How to Analyze Data in R: A Beginner’s Guide

8 min readAug 1, 2023

Five key points

R is a powerful tool for data analysis, but it can be intimidating for beginners.
How to use R to import, explore, manipulate, model, and evaluate data using various functions and packages.
How to use functions from the tidyverse, stats, car, broom, and caret packages to perform different tasks in data analysis.
Predicts life expectancy based on GDP per capita and continent using regression models.
The complete code and dataset for this project are on data03.online.

R is a robust data analysis tool that can be intimidating for beginners. If you want to learn how to use R to analyze data, this article is for you. In this article, you will learn:

How to import data into R
How to explore data using descriptive statistics and visualization
How to manipulate data using dplyr
How to create predictive models using regression
How to evaluate and improve your models

After this article, you will have a reasonable basis for data analysis using R. You will also have a portfolio-worthy project to offer prospective employers or clients.

Importing Data into R

Before you can analyze data in R, import it from a source. There are several ways to import data into R, depending on the type and location of the data. For example, you may use the read.csv() method to read data from a CSV file or the read_excel() function to read data from an Excel file.

For this article, we will use a dataset from the Gapminder project, which contains information about countries’ life expectancy, GDP per capita, population, and other indicators over time.

To import the dataset into R, you can use the following code:

# Load the readr package
library(readr)
# Import the dataset
gapminder <- read_csv("gapminder.csv")

Exploring Data with Descriptive Statistics and Visualization

Once you have imported the data into R, you must explore it to understand its structure, distribution, and relationships. Exploratory data analysis (EDA) is crucial for any data analysis project.

Two main ways to explore data in R are descriptive statistics and visualization.

Descriptive statistics are numerical data summaries, such as mean, median, standard deviation, minimum, maximum, etc. They help you understand the central tendency, variability, and range of the data.
Visualization is a graphical representation of the data, such as histograms, boxplots, scatterplots, etc. They help you see the data’s shape, outliers, patterns, and trends.

Descriptive Statistics

To perform EDA in R, you can use functions from the tidyverse packages. The tidyverse is a collection of packages that make data analysis more accessible and more consistent in R. Some of the most valuable packages for EDA are:

dplyr: for data manipulation
ggplot2: for data visualization
tidyr: for data tidying
tibble: for creating and working with tibbles (a modern version of data frames)

To load these packages into R, you can use the following code:

# Load the tidyverse packages
library(tidyverse)

To see the structure of the gapminder dataset, you can use the str() function:

# See the structure of the
dataset
str(gapminder)

It will show you the names and types of the variables in the dataset and some sample values.

To see a summary of the dataset, you can use the summary() function:

# See a summary of the dataset
summary(gapminder)

It will show you some descriptive statistics for each variable in the dataset.

To see a glimpse of the dataset, you can use the glimpse() function from tibble:

# See a glimpse of the dataset
glimpse(gapminder)

It will show you a more compact and informative view of the dataset.

To see a sample of rows from the dataset, you can use the head() function:

# See a sample of rows from the dataset
head(gapminder)

It will show you the first six rows of the dataset by default. You can change this by specifying a different number inside the parentheses.

To see how many rows and columns are in the dataset, you can use the dim() function:

# See how many rows and columns
are in the dataset
dim(gapminder)

It will show you a vector with two elements: the number of rows and columns.

To see how many unique values are in each variable, you can use the n_distinct() function from dplyr:

# See how many unique values are
in each variable
n_distinct(gapminder$country) # Number of unique countries
n_distinct(gapminder$continent) # Number of unique continents
n_distinct(gapminder$year) # Number of unique years

Run this code and explore the output

It will show you the number of distinct values in each variable.

Data Visualization

To see the distribution of a numeric variable, you can use the hist() function to create a histogram:

# See the distribution of life expectancy
hist(gapminder$lifeExp)

It will show you a histogram of the life expectancy variable, which shows how many observations fall into different bins.

To see the distribution of a categorical variable, you can use the barplot() function to create a bar plot:

# See the distribution of continent
barplot(table(gapminder$continent))

It will show you a bar plot of the continent variable, which shows how many observations belong to each category.

You may use the plot() method to build a scatterplot to observe the relationship between two numerical variables:

# See the relationship between GDP per capita and life
expectancy
plot(gapminder$gdpPercap, gapminder$lifeExp)

It will show you a scatterplot of the GDP per capita and life expectancy variables, showing how they vary.

