EDA — Variation

PSY 410: Data Science for Psychology

Dr. Sara Weston

2026-04-29

What is EDA?

Know your data before you test it

Before you run a single statistical test, you should know your data well enough to predict what the results will look like.

That’s what EDA gives you — no surprises.

It’s also how you catch problems early: rows that didn’t load, codes that weren’t recoded, “999” sneaking in as a real age.

Open by asking students: “How many of you have ever run an analysis and been confused by the results?” This is the problem EDA solves. Spend ~2 minutes here. Frame EDA two ways: (1) it tells you what your data look like before you analyze them, and (2) it’s the last line of defense against data that loaded wrong, wasn’t cleaned, or has miscoded values. A surprising number of “weird results” turn out to be a column that read in as character, or a missing-value sentinel that wasn’t converted to NA. EDA is how you catch that.

Exploratory vs. confirmatory

	Exploratory (EDA)	Confirmatory
Goal	Discover patterns	Test hypotheses
Attitude	Curiosity	Rigor
Questions	Open-ended	Pre-specified
Output	Visualizations, hunches	p-values, conclusions

The two roles get mixed up if you do them on the same data. Preregistration keeps them honest: you write your confirmatory hypotheses down before you peek.

Students sometimes think EDA is optional or that it’s what you do when you don’t have a hypothesis. Emphasize that even in confirmatory research, EDA is step one — it tells you whether your data look the way you expect. The risk is that exploration generates a hypothesis and then you “confirm” it on the same data — that’s HARKing / p-hacking. Preregistration (registering your hypotheses on OSF or AsPredicted before looking at the data) is the standard tool researchers use to keep exploration and confirmation separate. Connect back to the replication-crisis opening from Session 1.

A cleaner pattern: split your data

If you’re worried about exploring and testing on the same dataset, use multiple datasets:

• Dataset 1 → EDA. Look around. Generate ideas.
• Dataset 2 → Confirm ideas from Set 1. Then EDA on Set 2 → new ideas.
• Dataset 3 → Confirm ideas from Sets 1 & 2. Then EDA on Set 3 → new ideas.
• … and so on.

Each new dataset gets one shot at confirmation, then becomes fair game for exploration.

This is the iterative cycle that mature research programs use — sometimes called “replication chains” or “rolling confirmation.” You can also do this within one dataset by holding out a portion (a “lockbox” or train/test split). The point: EDA generates hypotheses, and confirmation has to happen on data that didn’t generate them. Spend ~1 minute here. This isn’t something they’ll do in this class, but it’s the right mental model going forward.

Good EDA means looking before you test

“EDA is an attitude, not a technique.” — John Tukey

• Ask questions
• Answer them by visualizing data
• Use what you learn to ask new questions
• Repeat

There is no single “right” way to do EDA. The goal is understanding.

The Tukey quote is worth pausing on. Students who are used to following step-by-step procedures may feel anxious that there’s no single recipe. Reassure them: EDA is more like being a detective than following a protocol. The “attitude” framing gives them permission to explore.

What we’re doing today

Exploring variation — what does a single variable look like?

• Distribution shape
• Center and spread
• Outliers and unusual values
• Missing data

Tomorrow: covariation — how do variables relate to each other?

Quick roadmap slide — spend ~30 seconds. This orients students on the two-session arc: today is single variables, next class is relationships between variables.

Our dataset: Big Five Personality

dim(bfi)

[1] 2800   28

names(bfi)

 [1] "A1"        "A2"        "A3"        "A4"        "A5"        "C1"       
 [7] "C2"        "C3"        "C4"        "C5"        "E1"        "E2"       
[13] "E3"        "E4"        "E5"        "N1"        "N2"        "N3"       
[19] "N4"        "N5"        "O1"        "O2"        "O3"        "O4"       
[25] "O5"        "gender"    "education" "age"      

25 items measuring five personality factors (Agreeableness, Conscientiousness, Extraversion, Neuroticism, Openness) + demographics.

Point out the dimensions (~2800 rows, 28 columns) and walk through the names. Five blocks of five items (A1–A5, C1–C5, E1–E5, N1–N5, O1–O5) plus three demographic columns. The next slide covers what each item code means. If students have taken personality psych, ask what the Big Five are.

