Descriptive Stats Plots

ggplot2 is the gold standard in data visualization in data work. It's one of the main reason that people use R over other programming languages.

Very simple syntax and allows you to add elements very easily.

You can use ggplot2 to create any type of plot you can think of.

I've included a lot of links at the end of these slides to explore the possibilities of ggplot2 further. Strongly recommend you use them or at least save them somewhere.

The Magic of ggplot2

Using ggplot2 to create plots is great because the structure it sets up makes plot creation intuitive.

ggplot(data = <DATA>) +
  <GEOM_FUNCTION>(
     mapping = aes(<MAPPINGS>),
     stat = <STAT>,
     position = <POSITION>
  ) +
  <SCALE_FUNTION> +
  <FACET_FUNCTION> +
  <THEME_FUNCTION>

Scatter Plot — Step-by-Step

head(mtcars)

##                    mpg cyl disp  hp drat    wt  qsec vs am gear carb
## Mazda RX4         21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
## Mazda RX4 Wag     21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
## Datsun 710        22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
## Hornet 4 Drive    21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
## Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2
## Valiant           18.1   6  225 105 2.76 3.460 20.22  1  0    3    1

ggplot(mtcars)

ggplot(mtcars) +
  geom_point(
    aes(x = mpg, y = wt)
  )

Scatter Plot — Make It Better

ggplot(mtcars) +
  geom_point(
    aes(
      x = mpg, y = wt,
      color = factor(cyl)
    ),
    size = 6
  ) +
  xlab("Miles/Gallon") +
  ylab("Weight") +
  scale_color_discrete(
    name = "# of Cylinders"
  ) +
  theme_minimal(base_size = 24) +
  theme(
    legend.position = "bottom"
  )

Bar Plot — Step-by-Step

mtcars_summary

## # A tibble: 3 × 2
##     cyl   mpg
##   <dbl> <dbl>
## 1     4  26.7
## 2     6  19.7
## 3     8  15.1

ggplot(mtcars_summary)

ggplot(mtcars_summary) +
  geom_col(
    aes(
      x = cyl,
      y = mpg
    )
  )

ggplot(mtcars_summary) +
  geom_col(
    aes(
      x = factor(cyl),
      y = mpg
    )
  )

Bar Plot — Make It Better

ggplot(mtcars_summary) +
  geom_col(
    aes(
      x    = factor(cyl),
      y    = mpg,
      fill = factor(cyl)
    )
  ) +
  xlab("# of Cylinders") +
  ylab("Miles/Gallon") +
  scale_y_continuous(
      limits = c(0, 30)
  ) +
  theme_minimal(base_size = 24) +
  theme(
    legend.position = "none"
  )

Descriptive Statistics Tables

Thankfully, not every RA position requires academic-standard tables or use of LateX.

It is still useful, however, to be able to communicate descriptive statistics about data.

There are countless R packages to help do this. Today, we're looking at the gt package. It's simple to use and it's very easy to create good-looking tables using it.

gt exports into .png, .pdf, or .html. You can add interactive elements, plots within columns.

Descriptive Statistics Table — Step-by-Step

We will mainly use the example in the script for this. To summarize, the steps are:

• Create a dataset you want to export

• Run the dataset through the gt() function to create a gt object

• Customize the table using functions from the gt package (see online for further things you can do). Examples of what you can do include:

  • Modify column names — cols_label()
  • Modify borders — tab_style(), cell_borders()
  • Add colors conditional on cell value — data_color()
  • Add title/subtitle — tab_header()

• Export the table using gtsave()

Regression Tables

Regression tables are very common in economic/policy analysis.

They're very simple to create using R and a software called LateX (pronounced latek).

Unless you're getting into academic research, you don't need to know how to properly use LateX. Just enough to:

• Export the LateX script from R
• Copy/paste it into a LateX-reading software, e.g. Overleaf
• Export the pdf or png to share

Regression Table — Step by Step

# Simplest regression format in R
reg_example <- lm(
    outcome_variable ~ independent_variable + control_variables,
    data = dataset
)
# Observe results
summary(reg_example)

reg_example_ht <- huxtable::huxreg(reg_example)

reg_example_sg <- stargazer::stargazer(reg_example)
# Many options to make prettier

Regression Table — Step by Step

  huxtable::quick_latex(
      reg_example_ht,
      file = "filepath/filepath/filepath/reg_example_ht.tex"
  )
  huxtable::quick_pdf
      reg_example_ht,
      file = "filepath/filepath/filepath/reg_example_ht.pdf"
  )
  huxtable::quick_html(
      reg_example_ht,
      file = "filepath/filepath/filepath/reg_example_ht.html"
  )

# You can export a LateX script using the 'writeLines' function
writeLines(
    reg_example_sg,
    "filepath/filepath/filepath/reg_example_sg.tex"
)

Background

"The survey, which started in 1981, seeks to use the most rigorous, high-quality research designs in each country. The WVS consists of nationally representative surveys conducted in almost 100 countries which contain almost 90 percent of the world’s population, using a common questionnaire. [...] WVS seeks to help scientists and policy makers understand changes in the beliefs, values and motivations of people throughout the world."

Survey Contents

Today's practical component

1. Download the required data for this session from this Dropbox folder

2. Successfully run the code in the session_2.R script

3. Attempt the challenges at the bottom of the script!