :812                                         
      Year       Tenure Year         S_Game       S_Diversion    
 Min.   :2003   Min.   : 1.000   Min.   :1.000   Min.   :0.0000  
 1st Qu.:2013   1st Qu.: 2.000   1st Qu.:2.000   1st Qu.:0.1585  
 Median :2016   Median : 4.000   Median :4.000   Median :0.2984  
 Mean   :2015   Mean   : 5.948   Mean   :3.873   Mean   :0.3996  
 3rd Qu.:2018   3rd Qu.: 8.250   3rd Qu.:6.000   3rd Qu.:0.6770  
 Max.   :2024   Max.   :20.000   Max.   :9.000   Max.   :0.9868  
                                                 NA's   :5       
   Attendance       Game Time   Game result (Win=1; Loss=0)
 Min.   :  1275   12:00  :357   0   :418                   
 1st Qu.: 48574   15:30  :248   1   :977                   
 Median : 78306   19:30  :131   NA's:  1                   
 Mean   : 73494   19:00  :101                              
 3rd Qu.:101708   12:30  : 71                              
 Max.   :115109   20:00  : 62                              
 NA's   :1        (Other):426                              
 Athletic Dept Profit Total Expenses      Total Revenues     
 Min.   :-64721133    Min.   : 48207321   Min.   : 47191240  
 1st Qu.:        0    1st Qu.: 86924779   1st Qu.: 89104119  
 Median :  1877033    Median :115498047   Median :123034495  
 Mean   :  4412514    Mean   :120193930   Mean   :125117886  
 3rd Qu.:  8224233    3rd Qu.:139798191   3rd Qu.:147308138  
 Max.   : 65413805    Max.   :327782612   Max.   :331905866  
                      NA's   :145         NA's   :145

skim(data_clean)

Data summary
Name	data_clean
Number of rows	1396
Number of columns	13
_______________________
Column type frequency:
factor	5
numeric	8
________________________
Group variables	None

Variable type: factor

skim_variable	n_missing	complete_rate	ordered	n_unique	top_counts
Conference	0	1	FALSE	5	Big: 598, SEC: 269, ACC: 230, Pac: 221
School	0	1	FALSE	31	Mic: 143, Ohi: 123, UNC: 100, Pen: 82
Area Classification (0-Rural; 1-Urban)	0	1	FALSE	2	1: 1247, 0: 149
Game Time	0	1	FALSE	56	12:: 357, 15:: 248, 19:: 131, 19:: 101
Game result (Win=1; Loss=0)	1	1	FALSE	2	1: 977, 0: 418

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
Year	0	1.0	2015.20	4.60	2003	2013.00	2016.0	2018.00	2024.00	▂▂▅▇▂
Tenure Year	0	1.0	5.95	4.63	1	2.00	4.0	8.25	20.00	▇▃▂▂▁
S_Game	0	1.0	3.87	1.98	1	2.00	4.0	6.00	9.00	▇▇▃▆▁
S_Diversion	5	1.0	0.40	0.29	0	0.16	0.3	0.68	0.99	▇▆▃▃▃
Attendance	1	1.0	73494.20	27953.92	1275	48573.50	78306.0	101708.00	115109.00	▁▅▅▅▇
Athletic Dept Profit	0	1.0	4412513.64	12959762.29	-64721133	0.00	1877033.0	8224233.00	65413805.00	▁▁▇▂▁
Total Expenses	145	0.9	120193929.57	46285188.61	48207321	86924779.00	115498047.0	139798191.00	327782612.00	▇▇▁▁▁
Total Revenues	145	0.9	125117885.63	48678554.01	47191240	89104119.00	123034495.0	147308138.00	331905866.00	▆▇▂▁▁

summary_df <- summarytools::dfSummary(data_clean,
                                     varnumbers=FALSE,
                                     plain.ascii=FALSE,
                                     style="grid",
                                     graph.col = TRUE,
                                     valid.col=FALSE)

# Print the summary table and suppress warnings
print(summary_df,
      method="render",
      table.classes="table-condensed")

Data Frame Summary

data_clean

Dimensions: 1396 x 13
Duplicates: 0

Conference [factor]

1. ACC
2. Big10
3. Big12
4. Pac12
5. SEC

230	(	16.5%	)
598	(	42.8%	)
78	(	5.6%	)
221	(	15.8%	)
269	(	19.3%	)

0 (0.0%)

School [factor]

1. Arizona State
2. Arkansas
3. Auburn
4. Clemson
5. Colorado University
6. Duke
7. Florida
8. Georgia
9. Georgia Tech
10. Illinois
[ 21 others ]

33	(	2.4%	)
6	(	0.4%	)
36	(	2.6%	)
28	(	2.0%	)
59	(	4.2%	)
38	(	2.7%	)
43	(	3.1%	)
36	(	2.6%	)
33	(	2.4%	)
28	(	2.0%	)
1056	(	75.6%	)

0 (0.0%)

Area Classification (0-Rural; 1-Urban) [factor]

1. 0
2. 1

149	(	10.7%	)
1247	(	89.3%	)

0 (0.0%)

Year [numeric]

Mean (sd) : 2015.2 (4.6)
min ≤ med ≤ max:
2003 ≤ 2016 ≤ 2024
IQR (CV) : 5 (0)

22 distinct values

0 (0.0%)

Tenure Year [numeric]

Mean (sd) : 5.9 (4.6)
min ≤ med ≤ max:
1 ≤ 4 ≤ 20
IQR (CV) : 6.2 (0.8)

20 distinct values

0 (0.0%)

S_Game [numeric]

Mean (sd) : 3.9 (2)
min ≤ med ≤ max:
1 ≤ 4 ≤ 9
IQR (CV) : 4 (0.5)

1	:	209	(	15.0%	)
2	:	212	(	15.2%	)
3	:	210	(	15.0%	)
4	:	207	(	14.8%	)
5	:	205	(	14.7%	)
6	:	201	(	14.4%	)
7	:	132	(	9.5%	)
8	:	19	(	1.4%	)
9	:	1	(	0.1%	)

0 (0.0%)

S_Diversion [numeric]

Mean (sd) : 0.4 (0.3)
min ≤ med ≤ max:
0 ≤ 0.3 ≤ 1
IQR (CV) : 0.5 (0.7)

1301 distinct values

5 (0.4%)

Attendance [numeric]

Mean (sd) : 73494.2 (27953.9)
min ≤ med ≤ max:
1275 ≤ 78306 ≤ 115109
IQR (CV) : 53134.5 (0.4)

1202 distinct values

1 (0.1%)

Game Time [factor]

1. 09:00
2. 10:00
3. 11:00
4. 11:05
5. 11:30
6. 12:00
7. 12:05
8. 12:10
9. 12:15
10. 12:20
[ 46 others ]

1	(	0.1%	)
2	(	0.1%	)
60	(	4.3%	)
2	(	0.1%	)
7	(	0.5%	)
357	(	25.6%	)
1	(	0.1%	)
2	(	0.1%	)
1	(	0.1%	)
17	(	1.2%	)
946	(	67.8%	)

0 (0.0%)

Game result (Win=1; Loss=0) [factor]

1. 0
2. 1

418	(	30.0%	)
977	(	70.0%	)

1 (0.1%)

Athletic Dept Profit [numeric]

Mean (sd) : 4412514 (12959762)
min ≤ med ≤ max:
-64721133 ≤ 1877033 ≤ 65413805
IQR (CV) : 8224233 (2.9)

187 distinct values

0 (0.0%)

Total Expenses [numeric]