To see the relationship between a numeric and a categorical variable, you can use the boxplot() function to create a box plot:

# See the relationship between continent and life expectancy
boxplot(lifeExp ~ continent, data = gapminder)

It will show you a box plot of the life expectancy variable by continent, which shows how they differ across groups.

To see the relationship between two categorical variables, you can use the mosaicplot() function to create a mosaic plot:

# See the relationship between continent and year
mosaicplot(table(gapminder$continent, gapminder$year))

It will show you a mosaic plot of the continent and year variables, which shows their association.

To produce more elaborate and customizable charts, you can utilize the ggplot2 software. The foundation of ggplot2 is the syntax of graphics, a technique for constructing charts using layers. To build a plot using ggplot2, you need to supply three things:

The data and variables to plot
The geometric object (geom) represents the data
The aesthetic mapping (aes) defines how the variables are mapped to visual attributes

For example, to create a scatterplot of GDP per capita and life expectancy with ggplot2, you can use the following code:

# Create a scatterplot with ggplot2
ggplot(data = gapminder, # Specify the data
       mapping = aes(x = gdpPercap, y = lifeExp)) + # Specify the variables and
mapping
  geom_point() # Specify the geom

It will create a scatterplot similar to the one created with plot(), but with more options for customization. For example, you can add color, size, shape, or other attributes to your plot by adding them to the aes() function. You can add titles, labels, legends, or other elements as layers with +. You can also change the theme or scale of your plot by adding them as layers with +.

For example, to add color by continent and size by population to your scatterplot, you can use the following code:

# Add color and size to your scatterplot
ggplot(data = gapminder,
       mapping = aes(x = gdpPercap,
                     y = lifeExp,
                     color = continent,
                     size = pop)) +
  geom_point() +
  scale_x_log10() + # Change the x-axis scale to log10
  labs(title = "GDP per capita vs Life Expectancy",
       x = "GDP per capita (log10)",
       y = "Life Expectancy",
       color = "Continent",
       size = "Population") + # Add titles and labels
  theme_minimal() # Change the theme to minimal

It will create a more informative and appealing scatterplot that shows how GDP per capita and life expectancy vary by continent and population.

There are many other geoms and options that you can use with ggplot2 to create different types of plots. You can learn more about them from here.

Conclusion

In this article, you learned how to analyze data in R using various functions and packages. You learned how to:

Import data into R
Explore data using descriptive statistics and visualization
Manipulate data using dplyr
Create predictive models using regression
Evaluate and improve your models

You also created a portfolio-worthy project that you can showcase to potential employers or clients. You can find the complete code and dataset for this project here.

I hope you enjoyed this article and learned something new. If you have any questions or feedback, please comment below. Happy coding!

How to Learn Data Analysis with RSTUDIO: Join Our Community and Workshop Today!

Are you interested in learning how to analyze data with Rstudio?

Do you want to master the skills and tools to help you understand complex and large datasets? If yes, then you are in the right place!

We are a community of data enthusiasts who love to share our knowledge and experience with Rstudio, a powerful and versatile software for data analysis. We have created a YouTube channel where we post regular updates and tutorials on various topics related to Rstudio, such as data manipulation, visualization, modeling, reporting, and more.

You can find our channel here: Subscribe!

But that’s not all. We also have a special offer for you. We are launching an online training workshop for data analysis with Rstudio, where you will get access to a curated dataset for training, solved and real-world examples, and live sessions with our experts. This workshop will help you learn the fundamentals of Rstudio and some advanced techniques and best practices. You will also get a certificate of completion at the end of the workshop.
This is a limited-time offer, so don’t miss this opportunity to join our community and learn from the best.

All you need to do is register with us here. Register Now

Hurry up; the seats are filling fast! We hope to see you soon in our community and our workshop. Together, we can explore the amazing world of data analysis with Rstudio. Happy learning! 😊

If you are stuck with Data Analysis, you can also hire us: https://bit.ly/43KNuYY
Want to Explore free homework Resources? Explore it here:
https://bit.ly/3rTKH2n
Have Questions? Contact us: https://wa.me/message/J6ELCCB6EW7YC1
Join Our Communities: https://t.me/dataanalysis03
Watch Our Tutorials: https://youtube.com/@data.03