##############################################

##################################

# R PROGRAMMING PRACTICAL - BCA SEMESTER VI

# University of Madras - Complete Exercise Solutions

# Course Code: 320C61

##############################################
##################################

##############################################
##################################

# EXERCISE 1: DATA IN R

##############################################
##################################

cat("\n=== EXERCISE 1: DATA IN R ===\n")

# Basic data types

num_var <- 42

char_var <- "Hello R"

logical_var <- TRUE

complex_var <- 3 + 4i

# Vectors

numeric_vector <- c(1, 2, 3, 4, 5)

character_vector <- c("apple", "banana", "cherry")

logical_vector <- c(TRUE, FALSE, TRUE)

# Matrices

my_matrix <- matrix(1:9, nrow = 3, ncol = 3)

print("Matrix:")

print(my_matrix)

# Arrays

my_array <- array(1:24, dim = c(3, 4, 2))

# Data Frames

student_data <- [Link](

Name = c("John", "Alice", "Bob", "Diana"),

Age = c(20, 22, 21, 23),

Grade = c("A", "B", "A", "A"),

Score = c(85, 78, 92, 88)

print("Student Data Frame:")

print(student_data)

# Lists

my_list <- list(

numbers = c(1, 2, 3),

name = "R Programming",

matrix = matrix(1:4, nrow = 2),

dataframe = student_data

##############################################
##################################

# EXERCISE 2: READING AND WRITING DATA

##############################################
##################################

cat("\n=== EXERCISE 2: READING AND WRITING DATA ===\n")

# Writing CSV file

[Link](student_data, "student_data.csv", [Link] = FALSE)

cat("CSV file created: student_data.csv\n")

# Reading CSV file

read_data <- [Link]("student_data.csv")

print("Data read from CSV:")

print(read_data)

# Writing to text file

[Link](student_data, "student_data.txt", sep = "\t", [Link] = FALSE)

# Reading from text file

text_data <- [Link]("student_data.txt", header = TRUE, sep = "\t")

# Writing and reading RDS (R Data Serialization)

saveRDS(student_data, "student_data.rds")

rds_data <- readRDS("student_data.rds")

# Save and load R workspace

save(student_data, my_matrix, file = "[Link]")

# load("[Link]")
##############################################
##################################

# EXERCISE 3: R AND DATABASES

##############################################
##################################

cat("\n=== EXERCISE 3: R AND DATABASES ===\n")

# Using SQLite database (built-in)

if(require(RSQLite)) {

# Create connection

con <- dbConnect(RSQLite::SQLite(), "student_db.sqlite")

# Write data to database

dbWriteTable(con, "students", student_data, overwrite = TRUE)

# Query database

query_result <- dbGetQuery(con, "SELECT * FROM students WHERE Age >

21")

print("Database Query Result:")

print(query_result)

# Close connection

dbDisconnect(con)

} else {

cat("Install RSQLite package: [Link]('RSQLite')\n")

}
##############################################
##################################

# EXERCISE 4: DATES

##############################################
##################################

cat("\n=== EXERCISE 4: DATES ===\n")

# Current date and time

current_date <- [Link]()

current_time <- [Link]()

cat("Current Date:", [Link](current_date), "\n")

cat("Current Time:", [Link](current_time), "\n")

# Creating dates

my_date <- [Link]("2024-01-15")

formatted_date <- format(my_date, "%B %d, %Y")

cat("Formatted Date:", formatted_date, "\n")

# Date arithmetic

future_date <- my_date + 30

date_diff <- [Link](difftime(future_date, my_date, units = "days"))

cat("Days difference:", date_diff, "\n")

# Working with POSIXct

timestamp <- [Link]("2024-01-15 14:30:00")

cat("Timestamp:", [Link](timestamp), "\n")

# Extract components

year <- format(my_date, "%Y")

month <- format(my_date, "%m")

day <- format(my_date, "%d")

##############################################
##################################

# EXERCISE 5: FACTORS

##############################################
##################################

cat("\n=== EXERCISE 5: FACTORS ===\n")

# Creating factors

gender <- factor(c("Male", "Female", "Male", "Female", "Male"))

print("Gender Factor:")

print(gender)

# Factor levels

education <- factor(c("High School", "Bachelor", "Master", "Bachelor"),

levels = c("High School", "Bachelor", "Master", "PhD"),

ordered = TRUE)

print("Ordered Education Factor:")

print(education)