Mean (sd) : 120193930 (46285189)
min ≤ med ≤ max:
48207321 ≤ 115498047 ≤ 327782612
IQR (CV) : 52873412 (0.4)

189 distinct values

145 (10.4%)

Total Revenues [numeric]

Mean (sd) : 125117886 (48678554)
min ≤ med ≤ max:
47191240 ≤ 123034495 ≤ 331905866
IQR (CV) : 58204019 (0.4)

189 distinct values

145 (10.4%)

Generated by summarytools 1.1.4 (R version 4.5.1)
2025-10-15

Focous on missing data

Stadium Diversion

S_Diversion_Missing <- subset(data_clean, is.na(`S_Diversion`)) ## This one is cancelled
print.data.frame (S_Diversion_Missing)

  Conference   School Area Classification (0-Rural; 1-Urban) Year Tenure Year
1      Big10     Iowa                                      1 2018           3
2      Big10     Iowa                                      1 2018           3
3      Big10     Iowa                                      1 2018           3
4      Big10     Iowa                                      1 2018           3
5      Big12 Oklahoma                                      1 2015           4
  S_Game S_Diversion Attendance Game Time Game result (Win=1; Loss=0)
1      4          NA      69250     19:35                           0
2      5          NA      69250     11:00                           1
3      6          NA      66493     14:30                           0
4      7          NA      65299     11:00                           1
5      6          NA      85821     19:14                           1
  Athletic Dept Profit Total Expenses Total Revenues
1              5625207      131467820      137093027
2              5625207      131467820      137093027
3              5625207      131467820      137093027
4              5625207      131467820      137093027
5              6009098      128260251      134269349

Attendance

Attendance_Missing <- subset(data_clean, is.na(`Attendance`)) ## This one is cancelled
print.data.frame (Attendance_Missing)

  Conference School Area Classification (0-Rural; 1-Urban) Year Tenure Year
1        SEC    LSU                                      1 2015           1
  S_Game S_Diversion Attendance Game Time Game result (Win=1; Loss=0)
1      1   0.2034806         NA     19:30                        <NA>
  Athletic Dept Profit Total Expenses Total Revenues
1             12009860      126632377      138642237

Game result (Win=1; Loss=0)

Game_result_Missing <- subset(data_clean, is.na(`Game result (Win=1; Loss=0)`))
print.data.frame (Game_result_Missing)

  Conference School Area Classification (0-Rural; 1-Urban) Year Tenure Year
1        SEC    LSU                                      1 2015           1
  S_Game S_Diversion Attendance Game Time Game result (Win=1; Loss=0)
1      1   0.2034806         NA     19:30                        <NA>
  Athletic Dept Profit Total Expenses Total Revenues
1             12009860      126632377      138642237

Athletic Dept Total Expenses

Athletic_Dept_Total_Expenses_Missing <- subset(data_clean, is.na(`Total Expenses`))
print.data.frame (Athletic_Dept_Total_Expenses_Missing)

