Practice 8

PUBH 523/623

Overview

This practice shifts from describing the HRS dataset to visualizing it. You will build a ggplot2 plot from its basic grammar components, try out different geometric objects (geom_*()), control aesthetics like color and transparency, and then polish plots with labels, facets, and themes so they’re ready to share. Along the way you’ll get a little more practice with select() and the pipe (|>) from previous weeks, but the focus this week is on ggplot2.

Topics covered (Lessons 31-33):

• Data visualization: Intro to ggplot2
• Data visualization: Basic plotting
• Data visualization: Design choices

Directions

Download this practice .qmd from the course GitHub repository, rename it, and save it in your course folder.

• Download practice_08.qmd from GitHub.
• Rename the file to Lastname_Firstinitial_Practice_08.qmd (or lastname_firstinitial_practice_08.qmd), replacing with your actual last name and first initial.
• Save it inside your practice folder. You may create a practice_08 subfolder if you prefer.

TipHow to use this file

The boxes with the yellow stripe explain what to do. Keep these in your submitted file. Do all your work below and outside of the yellow-striped boxes. You will need to create code chunks within this document to run your R code.

Please delete the following sections before submitting:

• Overview
• Directions
• Tip boxes (green stripe)
• Caution boxes / Needed Steps (orange/red stripe)
• Submission checklist
• Note on AI usage

ImportantNeeded setup

You should already have hrs_data.rds from Practice 4 (link on the practice page). Place it in your data folder if you haven’t already. You can check out the codebook here.

Load the tidyverse and here packages. ggplot2 is part of the tidyverse, so you don’t need any new packages this week!

Questions

Question 1: Grammar of ggplot2

In Lesson 31, we saw that every ggplot2 plot is built from the same basic grammar: data, a mapping, and a layer.

Part A: The three required pieces

WarningTask

Fill in the table below with what each of the data, mapping, and layer contribute to a plot, and which function we use to supply each one.

Component	Contribution	Function supplied
Data
Mapping
Layer

Part B: Start with just the data

WarningTask

Call ggplot() with just hrs_data as the data (don’t add a mapping or a layer yet). Assign the result to hrs_01_plot_data and display it. What do you see in the plot area?

Write your answer here.

TipTip

To display a plot (or any R object), you don’t need print(). Just type the object’s name by itself on its own line in a code chunk and run it.

Part C: Add a mapping

WarningTask

Now rebuild the plot, this time adding a mapping: aes(x = height). Assign the result to hrs_02_plot_mapped and display it. Compare it to hrs_01_plot_data. What showed up this time, and what is still missing?

Write your answer here.

Part D: Add a layer

WarningTask

Finally, add a layer to hrs_02_plot_mapped by adding geom_histogram(). Assign the complete plot to hrs_03_plot_hist and display it.

TipTip

You don’t have to rebuild a plot from scratch every time. You can start from an existing ggplot object (like hrs_02_plot_mapped) and use + to add more layers to it.

Part E: Same plot, different code style

WarningTask

Recreate hrs_03_plot_hist again, but this time move aes(x = height) out of ggplot() and into geom_histogram() instead. Assign the result to hrs_04_plot_aes_in_geom. Confirm it looks identical to hrs_03_plot_hist.

Question 2: Basic plotting and aesthetics

In Lesson 32, we covered different geom_*() functions and how to set or map aesthetics like color, size, and transparency.

Part A: A density plot

WarningTask

Using hrs_data, create a plot of income and add geom_density() to show its distribution. Assign the plot to hrs_05_plot_density and display the plot.

Part B: A boxplot of the same variable

WarningTask

Now make the same plot of income, but use geom_boxplot() instead of geom_density(). Assign the plot to hrs_06_plot_boxplot.

Part C: A scatterplot of two continuous variables

WarningTask

Create a plot of ed (years of education, x-axis) vs. income (y-axis) from hrs_data using geom_point(). Assign it to hrs_07_plot_scatter and display it.

Part D: A line plot of the same two variables

WarningTask

Now make the same plot of ed vs. income, but use geom_smooth() instead of geom_point() to show the overall trend as a line. Assign the plot to hrs_08_plot_smooth and display it.

Part E: A boxplot of a categorical and a continuous variable

WarningTask

Create a plot of act_vig (vigorous physical activity frequency, x-axis) vs. income (y-axis) from hrs_data using geom_boxplot(). Assign it to hrs_09_plot_box.

Part F: Layer jitter on top

WarningTask

Starting from the same mapping, add a geom_jitter() layer on top of the boxplot layer so you can see the individual data points as well. Set alpha = 0.2 inside geom_jitter() so the points don’t overwhelm the boxplot. Assign the result to hrs_10_plot_box_jitter.

TipTip

Since both geom_boxplot() and geom_jitter() use the same x and y mapping, you can put aes() inside ggplot() once instead of repeating it in each geom_*().