# Factor manipulation

levels(gender)

nlevels(gender)
table(gender)

# Converting factors

[Link](education)

[Link](gender)

# Relevel factors

gender_releveled <- relevel(gender, ref = "Female")

##############################################
##################################

# EXERCISE 6: SUBSETTING

##############################################
##################################

cat("\n=== EXERCISE 6: SUBSETTING ===\n")

# Vector subsetting

vec <- c(10, 20, 30, 40, 50)

vec[1] # First element

vec[c(1, 3, 5)] # Multiple elements

vec[-2] # Exclude second element

vec[vec > 25] # Conditional subsetting

# Matrix subsetting

mat <- matrix(1:12, nrow = 3, ncol = 4)

mat[2, 3] # Element at row 2, col 3

mat[2, ] # Entire row 2

mat[, 3] # Entire column 3

mat[1:2, 2:4] # Submatrix

# Data frame subsetting

df <- [Link](

ID = 1:5,

Name = c("A", "B", "C", "D", "E"),

Score = c(85, 90, 78, 92, 88)

df[df$Score > 85, ] # Rows where Score > 85

df[df$Score > 85, "Name"] # Names where Score > 85

subset(df, Score > 85) # Using subset function

df[df$Score > 85 & df$ID < 5, ] # Multiple conditions

##############################################
##################################

# EXERCISE 7: CHARACTER MANIPULATION

##############################################
##################################

cat("\n=== EXERCISE 7: CHARACTER MANIPULATION ===\n")

# String operations

text <- "R Programming"

tolower(text)

toupper(text)

nchar(text)
# String concatenation

paste("Hello", "World")

paste0("R", "Programming") # No separator

# Substring

substr(text, 1, 4)

substring(text, 3, 8)

# String replacement

gsub("Programming", "Language", text)

sub("R", "Python", text)

# String splitting

strsplit("apple,banana,cherry", ",")

# Pattern matching

grep("gram", text)

grepl("prog", text, [Link] = TRUE)

# String formatting

sprintf("Score: %.2f", 85.5678)

##############################################
##################################

# EXERCISE 8: DATA AGGREGATION

##############################################
##################################

cat("\n=== EXERCISE 8: DATA AGGREGATION ===\n")

# Sample data

sales_data <- [Link](

Region = c("North", "South", "North", "East", "South", "East"),

Product = c("A", "B", "A", "B", "A", "B"),

Sales = c(100, 150, 120, 180, 140, 160)

# Aggregate function

agg_result <- aggregate(Sales ~ Region, data = sales_data, FUN = sum)

print("Aggregated Sales by Region:")

print(agg_result)

# Multiple aggregations

agg_multi <- aggregate(Sales ~ Region + Product, data = sales_data, FUN =

mean)

print("Average Sales by Region and Product:")

print(agg_multi)

# Using tapply

tapply(sales_data$Sales, sales_data$Region, sum)

# Using by

by(sales_data$Sales, sales_data$Region, summary)

##############################################
##################################

# EXERCISE 9: RESHAPING DATA BASICS

##############################################
##################################

cat("\n=== EXERCISE 9: RESHAPING DATA BASICS ===\n")

# Wide to long format

wide_data <- [Link](

ID = 1:3,

Year2021 = c(100, 110, 120),

Year2022 = c(105, 115, 125),

Year2023 = c(110, 120, 130)

long_data <- reshape(wide_data,

varying = c("Year2021", "Year2022", "Year2023"),

[Link] = "Value",

timevar = "Year",

times = c(2021, 2022, 2023),

direction = "long")

print("Long Format Data:")

print(long_data)

# Long to wide format

wide_back <- reshape(long_data,

timevar = "Year",

idvar = "ID",

direction = "wide")

# Using stack and unstack

stacked <- stack(wide_data[, -1])

unstacked <- unstack(stacked)

##############################################
##################################

# EXERCISE 10: THE R ENVIRONMENT

##############################################
##################################

cat("\n=== EXERCISE 10: THE R ENVIRONMENT ===\n")

# List objects in workspace

ls()

# Remove objects

temp_var <- 10

rm(temp_var)

# Get working directory

getwd()

# Set working directory

# setwd("/path/to/directory")

# Search path

search()

# Installed packages

[Link]()[1:5, c("Package", "Version")]

# Load package

# library(package_name)

# Session information

sessionInfo()

# Memory usage

[Link](student_data)