What’s in here

Variable	Description
A1–A5	Agreeableness items (1–6 scale)
C1–C5	Conscientiousness items (1–6 scale)
E1–E5	Extraversion items (1–6 scale)
N1–N5	Neuroticism items (1–6 scale)
O1–O5	Openness items (1–6 scale)
gender	1 = male, 2 = female (binary coding)
education	1–5 (HS incomplete through graduate)
age	Age in years

Exploring distributions

Start simple: summary statistics

bfi |>
  select(age, gender, education) |>
  summary()

      age            gender        education   
 Min.   : 3.00   Min.   :1.000   Min.   :1.00  
 1st Qu.:20.00   1st Qu.:1.000   1st Qu.:3.00  
 Median :26.00   Median :2.000   Median :3.00  
 Mean   :28.78   Mean   :1.672   Mean   :3.19  
 3rd Qu.:35.00   3rd Qu.:2.000   3rd Qu.:4.00  
 Max.   :86.00   Max.   :2.000   Max.   :5.00  
                                 NA's   :223   

But summary stats can hide a lot. Always visualize.

Run this live and walk through the output. Point out the NA counts in the summary — students will see missing data here for the first time. Ask: “What does this summary tell you about education? Is it really a number?” This sets up the idea that summary stats on categorical-coded-as-numeric variables are misleading. Spend ~2 minutes.

Histograms: the workhorse

bfi |>
  ggplot(aes(x = age)) +
  geom_histogram(binwidth = 5, fill = "#2c7fb8", color = "white") +
  labs(x = "Age (years)", y = "Count") +
  theme_minimal(base_size = 14) +
  theme(panel.grid = element_blank(),
        axis.line = element_line(color = "gray70"))

This is the first histogram of the session. Walk through the code line by line: the pipe into ggplot, the aes() mapping, and then geom_histogram(). Emphasize that binwidth is a choice, not a default — ggplot will warn them if they don’t set it. Ask students to describe the shape: right-skewed, most people are young. Spend ~3 minutes here since this is a core geom. Note that we’re skipping titles for these EDA plots — titles matter for the final report, not for the explore-loop.

Histograms: the workhorse

Choosing binwidth

The binwidth matters a lot:

There’s no “right” answer — try a few and pick the one that shows the shape clearly.

Spend ~2 minutes comparing the three panels. Point to specific differences: binwidth=1 shows noisy spikes that are just sampling variability, binwidth=20 hides the right skew entirely. A common student question: “Which binwidth should I use on the assignment?” Answer: try a few, pick the one that shows the overall shape without too much noise. There is no single correct answer.

Density plots: smooth alternative

bfi |>
  ggplot(aes(x = age)) +
  geom_density(fill = "#2c7fb8", alpha = 0.6, color = "#2c7fb8") +
  labs(x = "Age (years)", y = "Density") +
  theme_minimal(base_size = 14) +
  theme(panel.grid = element_blank(),
        axis.line = element_line(color = "gray70"))

Briefly explain that density plots are like a smoothed histogram — the y-axis is density, not count, so the area under the curve sums to 1. Students often ask what the y-axis means; it’s fine to say “think of it as relative likelihood” without going deep into probability density. The main advantage: no binwidth decision. The main disadvantage: harder to read exact counts.

Density plots: smooth alternative

Exploring survey items

# All Extraversion items
item_labels <- c(
  E1 = "E1\nDon't talk a lot. (R)",
  E2 = "E2\nFind it difficult to\napproach others. (R)",
  E3 = "E3\nKnow how to\ncaptivate people.",
  E4 = "E4\nMake friends easily.",
  E5 = "E5\nTake charge."
)

bfi |>
  select(E1:E5) |>
  pivot_longer(everything(), names_to = "item", values_to = "response") |>
  ggplot(aes(x = response)) +
  geom_bar(fill = "#2c7fb8") +
  facet_wrap(~ item, nrow = 1, labeller = as_labeller(item_labels)) +
  scale_x_continuous(breaks = 1:6) +
  labs(
    title = "Distribution of responses to Extraversion items",
    x = NULL,
    y = NULL,
    caption = "Scale: 1 = Very inaccurate, 6 = Very accurate.   (R) = reverse-scored."
  ) +
  theme_minimal(base_size = 12) +
  theme(panel.grid = element_blank(),
        axis.line.x = element_line(color = "gray70"),
        axis.line.y = element_blank(),
        axis.text.y = element_blank(),
        axis.ticks.y = element_blank(),
        strip.text = element_text(lineheight = 1.1),
        plot.caption = element_text(hjust = 0, size = 10))

This slide introduces pivot_longer in a practical context — students saw it in the tidying session but may need a reminder. The key insight: E1 and E2 are reverse-scored (“(R)” in the caption), which is why they skew opposite to E3, E4, E5. Use this to introduce the idea that survey items don’t all point the same direction — to compute a meaningful Extraversion score, you’d reverse-score E1 and E2 first. Students saw this idea briefly in the tidying session; this is the natural place to reinforce it. Don’t dwell on pivot_longer mechanics; the focus is the visualization.

