Module 3: Moneyball Analytics
plot(cars)
# Read in data
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 ...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 ...# Scatterplot to check for linear relationship
plot(moneyball$RD, moneyball$W)
# Regression model to predict 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-16runs_difference=763-614
wins=80.881+0.105766*runs_difference
wins[1] 96.64013According to our model the A’s would win 96 or 97 games.
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