What is the difference between a frequency polygon and a cumulative frequency diagram regarding the x-axis?

A frequency polygon plots points at the midpoint of each class interval, whereas a cumulative frequency diagram plots points at the upper class boundary. This is because cumulative frequency represents the total data accumulated up to the end of that interval.

When should you use the lower boundary of a class interval in a cumulative frequency diagram?

The lower boundary of the very first class interval is used only once to plot the starting point of the graph at a cumulative frequency of 0. All subsequent points are plotted using the upper boundaries of their respective classes.

How does the calculation of the median position differ between a raw list of data and a cumulative frequency diagram?

For a raw list of $n$ items, the median position is often $\frac{n+1}{2}$. However, for a cumulative frequency diagram representing grouped continuous data, the median position is simply $\frac{n}{2}$ on the y-axis.

What is a common error when plotting the points for a cumulative frequency diagram?

A common mistake is plotting the cumulative frequency against the midpoint of the class interval instead of the upper boundary. This results in an inaccurate representation of the data accumulation and incorrect estimates for the median and quartiles.

Why is it incorrect for a cumulative frequency curve to ever slope downwards?

Cumulative frequency is a running total of frequencies. Since frequency counts cannot be negative, the total can only increase or stay the same as you move across the data range, meaning the curve must always be non-decreasing.

What happens if you forget to start the cumulative frequency curve at $y=0$?

If the curve does not start at the lower boundary of the first class at $y=0$, the graph will not accurately represent the full range of the data. This often leads to incorrect estimations of percentiles and quartiles near the lower end of the dataset.

Define 'Cumulative Frequency'.

Cumulative frequency is the sum of the frequencies of a data set up to a certain point. In a grouped frequency table, it is the running total of all frequencies from the first interval to the current one.

An ogive is the technical term for a cumulative frequency polygon or curve. It displays the cumulative frequency on the y-axis against the class boundaries on the x-axis, typically forming an S-shaped curve.

What is the formula for the position of the $p$-th percentile on the y-axis?

The position of the $p$-th percentile for a dataset with $n$ total values is calculated as $\frac{p}{100} \times n$. You then find this value on the y-axis to determine the percentile value on the x-axis.

How is the Interquartile Range (IQR) determined from a cumulative frequency graph?

The IQR is found by subtracting the Lower Quartile ($Q_1$, at $\frac{n}{4}$) from the Upper Quartile ($Q_3$, at $\frac{3n}{4}$). It represents the spread of the middle 50% of the data values.

Drawing Cumulative Frequency Diagrams | WJEC GCSE Maths

Maths And Numeracy Double Award / Higher

Statistics & Probability

Drawing Cumulative Frequency Diagrams

Summary

A cumulative frequency diagram, often called an ogive, is a statistical graph used to represent the running total of frequencies for grouped continuous data. It provides a visual method for estimating the median, quartiles, and percentiles of a dataset when the exact raw values are unknown.

1. Definition & Core Concepts

Cumulative Frequency: This is the 'running total' of frequencies. For any given class interval, the cumulative frequency is the sum of the frequency of that interval and all preceding intervals.
Grouped Data: Cumulative frequency diagrams are specifically designed for data that has been organized into classes or intervals, such as heights, weights, or time durations.
The Ogive: This is the technical name for the resulting S-shaped curve. It must always be non-decreasing because cumulative totals can only stay the same or increase as more data is added.

A cumulative frequency diagram showing an S-shaped curve with dashed lines indicating how to find the median from the y-axis (n/2) to the x-axis.

2. Underlying Principles

Upper Boundary Logic: Points are plotted against the upper class boundary because the cumulative frequency represents the total number of observations that are less than or equal to that specific value. We cannot guarantee all items in a class are accounted for until we reach the end of that class.
The Zero Point: Every cumulative frequency diagram must start at the lower boundary of the first class with a cumulative frequency of 0. This represents the point where no data has yet been recorded.
Continuous Assumption: By joining points with a smooth curve, we assume that the data is distributed evenly and continuously across each interval.

3. Methods & Techniques

Step 1: Create a Cumulative Frequency Table: Add a new column to the frequency table. Calculate the running total by adding each frequency to the sum of all previous frequencies.
Step 2: Identify Coordinates: The x-coordinate is always the upper class boundary of the interval. The y-coordinate is the cumulative frequency calculated for that interval.
Step 3: Plotting: Plot each coordinate pair on a grid. Ensure the y-axis scale accommodates the total frequency ( $n$ ) and the x-axis covers the full range of data classes.
Step 4: Drawing the Curve: Connect the points with a smooth, freehand S-shaped curve. Avoid using a ruler to connect points unless specifically asked for a cumulative frequency polygon.

4. Data Interpretation

5. Key Distinctions

6. Exam Strategy & Tips