Exploring survey items

A quick aside: factor()

Education is stored as numbers (1–5), but the numbers are codes, not measurements. factor() turns them into ordered categories with readable labels:

factor(education,
       levels = 1:5,
       labels = c("Some HS", "HS grad", "Some college",
                  "College grad", "Graduate"))

• levels = the values currently in the data (in the order you want them)
• labels = what to show instead

We’ll come back to factors in detail in a later session — for now, just know this is how we attach labels to numeric codes.

Spend ~1 minute. Students don’t need a deep understanding of factors yet — just enough to read the next few slides without confusion. The full treatment is in Session 13 (Strings, Factors & Text). Reassure them: factors look like character vectors but remember an order, which is exactly what you want for things like education levels or Likert scales.

Categorical variables

bfi |>
  filter(!is.na(education)) |>
  mutate(education = factor(education,
    levels = 1:5,
    labels = c("Some HS", "HS grad", "Some college", "College grad", "Graduate"))) |>
  ggplot(aes(x = education)) +
  geom_bar(fill = "#2c7fb8") +
  labs(x = "Education", y = "Count") +
  theme_minimal(base_size = 14) +
  theme(panel.grid = element_blank(),
        axis.line = element_line(color = "gray70"))

Categorical variables

Counts and proportions

# Counts
bfi |>
  filter(!is.na(education)) |>
  mutate(education = factor(education,
    levels = 1:5,
    labels = c("Some HS", "HS grad", "Some college", "College grad", "Graduate"))) |>
  count(education)

# A tibble: 5 × 2
  education        n
  <fct>        <int>
1 Some HS        224
2 HS grad        292
3 Some college  1249
4 College grad   394
5 Graduate       418

Counts and proportions

# Proportions
bfi |>
  filter(!is.na(education)) |>
  mutate(education = factor(education,
    levels = 1:5,
    labels = c("Some HS", "HS grad", "Some college", "College grad", "Graduate"))) |>
  count(education) |>
  mutate(proportion = n / sum(n))

# A tibble: 5 × 3
  education        n proportion
  <fct>        <int>      <dbl>
1 Some HS        224     0.0869
2 HS grad        292     0.113 
3 Some college  1249     0.485 
4 College grad   394     0.153 
5 Graduate       418     0.162 

Don’t round inside the data frame

Keep the full precision in your data. Round only when you’re displaying it:

bfi |>
  count(education) |>
  mutate(proportion = n / sum(n)) |>
  knitr::kable(digits = 2)

If you round in the data frame, you’ve thrown away precision you can’t get back. If you round at display, the underlying data is still exact.

Quick aside — ~30 seconds. The point is the habit: data frames hold data, display functions handle formatting. Students will encounter this again with reports in Session 16; foreshadow that they’ll use kable() a lot in Quarto.

Outliers

What are outliers?

Values that are unusual compared to the rest of the data. They might be:

• Real — genuinely extreme values (a 95-year-old in a college study)
• Errors — data entry mistakes (age = 999)
• Interesting — worth investigating

Never delete an outlier without understanding it.

This is one of the most important slides in the deck. Spend ~3 minutes here. Students in psych methods courses are often taught to “remove outliers” as a default step. Push back on that: outliers are data, and deleting them is a decision that changes your results. The real question is always “is this value plausible?” A 95-year-old in a college study is real but might not represent your target population. An age of 999 is clearly an error. These are different situations requiring different responses.