# Get help

# ?mean

# help(mean)

##############################################
##################################

# EXERCISE 11: PROBABILITY AND DISTRIBUTIONS

##############################################
##################################

cat("\n=== EXERCISE 11: PROBABILITY AND DISTRIBUTIONS ===\n")

# Normal distribution

x <- seq(-4, 4, length = 100)

y <- dnorm(x, mean = 0, sd = 1)

plot(x, y, type = "l", main = "Normal Distribution",

xlab = "x", ylab = "Density")

# Probability calculations

pnorm(1.96) # P(Z <= 1.96)

qnorm(0.975) # Z-value for 97.5% probability

rnorm(10, mean = 100, sd = 15) # Random normal values

# Binomial distribution

dbinom(3, size = 10, prob = 0.5) # P(X = 3)

pbinom(3, size = 10, prob = 0.5) # P(X <= 3)

rbinom(10, size = 10, prob = 0.5) # Random binomial values

# Poisson distribution

dpois(5, lambda = 3)

ppois(5, lambda = 3)

# Uniform distribution

runif(10, min = 0, max = 1)

##############################################
##################################

# EXERCISE 12: DESCRIPTIVE STATISTICS AND GRAPHICS

##############################################
##################################

cat("\n=== EXERCISE 12: DESCRIPTIVE STATISTICS AND GRAPHICS ===\n")

# Sample data

scores <- c(85, 78, 92, 88, 76, 95, 82, 90, 87, 91)

# Measures of central tendency

mean_score <- mean(scores)

median_score <- median(scores)

# mode (no built-in function)

# Measures of dispersion

var_score <- var(scores)

sd_score <- sd(scores)

range_score <- range(scores)

iqr_score <- IQR(scores)

cat("Mean:", mean_score, "\n")

cat("Median:", median_score, "\n")

cat("SD:", sd_score, "\n")

# Summary statistics

summary(scores)

# Graphics

par(mfrow = c(2, 2)) # 2x2 plot layout

# Histogram

hist(scores, main = "Histogram of Scores", xlab = "Scores", col = "lightblue")

# Boxplot

boxplot(scores, main = "Boxplot of Scores", ylab = "Scores", col =

"lightgreen")

# Scatter plot

x <- 1:10

plot(x, scores, main = "Scatter Plot", xlab = "Student ID",

ylab = "Score", pch = 19, col = "red")

# Bar plot

categories <- c("A", "B", "C", "D")

counts <- c(15, 20, 18, 12)

barplot(counts, [Link] = categories, main = "Bar Plot",

xlab = "Category", ylab = "Count", col = "orange")

par(mfrow = c(1, 1)) # Reset plot layout

##############################################
##################################

# EXERCISE 13: ONE- AND TWO-SAMPLE TESTS

##############################################
##################################

cat("\n=== EXERCISE 13: ONE- AND TWO-SAMPLE TESTS ===\n")

# One-sample t-test

sample_data <- c(23, 25, 27, 29, 31, 28, 26, 30, 24, 28)

t_test_one <- [Link](sample_data, mu = 25)

print("One-Sample t-test:")

print(t_test_one)

# Two-sample t-test (independent)

group1 <- c(23, 25, 27, 29, 31)

group2 <- c(20, 22, 24, 26, 28)

t_test_two <- [Link](group1, group2)

print("Two-Sample t-test:")

print(t_test_two)

# Paired t-test

before <- c(120, 135, 128, 140, 132)

after <- c(115, 130, 125, 135, 128)

t_test_paired <- [Link](before, after, paired = TRUE)

print("Paired t-test:")

print(t_test_paired)

# Wilcoxon test (non-parametric)

wilcox_test <- [Link](group1, group2)

print("Wilcoxon Test:")

print(wilcox_test)

##############################################
##################################
# EXERCISE 14: REGRESSION AND CORRELATION

##############################################
##################################

cat("\n=== EXERCISE 14: REGRESSION AND CORRELATION ===\n")

# Sample data

hours_studied <- c(2, 3, 4, 5, 6, 7, 8, 9, 10, 11)

exam_scores <- c(55, 60, 65, 70, 75, 80, 85, 88, 92, 95)

# Correlation

cor_result <- cor(hours_studied, exam_scores)

cat("Correlation coefficient:", cor_result, "\n")

# Correlation test

cor_test <- [Link](hours_studied, exam_scores)

print(cor_test)

