Getting Started with R, Part 2

Case-scenario 1: Juan Soto

# Walks in first five seasons
walks_first5 <- c(79, 108, 41, 145, 135)

# Desired average
wanted_avg <- 100
n_seasons <- 6

# Solve for x6
x6 <- n_seasons * wanted_avg - sum(walks_first5)
x6

## [1] 92

# Confirm new average
soto_walks <- c(walks_first5, x6)
mean(soto_walks)

## [1] 100

sd(soto_walks)

## [1] 38.20995

max(soto_walks)

## [1] 145

min(soto_walks)

## [1] 41

summary(soto_walks)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   41.00   82.25  100.00  100.00  128.25  145.00

Case-scenario 2: Combined Salaries

# Salaries of basketball and NFL players
n_basketball <- 7
n_nfl <- 9
salary_basketball <- 102000
salary_nfl <- 91000

# Overall mean salary
overall_salary <- (n_basketball * salary_basketball + n_nfl * salary_nfl) / (n_basketball + n_nfl)
overall_salary

## [1] 95812.5

Case-scenario 3: Contract Length Analysis

# Read contract data
contract_length <- read.csv("allcontracts.csv")
contract_years <- contract_length$years

# Basic stats
contracts_mean <- mean(contract_years)
contracts_median <- median(contract_years)
contracts_sd <- sd(contract_years)
contracts_n <- length(contract_years)

contracts_mean

## [1] 3.458918

contracts_median

## [1] 3

contracts_sd

## [1] 1.69686

contracts_n

## [1] 499

# Percent within 1 SD
contracts_w1sd <- sum(abs((contract_years - contracts_mean)/contracts_sd) < 1) / contracts_n
contracts_w1sd

## [1] 0.6693387

contracts_w1sd - 0.68

## [1] -0.01066132

# Percent within 2 SD
contracts_w2sd <- sum(abs((contract_years - contracts_mean)/contracts_sd) < 2) / contracts_n
contracts_w2sd

## [1] 1

contracts_w2sd - 0.95

## [1] 0.05

# Percent within 3 SD
contracts_w3sd <- sum(abs((contract_years - contracts_mean)/contracts_sd) < 3) / contracts_n
contracts_w3sd

## [1] 1

contracts_w3sd - 0.9973

## [1] 0.0027

# Histogram
hist(contract_years, xlab = "Years Left in Contract", col = "green", border = "red", 
     xlim = c(0,8), ylim = c(0,225), breaks = 5)