TASK-2 name: Manipriyaa R

regno: 23BAI0214
problem-1
#Question-1
# Define the data
x <- c(3.545, 2.6, 3.245, 3.93, 3.995, 3.115, 3.235, 3.225, 2.44, 3.24, 2.29, 2.5, 4.02)
y <- c(30, 32, 30, 24, 26, 30, 33, 27, 37, 32, 37, 34, 26)
correlation <- cor(x, y)
cat("The correlation coefficient between weight (x) and fuel efficiency (y) is:", correlation, "\n")

## The correlation coefficient between weight (x) and fuel efficiency (y) is: -0.8977642

1
Problem-2
ENJOY <- c(4, 15, 1, 11, 13, 19, 6, 10, 15, 3, 11, 20, 7, 6, 7, 18, 8, 2, 7, 12, 13, 15, 4, 3, 9, 7, 10,
BUY <- c(16, 19, 0, 19, 25, 24, 23, 21, 13, 7, 28, 31, 4, 12, 14, 16, 20, 13, 12, 13, 22, 19, 12, 10,
READ <- c(6, 13, 1, 13, 12, 11, 7, 8, 12, 4, 15, 14, 7, 5, 7, 12, 10, 6, 9, 23, 9, 13, 9, 5, 7, 8, 8, 2

data <- data.frame(ENJOY, BUY, READ)

correlation_matrix <- cor(data)
print("Correlation Matrix:")

## [1] "Correlation Matrix:"

print(correlation_matrix)

## ENJOY BUY READ

## ENJOY 1.0000000 0.6226953 0.6595060
## BUY 0.6226953 1.0000000 0.5751954
## READ 0.6595060 0.5751954 1.0000000

1
Problem-3
# Define the data
Area <- c(1, 2, 3, 4, 5, 6, 7, 8)
Y <- c(110, 80, 70, 102, 105, 90, 70, 120)
X1 <- c(30, 40, 20, 50, 60, 40, 20, 60)
X2 <- c(11, 10, 7, 15, 19, 12, 8, 14)
data <- data.frame(Area, Y, X1, X2)
model <- lm(Y ~ X1 + X2, data=data)
summary(model)

##
## Call:
## lm(formula = Y ~ X1 + X2, data = data)
##
## Residuals:
## 1 2 3 4 5 6 7 8
## 24.282 -11.177 -4.765 -1.230 -9.183 -3.375 -5.863 11.311
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 53.9564 17.4097 3.099 0.0269 *
## X1 0.6558 0.7911 0.829 0.4449
## X2 1.0988 3.2298 0.340 0.7475
## ---
## Signif. codes: 0 ’***’ 0.001 ’**’ 0.01 ’*’ 0.05 ’.’ 0.1 ’ ’ 1
##
## Residual standard error: 14.12 on 5 degrees of freedom
## Multiple R-squared: 0.5977, Adjusted R-squared: 0.4368
## F-statistic: 3.715 on 2 and 5 DF, p-value: 0.1026

1
Problem-4

Load the dataset

data <- read.csv(“C:\Users\manip\Downloads\life_satisfaction_1.csv”, header=TRUE)

View the first few rows

head(data)

Select numerical columns (modify based on your dataset)

data_clean <- data[, c(“X2013”, “X2018”, “X2022”)]

Convert columns to numeric (if needed)

data_clean <- data.frame(lapply(data_clean, as.numeric))

Remove missing values

data_clean <- na.omit(data_clean)

Fit the regression model

model <- lm(X2013 ~ X2018 + X2022, data = data_clean)

Show model summary

summary(model)

1
Problem-5
# Given values
n <- 20 # Total trials
p <- 0.10 # Probability of success (defective screw)

# (i) Probability of exactly 2 defectives

p_exactly_2 <- dbinom(2, size = n, prob = p)
print(paste("P(X = 2) =", p_exactly_2))

## [1] "P(X = 2) = 0.285179807064298"

# (ii) Probability of at least 2 defectives

n <- 20 # Total trials
p <- 0.10
p_at_least_2 <- 1 - pbinom(1, size = n, prob = p)
print(paste("P(X � 2) =", p_at_least_2))

## [1] "P(X � 2) = 0.608253001874832"

n <- 20 # Total trials

p <- 0.10
# (iii) Probability of between 1 and 3 defectives (inclusive)
p_between_1_and_3 <- sum(dbinom(1:3, size = n, prob = p))
print(paste("P(1 � X � 3) =", p_between_1_and_3))

## [1] "P(1 � X � 3) = 0.745470021975096"

1
Problem
Problem 6
1: X ~ Bin(20, 0.5)
n1 <- 20 p1 <- 0.5

# (i) P(X < 4) = P(X = 0) + P(X = 1) + P(X = 2) + P(X = 3)

n1 <- 20
p1 <- 0.5

p1_less_than_4 <- pbinom(3, size = n1, prob = p1)

print(paste("P(X < 4) =", p1_less_than_4))

