Statistical Averages and Data Representation

Statistics Unlocked: From Data to Dominance 📊

Introduction

1. Introduction

Hey! Welcome to the world of Statistics. I know, I know... 'stats' sounds like something your parents talk about, but trust me, it's everywhere. It's how Spotify knows what to put in your Discover Weekly, how game developers balance weapons in your favorite shooter, and how you figure out if you're actually spending too much time on TikTok. We're going to break it all down, make it make sense, and you'll be a data wizard in no time. Let's get this bread. 🥖

8. Comparing Data with Back-to-Back Stem-and-Leaf Diagrams

What's better than one stem-and-leaf diagram? Two, obviously! A back-to-back diagram lets you compare two sets of data using the same stem. It's perfect for comparing things like test scores between two classes, or the performance of two different sports teams. You read one side normally (left to right) and the other side backwards (right to left). When you're asked to compare the data, you should calculate things like the median and range for both datasets and then write a sentence comparing them. For example, 'Class A has a higher median score, so they performed better on average, but Class B has a smaller range, so their scores were more consistent.'

A back-to-back stem-and-leaf diagram comparing boys' and girls' test scores. The stem is in the middle, with leaves for girls on the left and leaves for boys on the right.

Worked example

Worked Example: Comparing Data Sets Using Back-to-Back Diagrams

Worked Example: Comparing Likes on Two Posts

The diagram shows the number of likes received per minute on two different Instagram posts (Post A and Post B) in their first 10 minutes. Compare the two sets of data by finding the median and range for each. Key: 8|1|2 means 18 for Post A and 12 for Post B. Post A (Leaf) | Stem | Post B (Leaf) 8, 5, 2 | 1 | 2, 5, 9 9, 6, 3, 3 | 2 | 0, 1, 4, 8 4, 1 | 3 | 1

10. Classifying and Tabulating Statistical Data

Alright, let's talk about sorting data. Imagine you've just done a survey for your school project, asking everyone their favourite gaming console. Right now, you have a massive, messy list of answers: 'PlayStation', 'Xbox', 'Switch', 'PlayStation', 'PC', 'Switch'... it's basically your brain after scrolling through TikTok for an hour - total chaos! This messy list is called raw data . So, how do we make sense of it? The first step is to organise it into a table. The simplest way is a tally and frequency table . You create columns for the console, the tally, and the frequency (which is just the count). For every 'PlayStation' you see, you put a tally mark (|) next to it. Remember that cool gate thing we do for the fifth tally? (||||) That makes counting way faster. The final frequency column is just the total number for each console.

A clear example of a tally and frequency table showing favourite gaming consoles with columns for 'Console', 'Tally', and 'Frequency'.

But what if you want to compare two things at once? Like, who prefers which console, and whether they're in Year 10 or Year 11? That's where a two-way table comes in. It’s like a spreadsheet that lets you see the relationship between two different categories. You'd have the consoles along the top (as columns) and the year groups down the side (as rows). Each box (or 'cell') in the middle shows you the number of people who fit both categories, like 'Year 10 students who prefer PlayStation'. It's a super powerful way to see patterns in your data at a glance. You'll use these everywhere, from science experiments to business reports.

Worked example

Worked Example: Creating a Two-Way Table

Let's Get This Data Sorted ✨

A survey asked 30 students about their preferred music streaming service (Spotify or Apple Music) and whether they have a premium subscription. The raw data is: Spotify Premium, Apple Music Free, Spotify Free, Spotify Premium, Spotify Premium, Apple Music Premium, Spotify Free, Spotify Premium, Apple Music Free, Apple Music Premium, Spotify Premium, Spotify Free, Spotify Premium, Apple Music Free, Spotify Free, Apple Music Premium, Spotify Premium, Spotify Premium, Apple Music Free, Spotify Free, Apple Music Premium, Spotify Free, Spotify Premium, Apple Music Free, Spotify Premium, Apple Music Premium, Spotify Free, Apple Music Free, Spotify Premium, Apple Music Free. Organise this data into a two-way table.