# Simple linear regression

model <- lm(exam_scores ~ hours_studied)

print("Linear Regression Model:")

print(summary(model))

# Plotting regression

plot(hours_studied, exam_scores, main = "Regression Analysis",

xlab = "Hours Studied", ylab = "Exam Scores", pch = 19)

abline(model, col = "red", lwd = 2)

# Predictions

new_data <- [Link](hours_studied = c(5.5, 8.5))

predictions <- predict(model, newdata = new_data)

cat("Predictions:", predictions, "\n")

##############################################
##################################

# EXERCISE 15: ANALYSIS OF VARIANCE AND KRUSKAL-WALLIS TEST

##############################################
##################################

cat("\n=== EXERCISE 15: ANOVA AND KRUSKAL-WALLIS TEST ===\n")

# Sample data for ANOVA

group_A <- c(23, 25, 27, 29, 31)

group_B <- c(28, 30, 32, 34, 36)

group_C <- c(20, 22, 24, 26, 28)

# Create data frame

anova_data <- [Link](

value = c(group_A, group_B, group_C),

group = factor(rep(c("A", "B", "C"), each = 5))

# One-way ANOVA

anova_result <- aov(value ~ group, data = anova_data)

print("ANOVA Results:")

print(summary(anova_result))
# Post-hoc test (Tukey HSD)

tukey_result <- TukeyHSD(anova_result)

print("Tukey HSD:")

print(tukey_result)

# Kruskal-Wallis test (non-parametric alternative to ANOVA)

kruskal_result <- [Link](value ~ group, data = anova_data)

print("Kruskal-Wallis Test:")

print(kruskal_result)

# Boxplot for visualization

boxplot(value ~ group, data = anova_data,

main = "Comparison of Groups",

xlab = "Group", ylab = "Value", col = c("red", "green", "blue"))

##############################################
##################################

# EXERCISE 16: TABULAR DATA

##############################################
##################################

cat("\n=== EXERCISE 16: TABULAR DATA ===\n")

# Creating contingency tables

survey_data <- [Link](

Gender = c("M", "F", "M", "F", "M", "F", "M", "F"),

Preference = c("A", "B", "A", "A", "B", "B", "A", "B")

)

# Frequency table

freq_table <- table(survey_data$Gender, survey_data$Preference)

print("Frequency Table:")

print(freq_table)

# Proportions

prop_table <- [Link](freq_table)

print("Proportion Table:")

print(prop_table)

# Row and column proportions

[Link](freq_table, 1) # Row proportions

[Link](freq_table, 2) # Column proportions

# Chi-square test

chi_test <- [Link](freq_table)

print("Chi-Square Test:")

print(chi_test)

# Marginal tables

[Link](freq_table, 1) # Row totals

[Link](freq_table, 2) # Column totals

# Add margins

addmargins(freq_table)
##############################################
##################################

# EXERCISE 17: POWER AND COMPUTATION OF SAMPLE SIZE

##############################################
##################################

cat("\n=== EXERCISE 17: POWER AND SAMPLE SIZE ===\n")

# Power calculation for t-test

power_result <- [Link](

n = NULL, # Sample size to be calculated

delta = 0.5, # Effect size

sd = 1, # Standard deviation

[Link] = 0.05, # Significance level

power = 0.80, # Desired power

type = "[Link]"

print("Power Analysis for t-test:")

print(power_result)

# Sample size for proportion test

power_prop <- [Link](

n = NULL,

p1 = 0.65,

p2 = 0.75,

[Link] = 0.05,

power = 0.80
)

print("Sample Size for Proportion Test:")

print(power_prop)

# Power for ANOVA

power_anova <- [Link](

groups = 3,

n = NULL,

[Link] = 1,

[Link] = 3,

[Link] = 0.05,

power = 0.80

print("Power Analysis for ANOVA:")

print(power_anova)

##############################################
##################################

# EXERCISE 18: ADVANCED DATA HANDLING

##############################################
##################################

cat("\n=== EXERCISE 18: ADVANCED DATA HANDLING ===\n")

# Merging data frames

df1 <- [Link](ID = 1:4, Name = c("A", "B", "C", "D"))

df2 <- [Link](ID = c(2, 3, 4, 5), Score = c(85, 90, 78, 92))
# Inner join

inner_merge <- merge(df1, df2, by = "ID")

print("Inner Merge:")

print(inner_merge)

# Outer join

outer_merge <- merge(df1, df2, by = "ID", all = TRUE)

print("Outer Merge:")

print(outer_merge)