    Conference     School Area Classification (0-Rural; 1-Urban) Year
1          ACC       Duke                                      1 2014
2          ACC       Duke                                      1 2014
3          ACC       Duke                                      1 2014
4          ACC       Duke                                      1 2014
5          ACC       Duke                                      1 2014
6          ACC       Duke                                      1 2014
7          ACC       Duke                                      1 2014
8          ACC       Duke                                      1 2015
9          ACC       Duke                                      1 2015
10         ACC       Duke                                      1 2015
11         ACC       Duke                                      1 2015
12         ACC       Duke                                      1 2015
13         ACC       Duke                                      1 2015
14         ACC       Duke                                      1 2016
15         ACC       Duke                                      1 2016
16         ACC       Duke                                      1 2016
17         ACC       Duke                                      1 2016
18         ACC       Duke                                      1 2016
19         ACC       Duke                                      1 2016
20         ACC       Duke                                      1 2017
21         ACC       Duke                                      1 2017
22         ACC       Duke                                      1 2017
23         ACC       Duke                                      1 2017
24         ACC       Duke                                      1 2017
25         ACC       Duke                                      1 2017
26         ACC       Duke                                      1 2017
27         ACC       Duke                                      1 2018
28         ACC       Duke                                      1 2018
29         ACC       Duke                                      1 2018
30         ACC       Duke                                      1 2018
31         ACC       Duke                                      1 2018
32         ACC       Duke                                      1 2018
33         ACC       Duke                                      1 2019
34         ACC       Duke                                      1 2019
35         ACC       Duke                                      1 2019
36         ACC       Duke                                      1 2019
37         ACC       Duke                                      1 2019
38         ACC       Duke                                      1 2019
39       Big10   Michigan                                      1 2004
40       Big10   Michigan                                      1 2004
41       Big10   Michigan                                      1 2004
42       Big10   Michigan                                      1 2004
43       Big10   Michigan                                      1 2004
44       Big10   Michigan                                      1 2004
45       Big10 Penn State                                      1 2009
46       Big10 Penn State                                      1 2009
47       Big10 Penn State                                      1 2009
48       Big10 Penn State                                      1 2009
49       Big10 Penn State                                      1 2009
50       Big10 Penn State                                      1 2009
51       Big10 Penn State                                      1 2009
52       Big10 Penn State                                      1 2009
53       Big10 Penn State                                      1 2010
54       Big10 Penn State                                      1 2010
55       Big10 Penn State                                      1 2010
56       Big10 Penn State                                      1 2010
57       Big10 Penn State                                      1 2010
58       Big10 Penn State                                      1 2010
59       Big10 Penn State                                      1 2010
60       Pac12   Stanford                                      0 2015
61       Pac12   Stanford                                      0 2015
62       Pac12   Stanford                                      0 2015
63       Pac12   Stanford                                      0 2015
64       Pac12   Stanford                                      0 2015
65       Pac12   Stanford                                      0 2015
66       Pac12   Stanford                                      0 2016
67       Pac12   Stanford                                      0 2016
68       Pac12   Stanford                                      0 2016
69       Pac12   Stanford                                      0 2016
70       Pac12   Stanford                                      0 2016
71       Pac12   Stanford                                      0 2016
72       Pac12   Stanford                                      0 2015
73       Pac12   Stanford                                      0 2017
74       Pac12   Stanford                                      0 2017
75       Pac12   Stanford                                      0 2017
76       Pac12   Stanford                                      0 2017
77       Pac12   Stanford                                      0 2017
78       Pac12   Stanford                                      0 2017
79       Pac12   Stanford                                      0 2018
80       Pac12   Stanford                                      0 2018
81       Pac12   Stanford                                      0 2018
82       Pac12   Stanford                                      0 2018
83       Pac12   Stanford                                      0 2018
84       Pac12   Stanford                                      0 2018
85       Pac12   Stanford                                      0 2019
86       Pac12   Stanford                                      0 2019
87       Pac12   Stanford                                      0 2019
88       Pac12   Stanford                                      0 2019
89       Pac12   Stanford                                      0 2019
90       Pac12   Stanford                                      0 2019
91       Pac12   Stanford                                      0 2019
92         ACC        UNC                                      1 2004
93         ACC        UNC                                      1 2004
94         ACC        UNC                                      1 2004
95         ACC        UNC                                      1 2004
96         ACC        UNC                                      1 2004
97         ACC        UNC                                      1 2004
98       Pac12        USC                                      1 2015
99       Pac12        USC                                      1 2015
100      Pac12        USC                                      1 2015
101      Pac12        USC                                      1 2015
102      Pac12        USC                                      1 2015
103      Pac12        USC                                      1 2015
104      Pac12        USC                                      1 2015
105      Pac12        USC                                      1 2019
106      Pac12        USC                                      1 2019
107      Pac12        USC                                      1 2019
108      Pac12        USC                                      1 2019
109      Pac12        USC                                      1 2019
110      Pac12        USC                                      1 2019
111      Pac12        USC                                      1 2020
112      Pac12        USC                                      1 2020
113      Pac12        USC                                      1 2020
114      Pac12 Washington                                      1 2003
115      Pac12 Washington                                      1 2003
116      Pac12 Washington                                      1 2003
117      Pac12 Washington                                      1 2003
118      Pac12 Washington                                      1 2003
119      Pac12 Washington                                      1 2003
120      Pac12 Washington                                      1 2003
121      Pac12 Washington                                      1 2004
122      Pac12 Washington                                      1 2004
123      Pac12 Washington                                      1 2004
124      Pac12 Washington                                      1 2004
125      Pac12 Washington                                      1 2004
126      Pac12 Washington                                      1 2004
127      Pac12 Washington                                      1 2005
128      Pac12 Washington                                      1 2005
129      Pac12 Washington                                      1 2005
130      Pac12 Washington                                      1 2005
131      Pac12 Washington                                      1 2005
132      Pac12 Washington                                      1 2005
133      Pac12 Washington                                      1 2006
134      Pac12 Washington                                      1 2006
135      Pac12 Washington                                      1 2006
136      Pac12 Washington                                      1 2006
137      Pac12 Washington                                      1 2006
138      Pac12 Washington                                      1 2006
139      Pac12 Washington                                      1 2007
140      Pac12 Washington                                      1 2007
141      Pac12 Washington                                      1 2007
142      Pac12 Washington                                      1 2007
143      Pac12 Washington                                      1 2007
144      Pac12 Washington                                      1 2007
145      Pac12 Washington                                      1 2007
    Tenure Year S_Game S_Diversion Attendance Game Time
1             1      1  0.45965770      31213     18:00
2             1      2  0.55328798      25203     15:00
3             1      3  0.38927098      20197     12:30
4             1      4  0.44155844      28131     12:30
5             1      5  0.44279661      30107     12:00
6             1      6  0.65346535      33941     19:30
7             1      7  0.41448382      22246     19:00
8             2      1  0.35403727      33941     18:00
9             2      2  0.23130435      24127     12:30
10            2      3  0.45177665      20101     12:00
11            2      4  0.47011309      20009     15:00
12            2      5  0.71062547      30143     19:00
13            2      6  0.93586498      30241     12:00
14            3      1  0.78947368      35049     18:00
15            3      2  0.92653673      21077     15:00
16            3      3  0.78240741      25201     12:30
17            3      4  0.67702936      20613     15:30
18            3      5  0.79058824      38217     15:30
19            3      6  0.73416507      39212     19:30
20            4      1  0.68011958      30477     18:00
21            4      2  0.73101266      20241     12:00
22            4      3  0.78539493      26714     12:30
23            4      4  0.68818381      36314     19:00
24            4      5  0.76634214      31073     12:00
25            4      6  0.76619633      22621     12:20
26            4      7  0.83745583      20141     15:30
27            5      1  0.84955534      26017     19:00
28            5      2  0.69892580      30477     15:30
29            5      3  0.28565683      32177     19:00
30            5      4  0.82361005      20277     12:30
31            5      5  0.84183364      35493     12:20
32            5      6  0.76399322      20782     12:30
33            6      1  0.79851028      38313     18:00
34            6      2  0.86444975      22610     20:00
35            6      3  0.81692195      21741     12:30
36            6      4  0.79744735      40004     19:30
37            6      5  0.80054485      16286     16:00
38            6      6  0.69823789      15913     15:30
39            1      1  0.22668452     110815     12:00
40            1      2  0.22724735     109432     15:30
41            1      3  0.27982408     111428     15:30
42            1      4  0.20168067     111518     12:00
43            1      5  0.19452391     111609     15:30
44            1      6  0.16226979     111347     12:10
45            1      1  0.20416814     104968     12:00
46            1      2  0.14190507     106387     12:00
47            1      3  0.22660885     105514     15:30
48            1      4  0.13633213     109316     20:00
49            1      5  0.17337627     104488     12:00
50            1      6  0.13425000     107981     15:30
51            1      7  0.12309608     110033     15:30
52            1      8  0.14648760     107379     12:00
53            2      1  0.13005902     101213     12:00
54            2      2  0.17207665     100610     12:00
55            2      3  0.22771588     104840     15:30
56            2      4  0.19871122     107638     12:00
57            2      5  0.15857571     108539     20:00
58            2      6  0.17650602     104147     15:30
59            2      7  0.20653477     102649     12:00
60            1      1  0.08315098      51424     19:30
61            1      2  0.06550388      39100     19:30
62            1      3  0.14443885      51424     19:30
63            1      4  0.18003565      50846     19:30
64            1      5  0.10875650      48602     16:30
65            1      6  0.11517672      51424     19:30
66            2      1  0.12537092      46147     18:00
67            2      2  0.19192358      48763     17:00
68            2      3  0.30943026      33529     19:30
69            2      4  0.24571429      44535     12:00
70            2      5  0.28810573      38813     12:00
71            2      6  0.14048780      36171     17:00
72            2      7  0.12976070      51424     16:30
73            3      1  0.29346388      48042     19:30
74            3      2  0.41507510      44422     13:00
75            3      3  0.48589147      48559     20:00
76            3      4  0.56826568      44559     19:30
77            3      5  0.42449726      51424     17:00
78            3      6  0.40105715      47352     17:00
79            4      1  0.57912746      40913     18:00
80            4      2  0.29139073      42856     17:30
81            4      3  0.46209386      31772     11:00
82            4      4  0.65279770      37244     19:30
83            4      5  0.51059322      39596     16:00
84            4      6  0.43333333      34671     18:00
85            5      1  0.42704626      37179     13:00
86            5      2  0.45263158      39249     16:00
87            5      3  0.58174905      33225     19:30
88            5      4  0.41216216      31464     18:00
89            5      5  0.44992526      31711     12:30
90            5      6  0.50000000      48904     13:00
91            5      7  0.44674086      37391     13:00
92            1      1  0.42931937      43500     13:30
93            1      2  0.42303173      46250     18:00
94            1      3  0.44303797      49000     13:30