## [1] "P(X < 4) = 0.00128841400146485"

# (ii) P(X > 11) = 1 - P(X � 11)

n1 <- 20
p1 <- 0.5

p1_greater_than_11 <- 1 - pbinom(11, size = n1, prob = p1)

print(paste("P(X > 11) =", p1_greater_than_11))

## [1] "P(X > 11) = 0.25172233581543"

# (iii) P(1 � X � 8) = P(X � 8) - P(X � 0)

n1 <- 20
p1 <- 0.5

p1_between_1_and_8 <- pbinom(8, size = n1, prob = p1) - pbinom(0, size = n1, prob = p1)
print(paste("P(1 � X � 8) =", p1_between_1_and_8))

## [1] "P(1 � X � 8) = 0.251721382141113"

1
Problem-7
n <- 10 p <- 0.5

# (i) P(X � 5) = 1 - P(X � 4)

n <- 10
p <- 0.5
p_at_least_5 <- 1 - pbinom(4, size = n, prob = p)
print(paste("P(X � 5) =", p_at_least_5))

## [1] "P(X � 5) = 0.623046875"

# (ii) P(X = 5)
n <- 10
p <- 0.5
p_exactly_5 <- dbinom(5, size = n, prob = p)
print(paste("P(X = 5) =", p_exactly_5))

## [1] "P(X = 5) = 0.24609375"

# (iii) P(4 � X � 6) = P(X � 6) - P(X � 3)

n <- 10
p <- 0.5
p_between_4_and_6 <- pbinom(6, size = n, prob = p) - pbinom(3, size = n, prob = p)
print(paste("P(4 � X � 6) =", p_between_4_and_6))

## [1] "P(4 � X � 6) = 0.65625"

1
Problem 8
n <- 30 p <- 0.558

# 1. How is X distributed?
n <- 30
p <- 0.558
cat("X follows a Binomial distribution: X ~ Bin(30, 0.558)\n")

## X follows a Binomial distribution: X ~ Bin(30, 0.558)

# 2. Sketch the Probability Mass Function (PMF)

n <- 30
p <- 0.558
x_vals <- 0:n
pmf_vals <- dbinom(x_vals, size = n, prob = p)
plot(x_vals, pmf_vals, type = "h", col = "blue", lwd = 2,
main = "Probability Mass Function", xlab = "X", ylab = "P(X)")

Probability Mass Function

0.15
0.10
P(X)

0.05
0.00

0 5 10 15 20 25 30

# 3. Sketch the Cumulative Distribution Function (CDF)

n <- 30
p <- 0.558
cdf_vals <- pbinom(x_vals, size = n, prob = p)
plot(x_vals, cdf_vals, type = "s", col = "red", lwd = 2,
main = "Cumulative Distribution Function", xlab = "X", ylab = "P(X � x)")

1
 Cumulative Distribution Function
1.0
0.8
0.6
P(X = x)

0.4
0.2
0.0

0 5 10 15 20 25 30

# 4. P(X = 17)
n <- 30
p <- 0.558
p_17 <- dbinom(17, size = n, prob = p)
cat("P(X = 17) =", p_17, "\n")

## P(X = 17) = 0.1450715

# 5. P(X � 13)
n <- 30
p <- 0.558
p_at_most_13 <- pbinom(13, size = n, prob = p)
cat("P(X � 13) =", p_at_most_13, "\n")

## P(X � 13) = 0.1171176

# 6. P(X > 11) = 1 - P(X � 11)

n <- 30
p <- 0.558
p_greater_11 <- 1 - pbinom(11, size = n, prob = p)
cat("P(X > 11) =", p_greater_11, "\n")

## P(X > 11) = 0.9726686

2
# 7. P(X � 15) = 1 - P(X � 14)
n <- 30
p <- 0.558
p_at_least_15 <- 1 - pbinom(14, size = n, prob = p)
cat("P(X � 15) =", p_at_least_15, "\n")

## P(X � 15) = 0.7953302

# 8. P(16 � X � 19) = P(X � 19) - P(X � 15)

n <- 30
p <- 0.558
p_between_16_19 <- pbinom(19, size = n, prob = p) - pbinom(15, size = n, prob = p)
cat("P(16 � X � 19) =", p_between_16_19, "\n")

## P(16 � X � 19) = 0.5223442

# 9. Mean of X (E[X])
n <- 30
p <- 0.558
mean_X <- n * p
cat("E[X] =", mean_X, "\n")

## E[X] = 16.74

# 10. Variance of X
n <- 30
p <- 0.558
var_X <- n * p * (1 - p)
cat("Var(X) =", var_X, "\n")

## Var(X) = 7.39908

# 11. Standard deviation of X

n <- 30
p <- 0.558
sd_X <- sqrt(var_X)
cat("SD(X) =", sd_X, "\n")

## SD(X) = 2.720125

# 12. E(4X + 51.324) = 4E[X] + 51.324

n <- 30
p <- 0.558
E_4X_plus_51 <- 4 * mean_X + 51.324
cat("E(4X + 51.324) =", E_4X_plus_51, "\n")

## E(4X + 51.324) = 118.284