Spotting outliers visually

bfi |>
  ggplot(aes(x = age)) +
  geom_histogram(binwidth = 5, fill = "#2c7fb8", color = "white") +
  labs(x = "Age (years)", y = "Count") +
  theme_minimal(base_size = 14) +
  theme(panel.grid = element_blank(),
        axis.line = element_line(color = "gray70"))

Spotting outliers visually

Spotting outliers with boxplots

bfi |>
  ggplot(aes(x = age)) +
  geom_boxplot(fill = "#2c7fb8", alpha = 0.7) +
  labs(x = "Age (years)") +
  theme_minimal(base_size = 14) +
  theme(panel.grid = element_blank(),
        axis.line.x = element_line(color = "gray70"),
        axis.text.y = element_blank(),
        axis.ticks.y = element_blank())

Points beyond the whiskers are flagged as outliers by the 1.5×IQR rule.

Briefly explain the 1.5xIQR rule: any point more than 1.5 times the interquartile range above Q3 or below Q1 gets plotted individually. Students don’t need to memorize this, just know that boxplots have a built-in outlier detection rule. Transition: “But seeing a dot on a plot isn’t enough — let’s look at those outliers in the actual data.”

Spotting outliers with boxplots

Investigating outliers programmatically

# Find unusually old or young participants
bfi |>
  filter(age > 60) |>
  select(age, gender, education)

# A tibble: 22 × 3
     age gender education
   <int>  <int>     <int>
 1    68      1         5
 2    64      2         5
 3    74      1         5
 4    63      2         3
 5    62      1         2
 6    86      2         2
 7    61      1         2
 8    67      1         5
 9    67      1         5
10    63      1         5
# ℹ 12 more rows

What to do with outliers

Outlier type	What to do
Likely error (age = 999)	Fix or set to NA
Real but extreme	Note it, keep it, mention in write-up
Suspicious	Investigate further
Doesn’t affect conclusions	Keep it, move on

Document your decisions. Future you will want to know.

Emphasize the documentation point. In psychology research, you need to justify every data cleaning decision in your methods section. “I removed 3 participants with ages over 80 because the study targeted 18-65 year olds” is fine. “I removed outliers” with no explanation is not. This connects to the reproducibility theme from Session 1.

Let’s explore YOUR data

Our class survey

Remember that survey you filled out Week 1? Let’s do some EDA on it.

class_survey <- read_csv(
  "https://raw.githubusercontent.com/sjweston/datasci410/refs/heads/main/data/class_survey.csv"
)

glimpse(class_survey)

Rows: 34
Columns: 15
$ response_id       <chr> "R_7Fkq5bRdEYWENih", "R_7mni7E59hbZtnha", "R_7BKhLj1…
$ major             <chr> "Psychology", "Neuroscience", "Psychology", "Psychol…
$ year              <chr> "Junior", "Senior", "Junior", "Junior", "Senior", "S…
$ chronotype        <chr> "Evening person", "Morning person", "Morning person"…
$ sleep_hrs         <dbl> 8.0, 6.0, 9.0, 9.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.…
$ caffeine_per_day  <dbl> 2.00, 1.00, 2.00, 1.00, 2.00, 1.00, 0.15, 1.50, 1.30…
$ social_media_hrs  <dbl> 7.00, 2.00, 1.00, 3.00, 2.00, 8.00, 0.33, 1.00, 1.00…
$ tabs_open         <dbl> 363, 10, 2, 11, 6, 26, 7, 27, 12, 9, 6, 6, 246, 22, …
$ stress            <dbl> 4, NA, 3, 3, 2, 6, 6, 6, 2, 5, 3, 6, 7, 6, 7, 7, 7, …
$ coding_excited    <dbl> 7, 6, 8, 6, NA, 7, 7, NA, 5, 5, 6, 8, 8, 5, 5, 6, 7,…
$ coding_anxious    <dbl> 8, NA, 8, 8, 5, 7, 6, 5, 4, 5, 8, 7, 3, NA, 8, 9, 4,…
$ personality_neur  <dbl> 9, NA, 9, 7, NA, NA, NA, 7, 8, NA, NA, 9, NA, NA, NA…
$ personality_extra <dbl> 8, NA, 2, 6, 5, 4, 8, 7, 9, 7, 6, 9, 6, 5, 7, 5, 7, …
$ personality_consc <dbl> 8, 3, NA, 7, NA, 7, NA, 6, 8, 8, 8, 7, 4, 5, 5, 9, 7…
$ data_words        <chr> "frustrating and overwhelming", "novel", "novice", "…

Transition: “We’ve been using the BFI dataset to practice EDA. Now let’s see what our own class data looks like.” Walk students through the URL load — they can paste this directly into their console; no download needed because read_csv() accepts URLs. Students perk up when it’s their data. Walk through the glimpse output briefly — they should recognize the variable names from the survey they took.

