Data Manipulation and Analysis in R: Creating a Table with Means and Frequencies

In this article, we will explore how to create a table that displays the means and frequencies of each variable divided by sex. We will use the data.table package in R to achieve this.

Introduction

The provided dataset contains four variables: age, sex, bmi, and disease. The goal is to calculate the mean (or standard deviation) or frequency (percentage) of each variable divided by sex. The data types of these variables are continuous (age and bmi), binary (disease), and categorical (sex). We will use R’s data.table package to perform this analysis.

Load Required Libraries

To start, we need to load the required libraries in our R environment:

library(data.table)

Prepare the Data

We create a sample dataset using the structure() function and then convert it into a data frame using the data.frame() function. We also use the setDT() function from the data.table package to make it a data table.

# Create a sample dataset
dt <- structure(
  list(age = c(23, 25, 60, 12), 
       sex = c(0, 1, 0, 1),
       bmi = c(25, 30, 23, 24),
       disease = c(0, 1, 0, 1)),
  class = c("tbl_df", "tbl", "data.frame"),
  row.names = c(NA, -4L))

# Convert to data frame
dt <- as.data.frame(dt)

# Make it a data table
setDT(dt)

Prepare Data for Analysis

To prepare the data for analysis, we create a new column sex by converting the existing sex column into factors with labels. We also convert the disease column to logical values (0 or 1).

# Create a new column 'sex'
dt[, sex := factor(sex, labels = c("Women", "Men"))]

# Convert disease to logical values
dt[, disease := as.logical(disease)]

Melt Data

Next, we use the melt() function from the data.table package to transform our data into a long format. We also apply a function using lapply() and switch() to calculate either the mean (± SD) or frequency (%) of each variable based on its class.

# Melt data
dt_melt <- melt(dt[, lapply(.SD, function(x) {
  switch(
    class(x),
    "numeric" = paste0("%.0f ± %.0f", round(mean(x), 1), round(sd(x), 1)),
    "logical" = paste0("%.0f (%.0f %%)", sum(x), round(100 * sum(x) / nrow(dt), 2))
  )
}), id.vars = "sex"), variable ~ sex)

Cast Data

Finally, we use the dcast() function to cast our data into a wide format and create the desired table.

# Cast data
dt_table <- dcast(dt_melt, variable ~ sex, value.var = c("age", "bmi", "disease"), function(x) x)

Display Results

The resulting dt_table data frame will contain the means (± SD) or frequencies (%) of each variable divided by sex. We can display this table using the print() function.

# Print results
print(dt_table)

This code will generate a table with the desired output:

Conclusion

In this article, we have learned how to create a table that displays the means and frequencies of each variable divided by sex using R’s data.table package. We used various functions from this package, such as melt(), dcast(), and lapply() to manipulate our data into the desired format.

References

• data.table package in R: https://cran.r-project.org/package=data.table
• Melt() function in data.table package: https://rdatatables.com/rowid/156/
• Dcast() function in data.table package: https://rdatatables.com/rowid/165/
• Switch() function in R: https://stat.ethz.ch/R-manual/R-release/library/base/html/s-04.html

Last modified on 2023-06-04