baseball = read.csv("baseball.csv")
str(baseball)
'data.frame':   1232 obs. of  15 variables:
 $ Team        : chr  "ARI" "ATL" "BAL" "BOS" ...
 $ League      : chr  "NL" "NL" "AL" "AL" ...
 $ Year        : int  2012 2012 2012 2012 2012 2012 2012 2012 2012 2012 ...
 $ RS          : int  734 700 712 734 613 748 669 667 758 726 ...
 $ RA          : int  688 600 705 806 759 676 588 845 890 670 ...
 $ W           : int  81 94 93 69 61 85 97 68 64 88 ...
 $ OBP         : num  0.328 0.32 0.311 0.315 0.302 0.318 0.315 0.324 0.33 0.335 ...
 $ SLG         : num  0.418 0.389 0.417 0.415 0.378 0.422 0.411 0.381 0.436 0.422 ...
 $ BA          : num  0.259 0.247 0.247 0.26 0.24 0.255 0.251 0.251 0.274 0.268 ...
 $ Playoffs    : int  0 1 1 0 0 0 1 0 0 1 ...
 $ RankSeason  : int  NA 4 5 NA NA NA 2 NA NA 6 ...
 $ RankPlayoffs: int  NA 5 4 NA NA NA 4 NA NA 2 ...
 $ G           : int  162 162 162 162 162 162 162 162 162 162 ...
 $ OOBP        : num  0.317 0.306 0.315 0.331 0.335 0.319 0.305 0.336 0.357 0.314 ...
 $ OSLG        : num  0.415 0.378 0.403 0.428 0.424 0.405 0.39 0.43 0.47 0.402 ...
# Subset to only include moneyball years
moneyball = subset(baseball, Year < 2002)
str(moneyball)
'data.frame':   902 obs. of  15 variables:
 $ Team        : chr  "ANA" "ARI" "ATL" "BAL" ...
 $ League      : chr  "AL" "NL" "NL" "AL" ...
 $ Year        : int  2001 2001 2001 2001 2001 2001 2001 2001 2001 2001 ...
 $ RS          : int  691 818 729 687 772 777 798 735 897 923 ...
 $ RA          : int  730 677 643 829 745 701 795 850 821 906 ...
 $ W           : int  75 92 88 63 82 88 83 66 91 73 ...
 $ OBP         : num  0.327 0.341 0.324 0.319 0.334 0.336 0.334 0.324 0.35 0.354 ...
 $ SLG         : num  0.405 0.442 0.412 0.38 0.439 0.43 0.451 0.419 0.458 0.483 ...
 $ BA          : num  0.261 0.267 0.26 0.248 0.266 0.261 0.268 0.262 0.278 0.292 ...
 $ Playoffs    : int  0 1 1 0 0 0 0 0 1 0 ...
 $ RankSeason  : int  NA 5 7 NA NA NA NA NA 6 NA ...
 $ RankPlayoffs: int  NA 1 3 NA NA NA NA NA 4 NA ...
 $ G           : int  162 162 162 162 161 162 162 162 162 162 ...
 $ OOBP        : num  0.331 0.311 0.314 0.337 0.329 0.321 0.334 0.341 0.341 0.35 ...
 $ OSLG        : num  0.412 0.404 0.384 0.439 0.393 0.398 0.427 0.455 0.417 0.48 ...
# Compute Run Difference
moneyball$RD = moneyball$RS - moneyball$RA
str(moneyball)
'data.frame':   902 obs. of  16 variables:
 $ Team        : chr  "ANA" "ARI" "ATL" "BAL" ...
 $ League      : chr  "AL" "NL" "NL" "AL" ...
 $ Year        : int  2001 2001 2001 2001 2001 2001 2001 2001 2001 2001 ...
 $ RS          : int  691 818 729 687 772 777 798 735 897 923 ...
 $ RA          : int  730 677 643 829 745 701 795 850 821 906 ...
 $ W           : int  75 92 88 63 82 88 83 66 91 73 ...
 $ OBP         : num  0.327 0.341 0.324 0.319 0.334 0.336 0.334 0.324 0.35 0.354 ...
 $ SLG         : num  0.405 0.442 0.412 0.38 0.439 0.43 0.451 0.419 0.458 0.483 ...
 $ BA          : num  0.261 0.267 0.26 0.248 0.266 0.261 0.268 0.262 0.278 0.292 ...
 $ Playoffs    : int  0 1 1 0 0 0 0 0 1 0 ...
 $ RankSeason  : int  NA 5 7 NA NA NA NA NA 6 NA ...
 $ RankPlayoffs: int  NA 1 3 NA NA NA NA NA 4 NA ...
 $ G           : int  162 162 162 162 161 162 162 162 162 162 ...
 $ OOBP        : num  0.331 0.311 0.314 0.337 0.329 0.321 0.334 0.341 0.341 0.35 ...
 $ OSLG        : num  0.412 0.404 0.384 0.439 0.393 0.398 0.427 0.455 0.417 0.48 ...
 $ RD          : int  -39 141 86 -142 27 76 3 -115 76 17 ...
# creating a scatter plot

plot(moneyball$RD,moneyball$W)