How many tabs do you have open?

ggplot(class_survey, aes(x = tabs_open)) +
  geom_histogram(binwidth = 5, fill = "#2c7fb8", color = "white") +
  labs(x = "Number of tabs", y = "Count") +
  theme_minimal(base_size = 14) +
  theme(panel.grid = element_blank(),
        axis.line = element_line(color = "gray70"))

This variable almost always produces a beautiful right skew with outliers. Ask: “Who’s the person with 80+ tabs?” Let students laugh. Then pivot: “Is that an outlier? Is it an error? Or is it just someone who doesn’t close tabs?” This reinforces the earlier lesson — outliers are information, not mistakes.

How many tabs do you have open?

How does our class sleep?

ggplot(class_survey, aes(x = sleep_hrs)) +
  geom_histogram(binwidth = 1, fill = "#2c7fb8", color = "white") +
  labs(x = "Average hours of sleep per night", y = "Count") +
  theme_minimal(base_size = 14) +
  theme(panel.grid = element_blank(),
        axis.line = element_line(color = "gray70"))

Compare this to the tabs distribution: “Notice how different the shape is. Sleep is roughly symmetric — most people cluster around 7 hours. Tabs was heavily skewed. That’s EDA in action — you’re noticing things.”

How does our class sleep?

Morning people or night owls?

ggplot(class_survey, aes(x = chronotype)) +
  geom_bar(fill = "#2c7fb8") +
  labs(x = "Chronotype", y = "Count") +
  theme_minimal(base_size = 14) +
  theme(panel.grid = element_blank(),
        axis.line = element_line(color = "gray70"))

A categorical variable from our own data. Ask: “Does this match what you’d expect from a class of college students?” Most college samples skew evening. Transition to the pair coding break.

Morning people or night owls?

Pair coding break

Your turn: 10 minutes

Using the class_survey data, look at the distribution of social_media_hrs (self-reported hours per day on social media):

1. Plot the distribution — what shape is it?
2. Check for outliers. Are any values suspicious?
3. What does this tell you about our class?

Tip

Try both a histogram and a boxplot. They show different things. Use summary(class_survey$social_media_hrs) first to get oriented.

Circulate during this exercise. Common issues: students forget to load class_survey, or they pick a binwidth that’s too small/large. The distribution will likely be right-skewed with a few extreme values — this is a great moment to ask “is the person who said 12 hours/day an outlier, an error, or just honest?” If pairs finish early, suggest they compare to caffeine_per_day or tabs_open.

Solution: Social media hours

class_survey |>
  ggplot(aes(x = social_media_hrs)) +
  geom_histogram(
    binwidth = 2,
    fill = "navy",
    color = "white") +
  scale_x_continuous(
    breaks = c(0, 2, 4, 6, 8)
  ) +
  theme_minimal()

class_survey |>
  ggplot(aes(x = social_media_hrs)) +
  geom_boxplot(
    fill = "lightgrey",
    color = "navy"
  ) +
  theme_bw()

Solution: histogram

Solution: boxplot

Missing data — a first look

Missing data are everywhere

# How much missing data do we have?
bfi |>
  summarize(across(everything(), ~ sum(is.na(.)))) |>
  pivot_longer(everything(), names_to = "variable", values_to = "n_missing") |>
  arrange(desc(n_missing))

# A tibble: 28 × 2
   variable  n_missing
   <chr>         <int>
 1 education       223
 2 N4               36
 3 N5               29
 4 O3               28
 5 A2               27
 6 A3               26
 7 C4               26
 8 E3               25
 9 C2               24
10 E1               23
# ℹ 18 more rows

This code is more advanced than what students have written themselves — across() and the anonymous function syntax may be new. Focus on the output, not the code mechanics. The takeaway: education has the most missing data (~200+ values). Ask: “Why might education be more likely to be missing than personality items?” (People skip demographic questions they find irrelevant or sensitive.)