95            1      4  0.43637847      60000     18:00
96            1      5  0.44019139      58000     19:00
97            1      6  0.40165441      58000     12:00
98            1      1  0.73089564      79809     20:00
99            1      2  0.74991027      72422     17:00
100           1      3  0.85296641      78306     17:00
101           1      4  0.83716421      63623     18:00
102           1      5  0.63879480      73435     16:30
103           1      6  0.78256829      76309     19:30
104           1      7  0.89491992      83602     12:30
105           5      1  0.84638301      48746     19:30
106           5      2  0.83367456      49835     19:30
107           5      3  0.89519024      45218     12:30
108           5      4  0.90120746      43181     18:30
109           5      5  0.92817982      49922     17:00
110           5      6  0.93120393      56710     12:30
111           6      1  0.79287216      54130     09:00
112           6      2  0.66666667      50775     16:30
113           6      3  0.82990991      45928     17:00
114           1      1  0.10252193      71125     13:00
115           1      2  0.11477411      71178     13:00
116           1      3  0.10577390      71875     12:30
117           1      4  0.10441767      70149     12:30
118           1      5  0.14401914      72015     12:30
119           1      6  0.10453118      72450     19:00
120           1      7  0.12658782      74549     15:30
121           2      1  0.15600394      65345     14:30
122           2      2  0.14525433      65235     16:00
123           2      3  0.23240833      65816     12:30
124           2      4  0.12817148      65351     12:30
125           2      5  0.14147910      63225     12:30
126           2      6  0.18232891      65451     12:30
127           3      1  0.14491844      57775     12:30
128           3      2  0.18322763      61183     12:30
129           3      3  0.18818565      71473     12:30
130           3      4  0.17925793      64096     12:30
131           3      5  0.16376663      60717     15:30
132           3      6  0.20824216      70713     12:15
133           4      1  0.23236741      52256     12:30
134           4      2  0.28983764      57012     12:30
135           4      3  0.29229963      58255     12:30
136           4      4  0.27884615      62656     15:30
137           4      5  0.30752334      58822     16:00
138           4      6  0.27132262      55896     12:30
139           5      1  0.29963009      70045     12:30
140           5      2  0.28233749      74927     12:30
141           5      3  0.27479407      68654     17:00
142           5      4  0.26198565      66481     16:30
143           5      5  0.26469160      61124     12:00
144           5      6  0.26849894      60005     12:30
145           5      7  0.22701504      72888     16:00
    Game result (Win=1; Loss=0) Athletic Dept Profit Total Expenses
1                             1                    0             NA
2                             1                    0             NA
3                             1                    0             NA
4                             1                    0             NA
5                             0                    0             NA
6                             0                    0             NA
7                             1                    0             NA
8                             1                    0             NA
9                             0                    0             NA
10                            1                    0             NA
11                            1                    0             NA
12                            0                    0             NA
13                            0                    0             NA
14                            1                    0             NA
15                            0                    0             NA
16                            0                    0             NA
17                            1                    0             NA
18                            0                    0             NA
19                            1                    0             NA
20                            1                    0             NA
21                            1                    0             NA
22                            1                    0             NA
23                            0                    0             NA
24                            0                    0             NA
25                            0                    0             NA
26                            1                    0             NA
27                            1                    0             NA
28                            1                    0             NA
29                            0                    0             NA
30                            0                    0             NA
31                            1                    0             NA
32                            0                    0             NA
33                            1                    0             NA
34                            0                    0             NA
35                            1                    0             NA
36                            0                    0             NA
37                            0                    0             NA
38                            1                    0             NA
39                            1                    0             NA
40                            1                    0             NA
41                            1                    0             NA
42                            1                    0             NA
43                            1                    0             NA
44                            1                    0             NA
45                            1                    0             NA
46                            1                    0             NA
47                            1                    0             NA
48                            0                    0             NA
49                            1                    0             NA
50                            1                    0             NA
51                            0                    0             NA
52                            1                    0             NA
53                            1                    0             NA
54                            1                    0             NA
55                            1                    0             NA
56                            0                    0             NA
57                            1                    0             NA
58                            1                    0             NA
59                            0                    0             NA
60                            1                    0             NA
61                            1                    0             NA
62                            1                    0             NA
63                            1                    0             NA
64                            0                    0             NA
65                            1                    0             NA
66                            1                    0             NA
67                            1                    0             NA
68                            0                    0             NA
69                            0                    0             NA
70                            1                    0             NA
71                            1                    0             NA
72                            1                    0             NA
73                            1                    0             NA
74                            1                    0             NA
75                            1                    0             NA
76                            1                    0             NA
77                            1                    0             NA
78                            1                    0             NA
79                            1                    0             NA
80                            1                    0             NA
81                            1                    0             NA
82                            0                    0             NA
83                            0                    0             NA
84                            1                    0             NA
85                            1                    0             NA
86                            0                    0             NA
87                            1                    0             NA
88                            0                    0             NA
89                            1                    0             NA
90                            0                    0             NA
91                            0                    0             NA
92                            1                    0             NA
93                            1                    0             NA
94                            0                    0             NA
95                            1                    0             NA
96                            1                    0             NA
97                            0                    0             NA
98                            1                    0             NA
99                            1                    0             NA
100                           0                    0             NA
101                           0                    0             NA
102                           1                    0             NA
103                           1                    0             NA
104                           1                    0             NA
105                           1                    0             NA
106                           1                    0             NA
107                           1                    0             NA
108                           1                    0             NA
109                           0                    0             NA
110                           1                    0             NA
111                           1                    0             NA
112                           1                    0             NA
113                           0                    0             NA
114                           1                    0             NA
115                           1                    0             NA
116                           1                    0             NA
117                           0                    0             NA
118                           0                    0             NA
119                           1                    0             NA
120                           1                    0             NA
121                           0                    0             NA
122                           0                    0             NA
123                           1                    0             NA
124                           0                    0             NA
125                           0                    0             NA
126                           0                    0             NA
127                           0                    0             NA
128                           1                    0             NA
129                           0                    0             NA
130                           0                    0             NA
131                           0                    0             NA
132                           0                    0             NA
133                           1                    0             NA
134                           1                    0             NA
135                           1                    0             NA
136                           0                    0             NA
137                           0                    0             NA
138                           0                    0             NA
139                           1                    0             NA
140                           0                    0             NA
141                           0                    0             NA
142                           0                    0             NA
143                           0                    0             NA
144                           1                    0             NA
145                           0                    0             NA
    Total Revenues
1               NA
2               NA
3               NA
4               NA
5               NA
6               NA
7               NA
8               NA
9               NA
10              NA
11              NA
12              NA
13              NA
14              NA
15              NA
16              NA
17              NA
18              NA
19              NA
20              NA
21              NA
22              NA
23              NA
24              NA
25              NA
26              NA
27              NA
28              NA
29              NA
30              NA
31              NA
32              NA
33              NA
34              NA
35              NA
36              NA
37              NA
38              NA
39              NA
40              NA
41              NA
42              NA
43              NA
44              NA
45              NA
46              NA
47              NA
48              NA
49              NA
50              NA
51              NA
52              NA
53              NA
54              NA
55              NA
56              NA
57              NA
58              NA
59              NA
60              NA
61              NA
62              NA
63              NA
64              NA
65              NA
66              NA
67              NA
68              NA
69              NA
70              NA
71              NA
72              NA
73              NA
74              NA
75              NA
76              NA
77              NA
78              NA
79              NA
80              NA
81              NA
82              NA
83              NA
84              NA
85              NA
86              NA
87              NA
88              NA
89              NA
90              NA
91              NA
92              NA
93              NA
94              NA
95              NA
96              NA
97              NA
98              NA
99              NA
100             NA
101             NA
102             NA
103             NA
104             NA
105             NA
106             NA
107             NA
108             NA
109             NA
110             NA
111             NA
112             NA
113             NA
114             NA
115             NA
116             NA
117             NA
118             NA
119             NA
120             NA
121             NA
122             NA
123             NA
124             NA
125             NA
126             NA
127             NA
128             NA
129             NA
130             NA
131             NA
132             NA
133             NA
134             NA
135             NA
136             NA
137             NA
138             NA
139             NA
140             NA
141             NA
142             NA
143             NA
144             NA
145             NA

