firstbase = read.csv(“firstbasestats.csv”) str(firstbase)

summary(firstbase)

Linear Regression (one variable)

model1 = lm(Payroll.Salary2023 ~ RBI, data=firstbase) summary(model1)

Sum of Squared Errors

model1$residuals

SSE = sum(model1$residuals^2) SSE

Linear Regression (two variables)

model2 = lm(Payroll.Salary2023 ~ AVG + RBI, data=firstbase) summary(model2)

Sum of Squared Errors

SSE = sum(model2$residuals^2) SSE

Linear Regression (all variables)

model3 = lm(Payroll.Salary2023 ~ HR + RBI + AVG + OBP+ OPS, data=firstbase) summary(model3)

Sum of Squared Errors

SSE = sum(model3$residuals^2) SSE

Remove HR

model4 = lm(Payroll.Salary2023 ~ RBI + AVG + OBP+OPS, data=firstbase) summary(model4)

firstbase<-firstbase[,-(1:3)]

Correlations

cor(firstbase\(RBI, firstbase\)Payroll.Salary2023)

cor(firstbase\(AVG, firstbase\)OBP)

cor(firstbase)

#Removing AVG model5 = lm(Payroll.Salary2023 ~ RBI + OBP+OPS, data=firstbase) summary(model5)

model6 = lm(Payroll.Salary2023 ~ RBI + OBP, data=firstbase) summary(model6)

Read in test set

firstbaseTest = read.csv(“firstbasestats_test.csv”) str(firstbaseTest)

Make test set predictions

predictTest = predict(model6, newdata=firstbaseTest) predictTest

Compute R-squared

SSE = sum((firstbaseTest\(Payroll.Salary2023 - predictTest)^2) SST = sum((firstbaseTest\)Payroll.Salary2023 - mean(firstbase$Payroll.Salary2023))^2) 1 - SSE/SST