NA
NA
NA
#Creating a Regression model to predit wins
Winsreg = lm(W ~ RD, data=moneyball)
summary(Winsreg)

Call:
lm(formula = W ~ RD, data = moneyball)

Residuals:
     Min       1Q   Median       3Q      Max 
-14.2662  -2.6509   0.1234   2.9364  11.6570 

Coefficients:
             Estimate Std. Error t value Pr(>|t|)    
(Intercept) 80.881375   0.131157  616.67   <2e-16 ***
RD           0.105766   0.001297   81.55   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 3.939 on 900 degrees of freedom
Multiple R-squared:  0.8808,    Adjusted R-squared:  0.8807 
F-statistic:  6651 on 1 and 900 DF,  p-value: < 2.2e-16

This is skipped for now

# VIDEO 3

#str(moneyball)
# Regression model to predict runs scored
RunsReg = lm(RS ~ OBP + SLG +BA, data = moneyball)
summary(RunsReg)

Call:
lm(formula = RS ~ OBP + SLG + BA, data = moneyball)

Residuals:
    Min      1Q  Median      3Q     Max 
-70.941 -17.247  -0.621  16.754  90.998 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  -788.46      19.70 -40.029  < 2e-16 ***
OBP          2917.42     110.47  26.410  < 2e-16 ***
SLG          1637.93      45.99  35.612  < 2e-16 ***
BA           -368.97     130.58  -2.826  0.00482 ** 
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 24.69 on 898 degrees of freedom
Multiple R-squared:  0.9302,    Adjusted R-squared:   0.93 
F-statistic:  3989 on 3 and 898 DF,  p-value: < 2.2e-16
# Regression model to predict runs scored again but removing the batting average
RunsReg = lm(RS ~ OBP + SLG, data=moneyball)
summary(RunsReg)

Call:
lm(formula = RS ~ OBP + SLG, data = moneyball)

Residuals:
    Min      1Q  Median      3Q     Max 
-70.838 -17.174  -1.108  16.770  90.036 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  -804.63      18.92  -42.53   <2e-16 ***
OBP          2737.77      90.68   30.19   <2e-16 ***
SLG          1584.91      42.16   37.60   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 24.79 on 899 degrees of freedom
Multiple R-squared:  0.9296,    Adjusted R-squared:  0.9294 
F-statistic:  5934 on 2 and 899 DF,  p-value: < 2.2e-16

In calss Activity 8

ExpectedRuns = -804.63+2737.77*(0.361)+1584.91*(0.409)
ExpectedRuns
[1] 831.9332

We expect the team to score 832

#install.packages("car")
install.packages("carData")
Error in install.packages : Updating loaded packages
library(car)
Loading required package: carData
vif(RunsReg)
     OBP      SLG 
2.856197 2.856197 
# Regression model to predict runs allowed
RunsAllowedReg = lm(RA ~ OOBP + OSLG, data=moneyball)
summary(RunsAllowedReg)

Call:
lm(formula = RA ~ OOBP + OSLG, data = moneyball)

Residuals:
    Min      1Q  Median      3Q     Max 
-82.397 -15.178  -0.129  17.679  60.955 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  -837.38      60.26 -13.897  < 2e-16 ***
OOBP         2913.60     291.97   9.979 4.46e-16 ***
OSLG         1514.29     175.43   8.632 2.55e-13 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 25.67 on 87 degrees of freedom
  (812 observations deleted due to missingness)
Multiple R-squared:  0.9073,    Adjusted R-squared:  0.9052 
F-statistic: 425.8 on 2 and 87 DF,  p-value: < 2.2e-16

In class Activity 8 Part 2

ExpectedRunsAllowed = -837.38+2913.60*(0.267)+1514.29*(0.392)
ExpectedRunsAllowed
[1] 534.1529

The number of Runs allowed came to 534

vif(RunsAllowedReg)
    OOBP     OSLG 
2.735629 2.735629

In class Activity 7

NumberofWins =80.88+0.106*(763-614)
NumberofWins
[1] 96.674

A team with a runs differennce of 148 is expected to be 97

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