Reading a Histogram

A histogram shows test scores. The interval $70-80$ has a bar reaching up to $12$. What does this tell us?

Identify the interval: The interval is $70-80$, meaning scores from 70 up to (but not including) 80 = Score range: 70-79

Read the frequency: The bar height is $12$ on the y-axis = Frequency = 12

Interpret the meaning: 12 students scored between 70 and 79 points = 12 students in this range

Answer: 12 students scored between 70 and 79 on the test.

Finding Total Data Points

A histogram has 4 bars with frequencies: $5$, $8$, $12$, and $3$. How many data points are there in total?

List all frequencies: Bar 1: 5, Bar 2: 8, Bar 3: 12, Bar 4: 3 = Four frequencies identified

Add all frequencies: $5 + 8 + 12 + 3 = 28$ = Sum = 28

State the total: Total data points = sum of all frequencies = 28 data points

Answer: There are 28 data points in total.

Creating Interval Boundaries

You have data ranging from 15 to 58. Create 5 equal intervals for a histogram.

Find the range: $58 - 15 = 43$ = Range = 43

Calculate interval width: $43 \div 5 = 8.6$, round up to 9 for nice numbers = Width = 9

Create the intervals: Start at 15: 15-24, 24-33, 33-42, 42-51, 51-60 = 5 equal intervals

Verify coverage: 15 to 60 covers all data from 15 to 58 = All data included

Answer: The 5 intervals are: 15-24, 24-33, 33-42, 42-51, and 51-60.

Comparing Distributions

Two histograms show exam scores. Class A has most bars on the left side. Class B has most bars on the right side. What does this tell us?

Analyze Class A: Bars concentrated on the left = lower scores more frequent = Class A: left-skewed distribution

Analyze Class B: Bars concentrated on the right = higher scores more frequent = Class B: right-concentrated distribution

Compare the classes: Right side means higher values, so Class B performed better overall = Class B scored higher

Draw conclusion: The shape of a histogram reveals performance patterns = Distribution shapes tell a story

Answer: Class B performed better overall because their scores are concentrated at higher values (right side of the histogram).

Mistake: Leaving gaps between bars

Why: In histograms, bars touch because the data is continuous. Gaps would imply missing data ranges.

Correct: Always draw histogram bars touching each other. Bar graphs (for categorical data) have gaps; histograms do not.

Mistake: Confusing histograms with bar graphs

Why: Bar graphs show categories (like favorite colors). Histograms show continuous numerical ranges.

Correct: Histogram = continuous data with intervals, bars touch. Bar graph = categories, bars have gaps.

Mistake: Using unequal interval widths

Why: Unequal widths make it hard to compare frequencies fairly - a wider bar naturally captures more data.

Correct: Keep all intervals the same width (e.g., all 10 units wide: 0-10, 10-20, 20-30).

Mistake: Miscounting which interval a value belongs to

Why: Boundary values can be confusing. Is 20 in the 10-20 or 20-30 interval?

Correct: Use a consistent rule: intervals include the lower bound but exclude the upper bound. So 20 goes in 20-30, not 10-20.

Analyzing Test Scores

Teachers use histograms to understand class performance at a glance.

A histogram of 30 test scores shows: 0-50 (2 students), 50-60 (5), 60-70 (8), 70-80 (10), 80-90 (4), 90-100 (1).

Customer Wait Times

Restaurants track how long customers wait to be seated to improve service.

A histogram shows wait times: 0-5 min (15 customers), 5-10 min (25), 10-15 min (18), 15-20 min (7), 20+ min (3).

Student Heights in PE Class

Physical education teachers track student heights to group students fairly for activities.

Heights in cm: 140-150 (4), 150-160 (12), 160-170 (18), 170-180 (8), 180-190 (3).

Q: What is the difference between a histogram and a bar graph?

A: A histogram shows continuous numerical data with touching bars, while a bar graph shows categorical data with gaps between bars. Histograms use intervals; bar graphs use distinct categories.

Q: How do I choose the number of intervals?

A: A common guideline is 5-15 intervals. Too few intervals hide details; too many create noise. The square root of the number of data points is a good starting point.

Q: What if a data value falls exactly on a boundary?

A: Use a consistent rule. Typically, intervals include the lower bound but exclude the upper bound. So 50 would go in the 50-60 interval, not the 40-50 interval.