# Apply family functions

data_matrix <- matrix(1:12, nrow = 3)

# apply on matrix

row_sums <- apply(data_matrix, 1, sum)

col_means <- apply(data_matrix, 2, mean)

# lapply (returns list)

my_list <- list(a = 1:5, b = 6:10, c = 11:15)

list_means <- lapply(my_list, mean)

# sapply (simplified output)

vector_means <- sapply(my_list, mean)

# mapply (multivariate)

mapply_result <- mapply(sum, 1:5, 6:10, 11:15)

# Data cleaning

messy_data <- [Link](

ID = c(1, 2, NA, 4, 5),

Value = c(10, NA, 30, 40, 50)

# Remove NA rows

clean_data <- [Link](messy_data)

# Replace NA with mean

messy_data$Value[[Link](messy_data$Value)] <- mean(messy_data$Value,

[Link] = TRUE)

##############################################
##################################

# EXERCISE 19: MULTIPLE REGRESSION

##############################################
##################################

cat("\n=== EXERCISE 19: MULTIPLE REGRESSION ===\n")

# Sample data

multi_data <- [Link](

Sales = c(150, 180, 200, 220, 250, 280, 300, 320, 350, 380),

Advertising = c(10, 12, 15, 18, 20, 22, 25, 28, 30, 35),

Price = c(50, 48, 45, 42, 40, 38, 35, 32, 30, 28),

Competition = c(5, 6, 7, 8, 9, 10, 11, 12, 13, 14)

)
# Multiple regression model

multi_model <- lm(Sales ~ Advertising + Price + Competition, data =

multi_data)

print("Multiple Regression Summary:")

print(summary(multi_model))

# Coefficients

coef(multi_model)

# Confidence intervals

confint(multi_model)

# Predictions

new_obs <- [Link](Advertising = 20, Price = 40, Competition = 10)

predict(multi_model, newdata = new_obs, interval = "prediction")

# Model diagnostics

par(mfrow = c(2, 2))

plot(multi_model)

par(mfrow = c(1, 1))

# Variance Inflation Factor (VIF) - check for multicollinearity

# if(require(car)) {

# vif(multi_model)

#}
##############################################
##################################

# EXERCISE 20: LINEAR MODELS

##############################################
##################################

cat("\n=== EXERCISE 20: LINEAR MODELS ===\n")

# ANOVA as linear model

plant_data <- [Link](

Growth = c(20, 22, 19, 25, 27, 26, 30, 32, 31, 28, 29, 27),

Fertilizer = factor(rep(c("A", "B", "C"), each = 4))

# Linear model for ANOVA

lm_anova <- lm(Growth ~ Fertilizer, data = plant_data)

print("Linear Model (ANOVA):")

print(summary(lm_anova))

print(anova(lm_anova))

# ANCOVA (Analysis of Covariance)

ancova_data <- [Link](

Response = c(15, 18, 20, 22, 25, 28, 30, 32, 35, 38),

Group = factor(rep(c("Control", "Treatment"), each = 5)),

Covariate = c(10, 12, 14, 16, 18, 11, 13, 15, 17, 19)

ancova_model <- lm(Response ~ Group + Covariate, data = ancova_data)

print("ANCOVA Model:")

print(summary(ancova_model))

# Polynomial regression

x_poly <- 1:20

y_poly <- 3 + 2*x_poly + 0.5*x_poly^2 + rnorm(20, 0, 5)

poly_model <- lm(y_poly ~ poly(x_poly, 2))

print("Polynomial Regression:")

print(summary(poly_model))

##############################################
##################################

# EXERCISE 21: LOGISTIC REGRESSION

##############################################
##################################

cat("\n=== EXERCISE 21: LOGISTIC REGRESSION ===\n")

# Binary outcome data

logit_data <- [Link](

Age = c(22, 25, 28, 32, 35, 40, 45, 50, 55, 60),

Income = c(30, 35, 40, 45, 50, 55, 60, 65, 70, 75),

Purchase = c(0, 0, 0, 1, 0, 1, 1, 1, 1, 1)

# Logistic regression model

logit_model <- glm(Purchase ~ Age + Income,

data = logit_data,
 family = binomial(link = "logit"))

print("Logistic Regression Summary:")

print(summary(logit_model))

# Odds ratios

exp(coef(logit_model))

