2.1 Clean the work environment

Caution: this action cannot be undone!

# Clean work environment 
rm(list = ls()) # USE with CAUTION: this will delete everything in your environment

2.2 Activate packages

Use the function library to activate/load R packages.

# Load packages
library(tidyverse)
library(stargazer)

These two packages should now appear as “selected” in the Packages tab (bottom right of the screen).

3.1 .RData

This “.RData” file format is specific to R. It is loaded using the load() function. The following command loads the ceosal2.RData file and automatically stores its contents in the work environment. Note that when using the load() function, we do not need to give a name to the file we are loading in order for it to be saved in our Environment.

# Load data
load("data/ceosal2.RData")

“.RData” files can store multiple objects, so it is important to check what objects were loaded. You can see that two new objects appeared in your work environment:

• Data: This is a table with data on CEO salaries.
• Desc: This is a table with the description of each variable in Data.

3.2 .csv Data

Since there are many software alternatives for data analysis (e.g. Excel, SPSS, Stata, MatLab), data are often distributed in “open” formats such as “.csv” (comma separated values). “.csv” files are text files in which each line of text corresponds to a row of data and each column of data is separated by a comma. To load a “.csv” file we can use the function read_delim() specifying that the delimiter is a comma (this function will also work for files that use different delimiters such as tab or semicolon), or we can use the function read_csv().

The following command reads the ceosal2.csv file and stores its contents in an object. Note that when using the read_delim() or the read_csv() functions, we need to give a name to the file we are loading in order for it to be saved in our Environment (otherwise the file is simply printed to the console.)

# Read comma delimited file
tb.ceosal2 <- read_delim("data/ceosal2.csv", delim= ",")
# or
tb.ceosal2 <- read_csv("data/ceosal2.csv")

5.1 Table info

We can get the names of the variables in a dataset by using the function names():

# Print the names of variables in dataset
names(tb.ceosal2)

##  [1] "salary"   "age"      "college"  "grad"     "comten"   "ceoten"  
##  [7] "sales"    "profits"  "mktval"   "lsalary"  "lsales"   "lmktval" 
## [13] "comtensq" "ceotensq" "profmarg"

An easy way to change the name of a variable is using the rename() function.

# Rename variables
tb.ceosal2 <- tb.ceosal2 %>%
  rename(logsales=lsales)

Note that we are creating a new object tb.ceosal2 (that is, we are overwriting our original data set) that contains the same data as the original but with a new name logsales for the variable previously called lsales. Note also that we have used the pipe operator. We can read the code as: take tb.ceosal2 “and then” rename the variable lsales and store this changed data set as tb.ceosal2 (overwrite the original).

We can count the number of columns in the data set using ncol():

# Count number of columns/variables in dataset
ncol(tb.ceosal2)

## [1] 15

We can count the number of observations (rows) using nrow() or summarise(). The summarise() function “creates a new data frame. It will have one (or more) rows for each combination of grouping variables; if there are no grouping variables, the output will have a single row summarizing all observations in the input.”³. The function n() returns the number of observations in a current group.

# Count the number of observations (rows)
nrow(tb.ceosal2)

## [1] 177

# or:
tb.ceosal2 %>% 
  summarize(n_row = n())

Below is a list of useful functions for exploring and interacting with your data in R:

⚠️ Note on Capitalization: R is case-sensitive. This means Mean() will not work, but mean() will. If a function or variable doesn’t work as expected, double-check your spelling and capitalization first.

to top

5.2 Ordering data

The function arrange() allows us to order the data.

# Ordering the data in ascending order (default) (output omitted)
tb.ceosal2 %>% 
  arrange(age)   

# Ordering the data in descending order (output omitted)
tb.ceosal2 %>% 
  arrange(desc(age)) 

Ordering the data using multiple conditions:

# Order data by age (ascending) and then by grad (ascending) (output omitted)
tb.ceosal2 %>% 
  arrange(age, grad)       

# Order data by grad (descending) and then by age (ascending) (output omitted)
tb.ceosal2 %>% 
  arrange(desc(grad), age) 

Note that these commands do not permanently order the data set — they only output the reordered set. To permanently order the data we would have to replace the contents of the object, doing something like tb.ceosal2 <- tb.ceosal2 %>% arrange(age,grad).

to top

5.3 Subsetting data

We can use the filter() function to subset the data based on any criteria we may want. For instance, we may want to focus our analysis on only young CEOs:

# Keep only CEOs who are 45 years old or younger
tb.ceosal2 %>% 
  filter(age <= 45)   

# Create new tibble with the filtered data
tb.young.ceosal2 <-  tb.ceosal2 %>% 
  filter(age <= 45) 

Note that the first command simply lists all the rows for which CEO age is below the specified threshold.

# Select CEOs who 45 years old or younger AND have a graduate degree.
tb.ceosal2 %>% 
  filter(age <= 45 & grad == 1)

# Select CEOs who are younger than 35 OR have a salary higher than 5000.
tb.ceosal2 %>% 
  filter(age < 35 | salary > 5000)

5.4 Creating new variables

To add a new variable to a tibble we use the function mutate().

Create a new variable that transforms/is a function of an existing variable(s):

# Add new variables that are functions of existing variables
tb.ceosal2 <- tb.ceosal2 %>% 
  mutate(log_salary = log(salary))

tb.ceosal2 <- tb.ceosal2 %>% 
  mutate(age_squared = age^2)

Create new variables that contain values specified by us:

# Add new variables that take on specific values
tb.ceosal2 <- tb.ceosal2 %>% 
  mutate(one = 1)

Deleting a variable:

# Delete a variable
tb.ceosal2 <- tb.ceosal2 %>% 
  select(-log_salary)

We can use the function head() or names() to verify the creation/deletion of variables.

to top

5.5 Grouping Data

Oftentimes we want to summarize data by a given grouping variable or set of variables. The function group_by allow us to group data. The following operations will be performed to each group. For instance:

# Count number of CEOs with and without graduate degree
tb.ceosal2 %>% 
  group_by(grad) %>%  
  summarize(n_ceo = n()) %>% 
  ungroup()

After performing the intended operation we can use the function ungroup() to remove the grouping of the data.

Grouping can be done using multiple variables as follows:

# Count number of CEOs with and without graduate and colleges degree
tb.ceosal2 %>% 
  group_by(grad, college) %>%  
  summarize(n_ceo = n()) %>% 
  ungroup()

to top