Part G: Setting an aesthetic

WarningTask

Create a plot of cond_count (x-axis) vs. act_vig (y-axis) using geom_jitter(), and set the color of the points to "darkblue" (this goes outside of aes()). Also set alpha lower so the individual dots show up better where they overlap. Assign the plot to hrs_11_plot_color_set.

Part H: Mapping an aesthetic

WarningTask

Now recreate the same plot, but this time map color to the smoke_ever variable inside aes() instead of setting a fixed color. Also set alpha lower so the dots show up better. Assign the plot to hrs_12_plot_color_map.

In 1-2 sentences, explain the difference between setting an aesthetic outside aes() and mapping it inside aes().

Write your answer here.

Question 3: Design choices for labels, facets, and themes

In Lesson 33, we covered how to polish a plot using labs(), facet_wrap()/facet_grid(), theme(), and how to save a finished plot with ggsave().

Part A: Labels

WarningTask

Starting from hrs_10_plot_box_jitter (Question 2 Part F), add a labs() layer with an x-axis label, a y-axis label, and a title of your choice. Assign the result to hrs_13_plot_labs and display it.

Part B: Facets

WarningTask

Using hrs_data, create a histogram of age_yr, faceted by sex with facet_wrap(). Assign the result to hrs_14_plot_facet.

Looking at the faceted plot, does the age distribution appear to differ between males and females?

Write your answer here.

TipTip

If you want to facet by two variables instead of one (e.g., sex and diab), use facet_grid(var1 ~ var2) instead of facet_wrap().

Part C: Color

WarningTask

Recreate the same distribution as hrs_14_plot_facet (a histogram of age_yr), but this time show the comparison by mapping fill to sex instead of faceting. Assign the result to hrs_15_plot_fill and display it.

Which approach, facet or fill, feels more appropriate for comparing the age distributions of males and females here? Why?

Write your answer here.

Part D: Themes

WarningTask

Take hrs_13_plot_labs from Part A and add a complete theme of your choice (e.g., theme_minimal(), theme_bw(), or theme_classic()). Then, use theme() to additionally increase the size of the plot title to 16. Assign the final plot to hrs_16_plot_final and display it.

TipTip

Order matters here! Add the complete theme (like theme_minimal()) before your theme() call that tweaks individual elements, not after.

Part E: Saving your plot

WarningTask

Use ggsave() to save hrs_16_plot_final as a .png file into your images folder (use here() to build the file path). Set the width to 6 inches, the height to 4 inches, and the dpi to 200.

Part F: Insert your saved plot

WarningTask

In a text section of your document (not a code chunk), insert the image you just saved in Part E using Markdown image syntax.

TipTip

Markdown image paths are relative to where your .qmd file is saved, not resolved through here(). If your file lives in practice/, and your images folder is one level up from that, your path would look like ../images/your_file_name.png. Adjust the path to match where you actually saved your file.

Submission Checklist

If having a checklist helps you stay organized, check off each item below as you complete it. You do not need to submit this checklist.

• Three grammar components (data, mapping, layer) filled into the table (Q1 Part A)
• hrs_01_plot_data created and displayed, with question answered (Q1 Part B)
• hrs_02_plot_mapped created and displayed, with question answered (Q1 Part C)
• hrs_03_plot_hist created and displayed (Q1 Part D)
• hrs_04_plot_aes_in_geom recreated with aes() moved into geom_histogram() (Q1 Part E)
• hrs_05_plot_density created for income (Q2 Part A)
• hrs_06_plot_boxplot created for income (Q2 Part B)
• hrs_07_plot_scatter created for ed vs. income (Q2 Part C)
• hrs_08_plot_smooth created for ed vs. income (Q2 Part D)
• hrs_09_plot_box created for act_vig vs. income (Q2 Part E)
• hrs_10_plot_box_jitter created by layering geom_jitter() (Q2 Part F)
• hrs_11_plot_color_set created (Q2 Part G)
• hrs_12_plot_color_map created, with question answered (Q2 Part H)
• hrs_13_plot_labs created with labs() (Q3 Part A)
• hrs_14_plot_facet created with facet_wrap(), with question answered (Q3 Part B)
• hrs_15_plot_fill created with fill, with question answered (Q3 Part C)
• hrs_16_plot_final created with a theme and customized title size (Q3 Part D)
• Final plot saved with ggsave() (Q3 Part E)
• Saved plot inserted into the document with Markdown image syntax (Q3 Part F)
• Document renders to HTML with no errors
• Files named correctly: Lastname_Firstinitial_Practice_08.qmd and Lastname_Firstinitial_Practice_08.html (or lowercase versions)
• Both .qmd and .html submitted to Brightspace

Note on AI usage

I used GenAI (Claude) to help me draft this practice assignment. It helped me brainstorm ideas for the assignment, and I directed it to help you complete the needed tasks that I showed in the lessons.