Session 2 — Types of Data Grade 4 Data Science · Ages 9–10 ← → or Space to navigate · F = fullscreen
1 / 15
Session 2 of 8

Types of Data

Not all data is the same. Today we learn to tell the difference — and why it matters for choosing the right graph.

📊 Data Science for Young Minds · Grade 4
2 / 15
Opening Hook

Which One Is Different?

Blue
Green
Red
42

Which one is different? Why?

3 / 15
Today's Plan

What We're Doing Today

4 / 15
Lesson 1

Categorical Data

Data that names a group or label. You can't do math on it — you can only count how many are in each group.

🏷️ Examples of Categorical Data
Favorite color · Eye color · Type of pet · Country of birth
Preferred sport · Hair color · Season born · Shoe brand

Quick test: Can you calculate the average? If no → it's probably categorical.
What's the average eye color? 🤷 Meaningless! That confirms it's categorical.

5 / 15
Lesson 2

Numerical Data

Data that is a number you can calculate with — add, subtract, find the average, compare sizes.

🔢 Examples of Numerical Data
Height (cm) · Age · Test score · Hours of sleep · Temperature
Number of pets · Distance to school · Pulse rate · Weight

Quick test: Can you find the average? If yes → it's numerical.
Average height of the class? ✅ That makes sense!

6 / 15
Lesson 3

Discrete vs. Continuous

Numerical data has two sub-types. The key question: can it be a fraction?

📌 Discrete

  • Whole numbers only
  • You count them
  • Can't be a fraction
  • 2 siblings, not 2.5
  • 3 pets, 7 books, 4 goals

📏 Continuous

  • Any value on a number line
  • You measure them
  • Can be a decimal
  • 1.73 m tall, 36.8°C
  • Height, weight, time, temp
7 / 15
Lesson 4

Data Type → Graph Type

The type of data you have determines which graph to use. Wrong type = misleading graph!

Categorical
Bar Chart
Compare group counts
Categorical
Pie Chart
Show parts of a whole
Categorical
Pictograph
Visual count by symbol
Numerical (Discrete)
Line Plot
Show frequency on a number line
Numerical (Discrete)
Stem-and-Leaf
Show distribution of values
Numerical (Continuous)
Line Graph
Show change over time
8 / 15
Activity Time!

Data Sorting Challenge

Your group has 20 data cards. Sort each one into:

🏷️ Categorical
Names a group or label.
Can't calculate average.
🔢 Numerical
A number you can calculate with.
Can find average.

⚠️ Some cards might be "Either" — that's OK! Be ready to explain your choice. ⏱ You have 15 minutes.

9 / 15
Tricky Cases!

Edge Cases — What Would You Do?

Data scientists debate these edge cases all the time. What matters is explaining your reasoning.

10 / 15
🧠
Brain Break — Data Type Bingo!

Your teacher will call out a variable. Stand up if it's categorical, stay seated if it's numerical!

Favorite food · Height · Eye color · Temperature · Number of siblings · Country · Test score · Hair color

11 / 15
Debrief

Sort Debrief — Let's Compare!

"Did any card cause a debate in your group? Which one? How did you decide?"

12 / 15
Graph Matching

Match the Data to the Graph

For each scenario below, which graph type would you choose?

No single right answer for every case — but some choices are clearly better. Be ready to explain why.

13 / 15
Connecting to Real Life

Where You See Data Types Every Day

🏷️ Categorical Around You

  • Sports teams (names)
  • Menu items at lunch
  • Countries on a map
  • Genres of books

🔢 Numerical Around You

  • Sports scores (discrete)
  • Weather temperature (continuous)
  • Price of lunch (continuous)
  • Steps walked today (discrete)

Data scientists ask "what type is this?" before doing anything else with data.

14 / 15
Vocabulary Review

Words to Know

Categorical
Data that names groups or labels; can't be averaged
Numerical
Data that is a number you can calculate with
Discrete
Countable whole numbers only — no fractions
Continuous
Can be any value including decimals; measured not counted
Variable
Any characteristic being measured or observed
Graph type
The visualization chosen based on the data type
15 / 15
Wrap Up

Session 2 Complete!

🔮 Coming up — Session 3: Now that we know what types of data exist, how do we collect it well? Better surveys — without the bias.