Athletic Dept Total Revenues

Athletic_Dept_Total_Revenues_Missing <- subset(data_clean, is.na(`Total Revenues`))
print.data.frame (Athletic_Dept_Total_Revenues_Missing)

    Conference     School Area Classification (0-Rural; 1-Urban) Year
1          ACC       Duke                                      1 2014
2          ACC       Duke                                      1 2014
3          ACC       Duke                                      1 2014
4          ACC       Duke                                      1 2014
5          ACC       Duke                                      1 2014
6          ACC       Duke                                      1 2014
7          ACC       Duke                                      1 2014
8          ACC       Duke                                      1 2015
9          ACC       Duke                                      1 2015
10         ACC       Duke                                      1 2015
11         ACC       Duke                                      1 2015
12         ACC       Duke                                      1 2015
13         ACC       Duke                                      1 2015
14         ACC       Duke                                      1 2016
15         ACC       Duke                                      1 2016
16         ACC       Duke                                      1 2016
17         ACC       Duke                                      1 2016
18         ACC       Duke                                      1 2016
19         ACC       Duke                                      1 2016
20         ACC       Duke                                      1 2017
21         ACC       Duke                                      1 2017
22         ACC       Duke                                      1 2017
23         ACC       Duke                                      1 2017
24         ACC       Duke                                      1 2017
25         ACC       Duke                                      1 2017
26         ACC       Duke                                      1 2017
27         ACC       Duke                                      1 2018
28         ACC       Duke                                      1 2018
29         ACC       Duke                                      1 2018
30         ACC       Duke                                      1 2018
31         ACC       Duke                                      1 2018
32         ACC       Duke                                      1 2018
33         ACC       Duke                                      1 2019
34         ACC       Duke                                      1 2019
35         ACC       Duke                                      1 2019
36         ACC       Duke                                      1 2019
37         ACC       Duke                                      1 2019
38         ACC       Duke                                      1 2019
39       Big10   Michigan                                      1 2004
40       Big10   Michigan                                      1 2004
41       Big10   Michigan                                      1 2004
42       Big10   Michigan                                      1 2004
43       Big10   Michigan                                      1 2004
44       Big10   Michigan                                      1 2004
45       Big10 Penn State                                      1 2009
46       Big10 Penn State                                      1 2009
47       Big10 Penn State                                      1 2009
48       Big10 Penn State                                      1 2009
49       Big10 Penn State                                      1 2009
50       Big10 Penn State                                      1 2009
51       Big10 Penn State                                      1 2009
52       Big10 Penn State                                      1 2009
53       Big10 Penn State                                      1 2010
54       Big10 Penn State                                      1 2010
55       Big10 Penn State                                      1 2010
56       Big10 Penn State                                      1 2010
57       Big10 Penn State                                      1 2010
58       Big10 Penn State                                      1 2010
59       Big10 Penn State                                      1 2010
60       Pac12   Stanford                                      0 2015
61       Pac12   Stanford                                      0 2015
62       Pac12   Stanford                                      0 2015
63       Pac12   Stanford                                      0 2015
64       Pac12   Stanford                                      0 2015
65       Pac12   Stanford                                      0 2015
66       Pac12   Stanford                                      0 2016
67       Pac12   Stanford                                      0 2016
68       Pac12   Stanford                                      0 2016
69       Pac12   Stanford                                      0 2016
70       Pac12   Stanford                                      0 2016
71       Pac12   Stanford                                      0 2016
72       Pac12   Stanford                                      0 2015
73       Pac12   Stanford                                      0 2017
74       Pac12   Stanford                                      0 2017
75       Pac12   Stanford                                      0 2017
76       Pac12   Stanford                                      0 2017
77       Pac12   Stanford                                      0 2017
78       Pac12   Stanford                                      0 2017
79       Pac12   Stanford                                      0 2018
80       Pac12   Stanford                                      0 2018
81       Pac12   Stanford                                      0 2018
82       Pac12   Stanford                                      0 2018
83       Pac12   Stanford                                      0 2018
84       Pac12   Stanford                                      0 2018
85       Pac12   Stanford                                      0 2019
86       Pac12   Stanford                                      0 2019
87       Pac12   Stanford                                      0 2019
88       Pac12   Stanford                                      0 2019
89       Pac12   Stanford                                      0 2019
90       Pac12   Stanford                                      0 2019
91       Pac12   Stanford                                      0 2019
92         ACC        UNC                                      1 2004
93         ACC        UNC                                      1 2004
94         ACC        UNC                                      1 2004
95         ACC        UNC                                      1 2004
96         ACC        UNC                                      1 2004
97         ACC        UNC                                      1 2004
98       Pac12        USC                                      1 2015
99       Pac12        USC                                      1 2015
100      Pac12        USC                                      1 2015
101      Pac12        USC                                      1 2015
102      Pac12        USC                                      1 2015
103      Pac12        USC                                      1 2015
104      Pac12        USC                                      1 2015
105      Pac12        USC                                      1 2019
106      Pac12        USC                                      1 2019
107      Pac12        USC                                      1 2019
108      Pac12        USC                                      1 2019
109      Pac12        USC                                      1 2019
110      Pac12        USC                                      1 2019
111      Pac12        USC                                      1 2020
112      Pac12        USC                                      1 2020
113      Pac12        USC                                      1 2020
114      Pac12 Washington                                      1 2003
115      Pac12 Washington                                      1 2003
116      Pac12 Washington                                      1 2003
117      Pac12 Washington                                      1 2003
118      Pac12 Washington                                      1 2003
119      Pac12 Washington                                      1 2003
120      Pac12 Washington                                      1 2003
121      Pac12 Washington                                      1 2004
122      Pac12 Washington                                      1 2004
123      Pac12 Washington                                      1 2004
124      Pac12 Washington                                      1 2004
125      Pac12 Washington                                      1 2004
126      Pac12 Washington                                      1 2004
127      Pac12 Washington                                      1 2005
128      Pac12 Washington                                      1 2005
129      Pac12 Washington                                      1 2005
130      Pac12 Washington                                      1 2005
131      Pac12 Washington                                      1 2005
132      Pac12 Washington                                      1 2005
133      Pac12 Washington                                      1 2006
134      Pac12 Washington                                      1 2006
135      Pac12 Washington                                      1 2006
136      Pac12 Washington                                      1 2006
137      Pac12 Washington                                      1 2006
138      Pac12 Washington                                      1 2006
139      Pac12 Washington                                      1 2007
140      Pac12 Washington                                      1 2007
141      Pac12 Washington                                      1 2007
142      Pac12 Washington                                      1 2007
143      Pac12 Washington                                      1 2007
144      Pac12 Washington                                      1 2007
145      Pac12 Washington                                      1 2007
    Tenure Year S_Game S_Diversion Attendance Game Time
1             1      1  0.45965770      31213     18:00
2             1      2  0.55328798      25203     15:00
3             1      3  0.38927098      20197     12:30
4             1      4  0.44155844      28131     12:30
5             1      5  0.44279661      30107     12:00
6             1      6  0.65346535      33941     19:30
7             1      7  0.41448382      22246     19:00
8             2      1  0.35403727      33941     18:00
9             2      2  0.23130435      24127     12:30
10            2      3  0.45177665      20101     12:00
11            2      4  0.47011309      20009     15:00
12            2      5  0.71062547      30143     19:00
13            2      6  0.93586498      30241     12:00
14            3      1  0.78947368      35049     18:00
15            3      2  0.92653673      21077     15:00
16            3      3  0.78240741      25201     12:30
17            3      4  0.67702936      20613     15:30
18            3      5  0.79058824      38217     15:30
19            3      6  0.73416507      39212     19:30
20            4      1  0.68011958      30477     18:00
21            4      2  0.73101266      20241     12:00
22            4      3  0.78539493      26714     12:30
23            4      4  0.68818381      36314     19:00
24            4      5  0.76634214      31073     12:00
25            4      6  0.76619633      22621     12:20
26            4      7  0.83745583      20141     15:30
27            5      1  0.84955534      26017     19:00
28            5      2  0.69892580      30477     15:30
29            5      3  0.28565683      32177     19:00
30            5      4  0.82361005      20277     12:30
31            5      5  0.84183364      35493     12:20
32            5      6  0.76399322      20782     12:30
33            6      1  0.79851028      38313     18:00
34            6      2  0.86444975      22610     20:00
35            6      3  0.81692195      21741     12:30
36            6      4  0.79744735      40004     19:30
37            6      5  0.80054485      16286     16:00
38            6      6  0.69823789      15913     15:30
39            1      1  0.22668452     110815     12:00
40            1      2  0.22724735     109432     15:30
41            1      3  0.27982408     111428     15:30
42            1      4  0.20168067     111518     12:00
43            1      5  0.19452391     111609     15:30
44            1      6  0.16226979     111347     12:10
45            1      1  0.20416814     104968     12:00
46            1      2  0.14190507     106387     12:00
47            1      3  0.22660885     105514     15:30
48            1      4  0.13633213     109316     20:00
49            1      5  0.17337627     104488     12:00
50            1      6  0.13425000     107981     15:30
51            1      7  0.12309608     110033     15:30
52            1      8  0.14648760     107379     12:00
53            2      1  0.13005902     101213     12:00
54            2      2  0.17207665     100610     12:00
55            2      3  0.22771588     104840     15:30
56            2      4  0.19871122     107638     12:00
57            2      5  0.15857571     108539     20:00
58            2      6  0.17650602     104147     15:30
59            2      7  0.20653477     102649     12:00
60            1      1  0.08315098      51424     19:30
61            1      2  0.06550388      39100     19:30
62            1      3  0.14443885      51424     19:30
63            1      4  0.18003565      50846     19:30
64            1      5  0.10875650      48602     16:30
65            1      6  0.11517672      51424     19:30
66            2      1  0.12537092      46147     18:00
67            2      2  0.19192358      48763     17:00
68            2      3  0.30943026      33529     19:30
69            2      4  0.24571429      44535     12:00
70            2      5  0.28810573      38813     12:00
71            2      6  0.14048780      36171     17:00
72            2      7  0.12976070      51424     16:30
73            3      1  0.29346388      48042     19:30
74            3      2  0.41507510      44422     13:00
75            3      3  0.48589147      48559     20:00
76            3      4  0.56826568      44559     19:30
77            3      5  0.42449726      51424     17:00
78            3      6  0.40105715      47352     17:00
79            4      1  0.57912746      40913     18:00
80            4      2  0.29139073      42856     17:30
81            4      3  0.46209386      31772     11:00
82            4      4  0.65279770      37244     19:30
83            4      5  0.51059322      39596     16:00
84            4      6  0.43333333      34671     18:00
85            5      1  0.42704626      37179     13:00
86            5      2  0.45263158      39249     16:00
87            5      3  0.58174905      33225     19:30
88            5      4  0.41216216      31464     18:00
89            5      5  0.44992526      31711     12:30
90            5      6  0.50000000      48904     13:00
91            5      7  0.44674086      37391     13:00
92            1      1  0.42931937      43500     13:30
93            1      2  0.42303173      46250     18:00