1
$First, let's identify our two categories. We're comparing the streaming service (Spotify vs. Apple Music) and the subscription type (Premium vs. Free). These will be the headings for our rows and columns.$
$Category 1: Streaming Service (Spotify, Apple Music) Category 2: Subscription Type (Premium, Free)$
2
$Next, we'll draw the grid for our two-way table. Let's put the streaming services as the columns and the subscription types as the rows. Don't forget to add 'Total' rows and columns - they're essential for checking our work later.$
| Spotify | Apple Music | Total
--------------------------------------------
Premium | | |
--------------------------------------------
Free | | |
--------------------------------------------
Total | | |
3
$Now for the main task. Go through the raw data list one by one and put a tally mark in the correct box. For example, the first entry is 'Spotify Premium', so a tally goes in the top-left box. The second is 'Apple Music Free', so a tally goes in the bottom-right box. Keep going until you've tallied all 30 responses.$
| Spotify | Apple Music | Total
-------------------------------------------------
Premium | |||| |||| | |||| |
-------------------------------------------------
Free | |||| || | |||| ||| |
-------------------------------------------------
Total | | |
4
$Finally, we count up the tallies to get the frequencies for each cell. Then, we add up the rows and columns to find the totals. The grand total in the bottom-right corner should be 30, the total number of students surveyed. If it is, we've nailed it! ✅$
| Spotify | Apple Music | Total
--------------------------------------------
Premium | 10 | 5 | 15
--------------------------------------------
Free | 7 | 8 | 15
--------------------------------------------
Total | 17 | 13 | 30

Answer

| Spotify | Apple Music | Total -------------------------------------------- Premium | 10 | 5 | 15 -------------------------------------------- Free | 7 | 8 | 15 -------------------------------------------- Total | 17 | 13 | 30

11. Measures of Central Tendency and Spread

\text{Mean} = \frac{\text{Sum of all values}}{\text{Number of values}}

A colorful infographic showing four boxes. Box 1 for Mean with a calculator icon and the formula . Box 2 for Median with an icon of a list of numbers with the middle one highlighted. Box 3 for Mode with a trophy icon next to the most frequent number. Box 4 for Range with an arrow pointing between the smallest and largest number.

Finally, we have the Range . The range isn't an average; it's a measure of spread . It tells you how consistent or spread out your data is. You just find the highest value and subtract the lowest value. A small range means your data is all clustered together (everyone in your group chat responds in under 5 minutes), while a large range means it's all over the place (one person responds instantly, another takes three days). Simple as that!

Worked example

Calculating Averages and Range from a Frequency Table

Let's Crunch Some Numbers 🤓

You poll your friends to see how many hours they spent gaming last Saturday. The results are shown in this frequency table. Let's find the mean, median, mode, and range of the hours spent gaming. Hours Gaming (x) | Frequency (f) 1 | 3 2 | 5 3 | 6 4 | 4 5 | 2

1
$First, let's find the Mode . This is the easiest one! We just look for the value with the highest frequency. The highest frequency is 6, which corresponds to 3 hours of gaming.$
$\text{Mode} = 3 \text{ hours}$
2
$x$
$\text{Range} = \text{Max value} - \text{Min value} = 5 - 1 = 4 \text{ hours}$
3
$\sum f$
$\text{Total Friends} (\sum f) = 3 + 5 + 6 + 4 + 2 = 20 \\ \text{Total Hours} (\sum (x \times f)) = (1 \times 3) + (2 \times 5) + (3 \times 6) + (4 \times 4) + (5 \times 2) = 3 + 10 + 18 + 16 + 10 = 57 \\ \text{Mean} = \frac{\sum (x \times f)}{\sum f} = \frac{57}{20} = 2.85 \text{ hours}$
4
$n=20$
$\text{Median Position} = \frac{20+1}{2} = 10.5^{th} \text{ value} \\ \text{Both the 10th and 11th values are 3.} \\ \text{Median} = 3 \text{ hours}$

Answer

\text{Median Position} = \frac{20+1}{2} = 10.5^{th} \text{ value} \\ \text{Both the 10th and 11th values are 3.} \\ \text{Median} = 3 \text{ hours}

12. Interpretation and Comparison of Statistical Data

Alright, let's talk about being a data detective. You get hit with stats all the time - your screen time report, your Spotify Wrapped, your K/D ratio in a game. Interpretation is just figuring out the story behind the numbers. When you see a bar chart showing your music genres, you're not just seeing bars; you're interpreting that you had a massive pop phase in July. That's drawing an inference!

A side-by-side comparison of two bar charts, one showing 'Hours Gaming per Week for Group A' and the other for 'Group B'. Group B's bars are generally higher but also more spread out.

Now, the real level-up is comparison . This is where you put two sets of data head-to-head, like comparing your part-time job earnings with your friend's. To do this like a pro, you need two key weapons: averages (mean or median) and the range . 1. Comparing Averages: This tells you which group is typically higher or lower. If Class X has a mean test score of 75% and Class Y has a mean of 68%, you can say, 'On average, Class X performed better.' It’s the main headline. 2. Comparing Ranges: This is all about consistency . A small range is like your friend who is always on time - super consistent and predictable. A large range is like that one character in a game with unpredictable special moves - all over the place! If Class X has a range of 20 marks and Class Y has a range of 50, you'd say, 'The scores in Class X were more consistent.' But hold up! 🛑 Before you jump to conclusions, remember data can be tricky. If your sample size is tiny (like asking two people), your conclusion isn't very reliable. And watch out for outliers! That one time you aced a test with 100% could pull your average up, but it might not represent how you usually do. So, always think: is this data telling the whole story?