Visualizing missingness

bfi |>
  summarize(across(everything(), ~ mean(is.na(.)))) |>
  pivot_longer(everything(), names_to = "variable", values_to = "pct_missing") |>
  mutate(pct_missing = pct_missing * 100) |>
  filter(pct_missing > 0) |>
  arrange(desc(pct_missing)) |>
  ggplot(aes(x = reorder(variable, pct_missing), y = pct_missing)) +
  geom_col(fill = "#2c7fb8") +
  coord_flip() +
  labs(x = "Variable", y = "% Missing") +
  theme_minimal(base_size = 14) +
  theme(panel.grid = element_blank(),
        axis.line = element_line(color = "gray70"))

Visualizing missingness

Why it matters for EDA

Missing data can bias your exploration:

• If missingness is related to the variables you’re studying, your distributions are wrong
• If certain groups are more likely to have missing data, you might miss important patterns

We’ll cover this in depth in Session 14. For now: always check for missing data before exploring.

Keep this brief — ~1 minute. The point is to plant a seed, not to teach missing data handling. Students just need to know that missing data exists and can bias their exploration. The full treatment comes in Session 14 (Missing Data).

The EDA workflow

A systematic approach

1. Look at the structure — glimpse(), summary()
2. Check for missing data — how much? Which variables?
3. Explore each variable — histograms, bar charts, summaries
4. Look for outliers — boxplots, programmatic checks
5. Ask questions — what surprised you? What do you want to know more about?
6. Repeat — EDA is iterative

This is the “cheat sheet” slide — the workflow students should follow when they sit down with a new dataset. Emphasize that step 6 is the most important: EDA is a loop, not a checklist. Each answer generates new questions. This workflow will be the backbone of Assignment 5. Spend ~2 minutes walking through the steps with the BFI data as a running example.

Putting it together: a mini-EDA

# Education distribution — what does it look like?
bfi |>
  filter(!is.na(education)) |>
  mutate(education = factor(education, labels = c(
    "HS incomplete", "HS grad", "Some college",
    "College grad", "Graduate degree"
  ))) |>
  ggplot(aes(x = education)) +
  geom_bar(fill = "#2c7fb8") +
  labs(x = "Education level", y = "Count") +
  theme_minimal(base_size = 14) +
  theme(panel.grid = element_blank(),
        axis.line = element_line(color = "gray70"),
        axis.text.x = element_text(angle = 30, hjust = 1))

Putting it together: a mini-EDA

Wrapping up

EDA toolkit so far

Tool	When to use
glimpse()	First look at structure
summary()	Quick numeric summaries
geom_histogram()	Continuous distributions
geom_density()	Smooth distribution shape
geom_bar()	Categorical distributions
geom_boxplot()	Outlier detection
count()	Frequency tables
is.na() / sum(is.na())	Missing data check

Before next class

📖 Read:

• R4DS Ch 10: Exploratory data analysis (sections 10.5–10.6)

✅ Practice:

• Explore at least 3 variables in bfi
• Look for outliers and missing data
• Start generating questions

Key takeaways

1. EDA is an attitude — curiosity, not confirmation
2. Always visualize — summary stats hide patterns
3. Outliers are information — investigate, don’t delete
4. Check missing data first — it affects everything
5. Ask questions, then answer them — that’s the loop

The one thing to remember

EDA isn’t a step you finish. It’s the habit of looking at your data before you believe anything about it.

Next time: EDA — Covariation

Remind students that the reading for next time is R4DS Ch 10 sections 10.5–10.6 (covariation). No assignment is due or assigned today, but the Final Project Proposal is due soon — check the schedule. The next slide gives them a head start on Assignment 5; if there’s time left in class, work through it together, otherwise frame it as homework.

Get a head start

Assignment 4: Part 2 (Distributions)

Open Assignment 4 and start Part 2. You have everything you need:

1. 2.1 — Histogram of penguin body mass. Try ≥3 binwidths in your scratch work; submit the one that best shows the shape, with a comment explaining why.
2. 2.2 — Overlapping density plots of body mass, colored by species, with transparency.
3. 2.3 — Boxplot of body mass by species, then violin plot. Comment on what each shows that the other doesn’t.

Due Sunday, May 3 at 11:59 PM.

Give students ~10 minutes of work time here if class time allows. Part 2 of A4 is a perfect match for today’s material — histograms, densities, and boxplots all just covered. Circulate and help with code issues. Common stumbles: forgetting library(palmerpenguins), missing na.rm = TRUE in summaries, picking a binwidth that’s too small/large. If pairs finish early, point them to Part 1 (bar chart with error bars from Session 8 material) or Part 3 (the bad-graph / good-graph exercise from Session 9).