94            1      3  0.44303797      49000     13:30
95            1      4  0.43637847      60000     18:00
96            1      5  0.44019139      58000     19:00
97            1      6  0.40165441      58000     12:00
98            1      1  0.73089564      79809     20:00
99            1      2  0.74991027      72422     17:00
100           1      3  0.85296641      78306     17:00
101           1      4  0.83716421      63623     18:00
102           1      5  0.63879480      73435     16:30
103           1      6  0.78256829      76309     19:30
104           1      7  0.89491992      83602     12:30
105           5      1  0.84638301      48746     19:30
106           5      2  0.83367456      49835     19:30
107           5      3  0.89519024      45218     12:30
108           5      4  0.90120746      43181     18:30
109           5      5  0.92817982      49922     17:00
110           5      6  0.93120393      56710     12:30
111           6      1  0.79287216      54130     09:00
112           6      2  0.66666667      50775     16:30
113           6      3  0.82990991      45928     17:00
114           1      1  0.10252193      71125     13:00
115           1      2  0.11477411      71178     13:00
116           1      3  0.10577390      71875     12:30
117           1      4  0.10441767      70149     12:30
118           1      5  0.14401914      72015     12:30
119           1      6  0.10453118      72450     19:00
120           1      7  0.12658782      74549     15:30
121           2      1  0.15600394      65345     14:30
122           2      2  0.14525433      65235     16:00
123           2      3  0.23240833      65816     12:30
124           2      4  0.12817148      65351     12:30
125           2      5  0.14147910      63225     12:30
126           2      6  0.18232891      65451     12:30
127           3      1  0.14491844      57775     12:30
128           3      2  0.18322763      61183     12:30
129           3      3  0.18818565      71473     12:30
130           3      4  0.17925793      64096     12:30
131           3      5  0.16376663      60717     15:30
132           3      6  0.20824216      70713     12:15
133           4      1  0.23236741      52256     12:30
134           4      2  0.28983764      57012     12:30
135           4      3  0.29229963      58255     12:30
136           4      4  0.27884615      62656     15:30
137           4      5  0.30752334      58822     16:00
138           4      6  0.27132262      55896     12:30
139           5      1  0.29963009      70045     12:30
140           5      2  0.28233749      74927     12:30
141           5      3  0.27479407      68654     17:00
142           5      4  0.26198565      66481     16:30
143           5      5  0.26469160      61124     12:00
144           5      6  0.26849894      60005     12:30
145           5      7  0.22701504      72888     16:00
    Game result (Win=1; Loss=0) Athletic Dept Profit Total Expenses
1                             1                    0             NA
2                             1                    0             NA
3                             1                    0             NA
4                             1                    0             NA
5                             0                    0             NA
6                             0                    0             NA
7                             1                    0             NA
8                             1                    0             NA
9                             0                    0             NA
10                            1                    0             NA
11                            1                    0             NA
12                            0                    0             NA
13                            0                    0             NA
14                            1                    0             NA
15                            0                    0             NA
16                            0                    0             NA
17                            1                    0             NA
18                            0                    0             NA
19                            1                    0             NA
20                            1                    0             NA
21                            1                    0             NA
22                            1                    0             NA
23                            0                    0             NA
24                            0                    0             NA
25                            0                    0             NA
26                            1                    0             NA
27                            1                    0             NA
28                            1                    0             NA
29                            0                    0             NA
30                            0                    0             NA
31                            1                    0             NA
32                            0                    0             NA
33                            1                    0             NA
34                            0                    0             NA
35                            1                    0             NA
36                            0                    0             NA
37                            0                    0             NA
38                            1                    0             NA
39                            1                    0             NA
40                            1                    0             NA
41                            1                    0             NA
42                            1                    0             NA
43                            1                    0             NA
44                            1                    0             NA
45                            1                    0             NA
46                            1                    0             NA
47                            1                    0             NA
48                            0                    0             NA
49                            1                    0             NA
50                            1                    0             NA
51                            0                    0             NA
52                            1                    0             NA
53                            1                    0             NA
54                            1                    0             NA
55                            1                    0             NA
56                            0                    0             NA
57                            1                    0             NA
58                            1                    0             NA
59                            0                    0             NA
60                            1                    0             NA
61                            1                    0             NA
62                            1                    0             NA
63                            1                    0             NA
64                            0                    0             NA
65                            1                    0             NA
66                            1                    0             NA
67                            1                    0             NA
68                            0                    0             NA
69                            0                    0             NA
70                            1                    0             NA
71                            1                    0             NA
72                            1                    0             NA
73                            1                    0             NA
74                            1                    0             NA
75                            1                    0             NA
76                            1                    0             NA
77                            1                    0             NA
78                            1                    0             NA
79                            1                    0             NA
80                            1                    0             NA
81                            1                    0             NA
82                            0                    0             NA
83                            0                    0             NA
84                            1                    0             NA
85                            1                    0             NA
86                            0                    0             NA
87                            1                    0             NA
88                            0                    0             NA
89                            1                    0             NA
90                            0                    0             NA
91                            0                    0             NA
92                            1                    0             NA
93                            1                    0             NA
94                            0                    0             NA
95                            1                    0             NA
96                            1                    0             NA
97                            0                    0             NA
98                            1                    0             NA
99                            1                    0             NA
100                           0                    0             NA
101                           0                    0             NA
102                           1                    0             NA
103                           1                    0             NA
104                           1                    0             NA
105                           1                    0             NA
106                           1                    0             NA
107                           1                    0             NA
108                           1                    0             NA
109                           0                    0             NA
110                           1                    0             NA
111                           1                    0             NA
112                           1                    0             NA
113                           0                    0             NA
114                           1                    0             NA
115                           1                    0             NA
116                           1                    0             NA
117                           0                    0             NA
118                           0                    0             NA
119                           1                    0             NA
120                           1                    0             NA
121                           0                    0             NA
122                           0                    0             NA
123                           1                    0             NA
124                           0                    0             NA
125                           0                    0             NA
126                           0                    0             NA
127                           0                    0             NA
128                           1                    0             NA
129                           0                    0             NA
130                           0                    0             NA
131                           0                    0             NA
132                           0                    0             NA
133                           1                    0             NA
134                           1                    0             NA
135                           1                    0             NA
136                           0                    0             NA
137                           0                    0             NA
138                           0                    0             NA
139                           1                    0             NA
140                           0                    0             NA
141                           0                    0             NA
142                           0                    0             NA
143                           0                    0             NA
144                           1                    0             NA
145                           0                    0             NA
    Total Revenues
1               NA
2               NA
3               NA
4               NA
5               NA
6               NA
7               NA
8               NA
9               NA
10              NA
11              NA
12              NA
13              NA
14              NA
15              NA
16              NA
17              NA
18              NA
19              NA
20              NA
21              NA
22              NA
23              NA
24              NA
25              NA
26              NA
27              NA
28              NA
29              NA
30              NA
31              NA
32              NA
33              NA
34              NA
35              NA
36              NA
37              NA
38              NA
39              NA
40              NA
41              NA
42              NA
43              NA
44              NA
45              NA
46              NA
47              NA
48              NA
49              NA
50              NA
51              NA
52              NA
53              NA
54              NA
55              NA
56              NA
57              NA
58              NA
59              NA
60              NA
61              NA
62              NA
63              NA
64              NA
65              NA
66              NA
67              NA
68              NA
69              NA
70              NA
71              NA
72              NA
73              NA
74              NA
75              NA
76              NA
77              NA
78              NA
79              NA
80              NA
81              NA
82              NA
83              NA
84              NA
85              NA
86              NA
87              NA
88              NA
89              NA
90              NA
91              NA
92              NA
93              NA
94              NA
95              NA
96              NA
97              NA
98              NA
99              NA
100             NA
101             NA
102             NA
103             NA
104             NA
105             NA
106             NA
107             NA
108             NA
109             NA
110             NA
111             NA
112             NA
113             NA
114             NA
115             NA
116             NA
117             NA
118             NA
119             NA
120             NA
121             NA
122             NA
123             NA
124             NA
125             NA
126             NA
127             NA
128             NA
129             NA
130             NA
131             NA
132             NA
133             NA
134             NA
135             NA
136             NA
137             NA
138             NA
139             NA
140             NA
141             NA
142             NA
143             NA
144             NA
145             NA