Worked example

Worked Example: Comparing Social Media Performance

Insta-Famous: The Head-to-Head Battle 🏆

Two friends, Alex and Ben, track the number of likes they get on their last 7 Instagram posts. The results are: Alex: 112, 130, 125, 119, 128, 115, 121 Ben: 150, 95, 142, 105, 135, 110, 118 Compare their performance using the mean and range.

13. Correlation and Scatter Diagrams

Alright, let's talk about correlation. Think of it as checking the 'vibe' between two sets of data. Are they related? Do they move together? A scatter diagram is our go-to tool here. It's basically a graph where you plot points (usually as little 'x's, as the syllabus likes!) to see if there's a pattern between two variables. Each 'x' on the graph represents one 'thing'—like one person or one car—and its position is determined by two pieces of info about it, like your hours spent gaming (x-axis) and your phone battery percentage (y-axis). Once you've plotted the points, you can see the relationship. There are three main types of correlation: 1. Positive Correlation : This is when both variables tend to increase together. Like the more hours you work at your part-time job, the more money you'll have. On the graph, the points will trend upwards from left to right, like they're climbing a hill. 2. Negative Correlation : This is the opposite. As one variable goes up, the other goes down. Think about the age of a car and its value - the older it gets, the less it's worth. The points will trend downwards. 3. No Correlation (or Zero Correlation): The points are just scattered everywhere, like random snaps on a map. There's no connection. For example, your shoe size and the number of songs on your Spotify playlist probably have zero to do with each other.

A clear diagram showing three scatter plots side-by-side. The first shows points trending upwards (Positive Correlation). The second shows points trending downwards (Negative Correlation). The third shows points scattered randomly (No Correlation). Each graph is clearly labelled.

When you do see a positive or negative correlation, we can draw a line of best fit . This is a single, straight line you draw with a ruler that goes right through the middle of your points. It shows the overall trend. The key is to draw it by eye so there are roughly the same number of points above the line as below it, spread out along its whole length. This line is super useful because you can use it to make predictions. For instance, you could estimate a student's test score based on the hours they revised, even if you don't have that exact data point. It's like predicting the next big trend before it even happens! 😉

Worked example

Worked Example: Scatter Diagram Construction and Interpretation

Let's Plot This Out and See the Trend 📈

A student records the number of hours they spent revising for different tests and the percentage score they achieved. The data is shown below. Hours Revising: [1, 5, 2, 8, 4, 3, 6, 9] Test Score (%): [45, 75, 50, 95, 60, 65, 80, 90] a) Plot a scatter diagram for this data. b) Describe the correlation. c) Draw a line of best fit. d) Use your line to estimate the test score for a student who revised for 7 hours.

Practice this in the app

Unlock the full chapter: practice questions, flashcards, mock papers and notes, free.

Practice this in the app

App Store Google Play

Continue revising

← Previous chapterProbability See more chapters →

Mathematics (0580)

Statistical Averages and Data Representation

1. Introduction

2. Introduction to Measures of Central Tendency

Worked Example: Calculating Median and Mode from Raw Data

3. Calculating a Missing Value Given the Mean

Worked Example: Determining a Missing Data Point

4. Calculating the New Mean After Adding a Data Point

Worked Example: Calculating a Revised Mean

5. Calculating the Mean from a Frequency Table

Worked Example: Mean from a Frequency Table

6. Finding the Median and Mode from a Frequency Table

Worked Example: Median and Mode from a Frequency Table

7. Introduction to Stem-and-Leaf Diagrams

Worked Example: Finding Median and Range from a Stem-and-Leaf Diagram

8. Comparing Data with Back-to-Back Stem-and-Leaf Diagrams

Worked Example: Comparing Data Sets Using Back-to-Back Diagrams

9. Calculating a Missing Frequency Using the Mean

Worked Example: Finding a Missing Frequency

10. Classifying and Tabulating Statistical Data

Worked Example: Creating a Two-Way Table

11. Measures of Central Tendency and Spread

Calculating Averages and Range from a Frequency Table

12. Interpretation and Comparison of Statistical Data

Worked Example: Comparing Social Media Performance

13. Correlation and Scatter Diagrams

Worked Example: Scatter Diagram Construction and Interpretation

Practice this in the app