Lab 4 Discussion

# Load the dataset
advertising <- read.csv("advertising.csv")

# View the dataset
head(advertising)

##      TV Radio Newspaper Sales
## 1 230.1  37.8      69.2  22.1
## 2  44.5  39.3      45.1  10.4
## 3  17.2  45.9      69.3  12.0
## 4 151.5  41.3      58.5  16.5
## 5 180.8  10.8      58.4  17.9
## 6   8.7  48.9      75.0   7.2

# Original sample size
nrow(advertising)

## [1] 200

# Randomly select 50% of the observations
set.seed(123)

advertising_half <- advertising[
  sample(nrow(advertising), nrow(advertising) / 2),
]

# Check new sample size
nrow(advertising_half)

## [1] 100

# EDA 1: Summary statistics for Sales
summary(advertising_half$Sales)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    5.30   10.88   15.95   14.97   18.52   26.20

# Histogram of Sales
hist(advertising_half$Sales,
     main = "Distribution of Sales",
     xlab = "Sales",
     ylab = "Frequency")

# EDA 2: TV Advertising vs. Sales
plot(advertising_half$TV,
     advertising_half$Sales,
     main = "TV Advertising vs. Sales",
     xlab = "TV Advertising",
     ylab = "Sales",
     pch = 19)

# Correlation between TV advertising and Sales
cor(advertising_half$TV, advertising_half$Sales)

## [1] 0.9021462