More detail Analysis

Character Variables

Conference

frequency_table_conference <- table(data_clean$Conference) %>% data.frame()
frequency_table_conference

   Var1 Freq
1   ACC  230
2 Big10  598
3 Big12   78
4 Pac12  221
5   SEC  269

ggplot(frequency_table_conference, aes(x = Var1, y = Freq)) +
  geom_bar(stat = "identity", fill = "black") +
  labs(title = "Barplot for Conference Categories",
       x = "Categories",
       y = "Frequency") +
  theme_classic()+
  theme(axis.text.x = element_text(hjust = 1, size = 8))

School

frequency_table_school <- table(data_clean$School) %>% data.frame()
frequency_table_school

                  Var1 Freq
1        Arizona State   33
2             Arkansas    6
3               Auburn   36
4              Clemson   28
5  Colorado University   59
6                 Duke   38
7              Florida   43
8              Georgia   36
9         Georgia Tech   33
10            Illinois   28
11                Iowa   20
12            Kentucky   34
13                 LSU   37
14            Maryland   29
15            Michigan  143
16      Michigan State   21
17           Minnesota   42
18            NC State   31
19          Ohio State  123
20            Oklahoma   24
21          Penn State   82
22              Purdue   55
23            Stanford   32
24           Tennessee   77
25                UCLA    7
26                 UNC  100
27             UoTexas   54
28                 USC   16
29          Washington   32
30    Washington State   42
31           Wisconsin   55

ggplot(frequency_table_school, aes(x = Var1, y = Freq)) +
  geom_bar(stat = "identity", fill = "black") +
  labs(title = "Barplot for School Categories",
       x = "Categories",
       y = "Frequency") +
  theme_classic()+
  theme(axis.text.x = element_text(angle = 90, hjust = 1, size = 8))

Area Classification (0-Rural; 1-Urban)

frequency_table_Area_Classification <- table(data_clean$`Area Classification (0-Rural; 1-Urban)`) %>% data.frame()
frequency_table_Area_Classification

  Var1 Freq
1    0  149
2    1 1247

ggplot(frequency_table_Area_Classification, aes(x = Var1, y = Freq)) +
  geom_bar(stat = "identity", fill = "black") +
  labs(title = "Barplot for Area Classification (0-Rural; 1-Urban)",
       x = "Categories",
       y = "Frequency") +
  theme_classic()+
  theme(axis.text.x = element_text(hjust = 1, size = 8))

Game time

frequency_table_game_time <- table(data_clean$`Game Time`) %>% data.frame()
frequency_table_game_time

    Var1 Freq
1  09:00    1
2  10:00    2
3  11:00   60
4  11:05    2
5  11:30    7
6  12:00  357
7  12:05    1
8  12:10    2
9  12:15    1
10 12:20   17
11 12:30   71
12 12:45    1
13 13:00   17
14 13:20    1
15 13:30   16
16 13:45    1
17 14:00    8
18 14:30   53
19 14:35    3
20 14:40    1
21 15:00   24
22 15:15    1
23 15:30  248
24 15:41    1
25 15:45    3
26 16:00   52
27 16:05    1
28 16:15    1
29 16:20    1
30 16:30   12
31 17:00   21
32 17:30    8
33 17:40    1
34 17:51    1
35 18:00   55
36 18:02    1
37 18:05    1
38 18:06    1
39 18:15    1
40 18:30   18
41 18:40    1
42 18:45    1
43 18:50    2
44 19:00  101
45 19:14    1
46 19:15    3
47 19:30  131
48 19:35    1
49 19:45    9
50 19:49    1
51 20:00   62
52 20:10    1
53 20:20    2
54 20:30    2
55 21:00    3
56 21:15    1

ggplot(frequency_table_game_time, aes(x = Var1, y = Freq)) +
  geom_bar(stat = "identity", fill = "black") +
  labs(title = "Barplot for Categories",
       x = "Categories",
       y = "Frequency") +
  theme_classic()+
  theme(axis.text.x = element_text(angle = 90, hjust = 1, size = 8))

