Intro to R Part 2

This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Ctrl+Shift+Enter.

# Home-runs so far
HR_before <- c(11, 13, 12)
# Average Number of Home-runs per season wanted
wanted_HR <- 20
# Number of seasons
n_seasons <- 4
# Needed Home-runs on season 4
x_4 <- n_seasons*wanted_HR - sum(HR_before)
# Minimum number of Home-runs needed by Robert
x_4

[1] 44

# Robert's performance
Robert_HRs <- c(11, 13, 12,44)
# Find mean
mean(Robert_HRs)

[1] 20

# Robert's performance
Robert_HRs <- c(11, 13, 12,38)
# Find mean
mean(Robert_HRs)

[1] 18.5

#Find standard deviation
sd(Robert_HRs)

[1] 13.02562

# Find the maximum number of home-runs during the four seasons period
max(Robert_HRs)

[1] 38

# Find the minimum number of home-runs during the four seasons period
min(Robert_HRs)

[1] 11

summary(Robert_HRs)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  11.00   11.75   12.50   18.50   19.25   38.00 

# walks so far
W_before <- c(79, 108,41,145, 135)
# Average Number of Home-runs per season wanted
wanted_W <- 100
# Number of seasons
n_seasons <- 6
# Needed Home-runs on season 6
x_6 <- n_seasons*wanted_W - sum(W_before)
# Minimum number of Home-runs needed by Robert
x_6

[1] 92

n_1 <- 10
n_2 <- 4
y_1 <- 72000
y_2 <- 84000
# Mean salary overall
salary_ave <-  (n_1*y_1 + n_2*y_2)/(n_1+n_2)
salary_ave

[1] 75428.57

n_1 <- 7
n_2 <- 9
y_1 <- 102000
y_2 <- 91000
# Mean salary overall
salary_ave <-  (n_1*y_1 + n_2*y_2)/(n_1+n_2)
salary_ave

[1] 95812.5

getwd()

[1] "/cloud/project"

contract_length <- read.table("allcontracts.csv", header = TRUE, sep = ",")
contract_years <- contract_length$years

# Mean 
contracts_mean  <- mean(contract_years)
contracts_mean

[1] 3.458918

# Median
contracts_median <- median(contract_years)
contracts_median

[1] 3

# Find number of observations
contracts_n <- length(contract_years)
# Find standard deviation
contracts_sd <- sd(contract_years)
contracts_n

[1] 499

contracts_sd

[1] 1.69686

contracts_w1sd <- sum((contract_years - contracts_mean)/contracts_sd < 1)/ contracts_n
# Percentage of observation within one standard deviation of the mean
contracts_w1sd

[1] 0.8416834

## Difference from empirical 
contracts_w1sd - 0.68

[1] 0.1616834

## Within 2 sd
contracts_w2sd <- sum((contract_years - contracts_mean)/ contracts_sd < 2)/contracts_n
contracts_w2sd

[1] 1

## Difference from empirical 
contracts_w2sd - 0.95

[1] 0.05

## Within 3 sd 
contracts_w3sd <- sum((contract_years - contracts_mean)/ contracts_sd < 3)/contracts_n
contracts_w3sd

[1] 1

## Difference from empirical 
contracts_w3sd - 0.9973

[1] 0.0027

# Create histogram
hist(contract_years,xlab = "Years Left in Contract",col = "green",border = "red", xlim = c(0,6), ylim = c(0,250),
   breaks = 3)

Answers to Question 3

doubles <- read.table("doubles_hit.csv", header = TRUE, sep = ",")
doublesnumber <- doubles$doubles_hit

# Mean 
doublesnumber_mean  <- mean(doublesnumber)
doublesnumber_mean

[1] 23.55

# Median
doublesnumber_median <- median(doublesnumber)
doublesnumber_median

[1] 23.5

# Find number of observations
players_n <- length(doublesnumber)
# Find standard deviation
players_sd <- sd(doublesnumber)

doublesnumber_w1sd <- sum((doublesnumber - doublesnumber_mean)/players_sd < 1)/ players_n
# Percentage of observation within one standard deviation of the mean
doublesnumber_w1sd

[1] 0.79

## Difference from empirical 
doublesnumber_w1sd - 0.68

[1] 0.11

## Within 2 sd
doublesnumber_w2sd <- sum((doublesnumber - doublesnumber_mean)/ players_sd < 2)/players_n
doublesnumber_w2sd

[1] 1

## Difference from empirical 
contracts_w2sd - 0.95

[1] 0.05

## Within 3 sd 
doublesnumber_w3sd <- sum((doublesnumber - doublesnumber_mean)/ players_sd < 3)/players_n
doublesnumber_w3sd

[1] 1

## Difference from empirical 
doublesnumber_w3sd - 0.9973

[1] 0.0027

hist(doublesnumber,xlab = "Amount of doubles hits",col = "green",border = "red", xlim = c(0,6), ylim = c(0,250),
   breaks = 3)