# Predictions (probabilities)

predicted_probs <- predict(logit_model, type = "response")

cat("Predicted Probabilities:\n")

print(predicted_probs)

# Classification

predicted_class <- ifelse(predicted_probs > 0.5, 1, 0)

# Confusion matrix

table(Predicted = predicted_class, Actual = logit_data$Purchase)

# Model fit statistics

# if(require(pscl)) {

# pR2(logit_model)

#}

##############################################
##################################

# EXERCISE 22: SURVIVAL ANALYSIS

##############################################
##################################

cat("\n=== EXERCISE 22: SURVIVAL ANALYSIS ===\n")

if(require(survival)) {

# Sample survival data

time <- c(5, 8, 12, 15, 20, 24, 30, 35, 40, 45)

status <- c(1, 1, 0, 1, 1, 0, 1, 0, 1, 1) # 1 = event occurred, 0 = censored

group <- factor(c(rep("A", 5), rep("B", 5)))

# Create survival object

surv_obj <- Surv(time, status)

# Kaplan-Meier survival curve

km_fit <- survfit(surv_obj ~ 1)

print("Kaplan-Meier Survival:")

print(km_fit)

# Plot survival curve

plot(km_fit, main = "Kaplan-Meier Survival Curve",

xlab = "Time", ylab = "Survival Probability",

[Link] = TRUE)

# Compare survival between groups

km_groups <- survfit(surv_obj ~ group)

plot(km_groups, col = c("red", "blue"),

main = "Survival by Group",

 xlab = "Time", ylab = "Survival Probability")

legend("topright", legend = c("Group A", "Group B"),

col = c("red", "blue"), lty = 1)

# Log-rank test

logrank_test <- survdiff(surv_obj ~ group)

print("Log-rank Test:")

print(logrank_test)

# Cox proportional hazards model

age <- c(45, 50, 55, 60, 65, 48, 52, 58, 62, 68)

cox_model <- coxph(surv_obj ~ group + age)

print("Cox Proportional Hazards Model:")

print(summary(cox_model))

} else {

cat("Install survival package: [Link]('survival')\n")

##############################################
##################################

# EXERCISE 23: RATES AND POISSON REGRESSION

##############################################
##################################

cat("\n=== EXERCISE 23: RATES AND POISSON REGRESSION ===\n")

# Count data

poisson_data <- [Link](

 Cases = c(2, 3, 5, 7, 9, 12, 15, 18, 20, 25),

Treatment = factor(rep(c("A", "B"), each = 5)),

Age = c(25, 30, 35, 40, 45, 28, 32, 38, 42, 48)

# Poisson regression

poisson_model <- glm(Cases ~ Treatment + Age,

data = poisson_data,

family = poisson(link = "log"))

print("Poisson Regression Summary:")

print(summary(poisson_model))

# Rate ratios (exponentiated coefficients)

cat("Rate Ratios:\n")

print(exp(coef(poisson_model)))

# Predictions

predict(poisson_model, type = "response")

# Goodness of fit

deviance(poisson_model)

pchisq(deviance(poisson_model), [Link](poisson_model), [Link] =

FALSE)

# Overdispersion check

# Check if residual deviance >> degrees of freedom

cat("Dispersion parameter:",
deviance(poisson_model)/[Link](poisson_model), "\n")

# If overdispersed, use quasi-Poisson

quasi_poisson_model <- glm(Cases ~ Treatment + Age,

data = poisson_data,

family = quasipoisson(link = "log"))

##############################################
##################################

# EXERCISE 24: NONLINEAR CURVE FITTING

##############################################
##################################

cat("\n=== EXERCISE 24: NONLINEAR CURVE FITTING ===\n")

# Exponential growth data

x_exp <- 1:20

y_exp <- 10 * exp(0.1 * x_exp) + rnorm(20, 0, 5)

# Nonlinear least squares (NLS)

nls_model <- nls(y_exp ~ a * exp(b * x_exp),

start = list(a = 10, b = 0.1))

print("Nonlinear Model Summary:")

print(summary(nls_model))

# Plot fitted curve

plot(x_exp, y_exp, main = "Nonlinear Curve Fitting",

xlab = "X", ylab = "Y", pch = 19)

lines(x_exp, predict(nls_model), col = "red", lwd = 2)

# Logistic growth model

y_logistic <- 100 / (1 + exp(-0.5 * (x_exp - 10))) + rnorm(20, 0, 2)

logistic_model <- n