Numerical Variables

Year

hist(data_clean$Year, main = "Histogram of Year", xlab = "Variable Value", ylab = "Frequency" )

frequency_table_year <- table(data_clean$Year) %>% data.frame()
frequency_table_year

   Var1 Freq
1  2003    7
2  2004   18
3  2005   19
4  2006   35
5  2007   42
6  2008   36
7  2009   50
8  2010   35
9  2011   35
10 2012   60
11 2013   64
12 2014   85
13 2015  142
14 2016  151
15 2017  156
16 2018  166
17 2019  138
18 2020   17
19 2021   31
20 2022   37
21 2023   33
22 2024   39

ggplot(frequency_table_year, aes(x = Var1, y = Freq)) +
  geom_bar(stat = "identity", fill = "black") +
  labs(title = "Barplot for Bar Plot of Year",
       x = "Categories",
       y = "Frequency") +
  theme_classic()+
  theme(axis.text.x = element_text(angle = 90, hjust = 1, size = 8))

Tenure Year

hist(data_clean$`Tenure Year`, main = "Barplot for Tenure Year", xlab = "Categories", ylab = "Frequency")

frequency_table_Tenure_Year <-table(data_clean$`Tenure Year`) %>% as.data.frame()

frequency_table_Tenure_Year

   Var1 Freq
1     1  197
2     2  172
3     3  173
4     4  161
5     5  137
6     6   88
7     7   65
8     8   54
9     9   44
10   10   47
11   11   46
12   12   40
13   13   42
14   14   30
15   15   25
16   16   24
17   17   19
18   18   17
19   19    7
20   20    8

ggplot(frequency_table_Tenure_Year, aes(x = Var1, y = Freq)) +
  geom_bar(stat = "identity", fill = "black") +
  labs(title = "Barplot for Tenure Year",
       x = "Categories",
       y = "Frequency") +
  theme_classic()+
  theme(axis.text.x = element_text(hjust = 1, size = 8))

In-Season Game

hist(data_clean$S_Game, main = "Barplot for In-Season Game",  xlab = "Categories", ylab = "Frequency")

frequency_table_In_Season_Game  <- table(data_clean$S_Game) %>% data.frame()
frequency_table_In_Season_Game

  Var1 Freq
1    1  209
2    2  212
3    3  210
4    4  207
5    5  205
6    6  201
7    7  132
8    8   19
9    9    1

ggplot(frequency_table_In_Season_Game, aes(x = Var1, y = Freq)) +
  geom_bar(stat = "identity", fill = "black") +
  labs(title = "Barplot for In-Season Game",
       x = "Categories",
       y = "Frequency") +
  theme_classic()+
  theme(axis.text.x = element_text(hjust = 1, size = 8))

Stadium Waste Diversion

hist(data_clean$S_Diversion, xlab="Variable Value", ylab ="Frequency",main = "Histogram of Stadium Waste Diversion" )

ggplot(data = data_clean, aes(x =S_Diversion)) +
geom_histogram(bins = 100, fill = "black", color = "black") +
          labs(title = "Histogram of Stadium Waste Diversion", x = "Variable Value", y = "Frequency")+
  theme_classic()

Warning: Removed 5 rows containing non-finite outside the scale range
(`stat_bin()`).

Attendance

hist(data_clean$Attendance, main = "Histogram of Attendance", xlab = "Variable Value", ylab = "Frequency")

Athletic Dept Profit

options(scipen = 999)

hist(data_clean$`Athletic Dept Profit`, main = "Histogram of Athletic Dept Profit", xlab = "Variable Value", ylab = "Frequency")

Athletic Dept Total Expenses

hist(data_clean$`Total Expenses`, main = "Athletic Dept Total Expenses", xlab = "Variable Value", ylab = "Frequency")

Athletic Dept Total Revenues

hist(data_clean$`Total Revenues`, main = "Athletic Dept Total Revenues", xlab = "Variable Value", ylab = "Frequency")

Compare two dataset

data <- read_excel("~/graduate2-1/Statistic consulting/Data_ForStatsGroup_version_2.xlsx")

data_clean_1 <- data %>% select(`Conference`, `School`, `Area Classification (0-Rural; 1-Urban)`, `Year`, `Tenure Year`, `In-Season_Game`, `S_Diversion`, `Attendance`, `Game Time`,`Game result (Win=1; Loss=0)`,`Athletic Dept Profit`, `Athletic Dept Total Expenses`, `Athletic Dept Total Revenues`)
data_clean_1$`Game Time`=format(data_clean_1$`Game Time`, format = "%H:%M")
data_clean_1 <- data_clean_1 %>% mutate(`Game Time`= as.character(`Game Time`)) %>% mutate(`Area Classification (0-Rural; 1-Urban)`= as.character(`Area Classification (0-Rural; 1-Urban)`)) %>% mutate(`Attendance`= as.numeric(`Attendance`))

Warning: There was 1 warning in `mutate()`.
ℹ In argument: `Attendance = as.numeric(Attendance)`.
Caused by warning:
! NAs introduced by coercion

head(data_clean_1)

# A tibble: 6 × 13
  Conference School  Area Classification …¹  Year `Tenure Year` `In-Season_Game`
  <chr>      <chr>   <chr>                  <dbl>         <dbl>            <dbl>
1 Pac12      Arizon… 0                       2015             1                1
2 Pac12      Arizon… 0                       2015             1                2
3 Pac12      Arizon… 0                       2015             1                3
4 Pac12      Arizon… 0                       2015             1                4
5 Pac12      Arizon… 0                       2015             1                5
6 Pac12      Arizon… 0                       2015             1                6
# ℹ abbreviated name: ¹`Area Classification (0-Rural; 1-Urban)`
# ℹ 7 more variables: S_Diversion <dbl>, Attendance <dbl>, `Game Time` <chr>,
#   `Game result (Win=1; Loss=0)` <chr>, `Athletic Dept Profit` <dbl>,
#   `Athletic Dept Total Expenses` <dbl>, `Athletic Dept Total Revenues` <dbl>

cols_to_factor <- data_clean_1%>% select_if(is.character) %>% colnames() 
cols_to_factor

[1] "Conference"                            
[2] "School"                                
[3] "Area Classification (0-Rural; 1-Urban)"
[4] "Game Time"                             
[5] "Game result (Win=1; Loss=0)"

 data_clean_1 <- data_clean_1 %>% 
  mutate(`Game result (Win=1; Loss=0)` = na_if(`Game result (Win=1; Loss=0)`, "N/A")) %>%
          mutate(across(all_of(cols_to_factor), as.factor))

data_clean <- data_clean %>% rename ("In-Season_Game" = "S_Game", "Athletic Dept Total Expenses" = "Total Expenses", "Athletic Dept Total Revenues" = "Total Revenues")

setdiff(data_clean, data_clean_1)

# A tibble: 5 × 13
  Conference School  Area Classification …¹  Year `Tenure Year` `In-Season_Game`
  <fct>      <fct>   <fct>                  <dbl>         <dbl>            <dbl>
1 Big10      Iowa    1                       2018             3                4
2 Big10      Iowa    1                       2018             3                5
3 Big10      Iowa    1                       2018             3                6
4 Big10      Iowa    1                       2018             3                7
5 Big12      Oklaho… 1                       2015             4                6
# ℹ abbreviated name: ¹`Area Classification (0-Rural; 1-Urban)`
# ℹ 7 more variables: S_Diversion <dbl>, Attendance <dbl>, `Game Time` <fct>,
#   `Game result (Win=1; Loss=0)` <fct>, `Athletic Dept Profit` <dbl>,
#   `Athletic Dept Total Expenses` <dbl>, `Athletic Dept Total Revenues` <dbl>