What is an Outlier?

S1-SA4-0547

Grade Level:

Class 5

Data Science, Computing, AI, Statistics, Anomaly Detection

Definition

What is it?

An outlier is a data point that is very different from most other data points in a set. It 'lies outside' the normal range of values, making it stand out from the rest.

Simple Example

Quick Example

Imagine your cricket team's scores in five matches: 25, 30, 28, 5, and 32. Most scores are around 25-32, but 5 is much lower. Here, 5 is an outlier because it's very different from the other scores.

Worked Example

Step-by-Step

Let's find the outlier in the number of rotis eaten by 7 friends: 2, 3, 2, 15, 3, 2, 4.

Step 1: Look at all the numbers in the list: 2, 3, 2, 15, 3, 2, 4.
---Step 2: Identify the range of most numbers. Most friends ate between 2 and 4 rotis.
---Step 3: Find any number that is much higher or much lower than this range.
---Step 4: The number 15 is much higher than 2, 3, and 4.
---Step 5: So, 15 is the outlier because it doesn't fit with the other numbers.

Answer: The outlier is 15.

Why It Matters

Outliers are important because they can sometimes be mistakes, or they can show something very unusual and important! Data scientists and AI experts use this concept to find strange patterns in everything from online shopping to health data, helping them make better decisions or spot problems.

Common Mistakes

MISTAKE: Thinking every slightly different number is an outlier. | CORRECTION: An outlier must be significantly different, not just a little bit. It should really stand out.

MISTAKE: Not looking at all the data points before deciding. | CORRECTION: Always check the entire set of numbers to see the 'normal' pattern before identifying what doesn't fit.

MISTAKE: Assuming an outlier is always a mistake. | CORRECTION: Outliers can be mistakes, but they can also be important rare events or discoveries, like a new medicine working exceptionally well.

Practice Questions

Try It Yourself

QUESTION: Find the outlier in this list of daily chai prices from a shop (in Rupees): 10, 12, 10, 50, 11, 10. | ANSWER: 50

QUESTION: A student's scores in 6 tests are: 85, 90, 88, 15, 92, 89. Which score is an outlier? | ANSWER: 15

QUESTION: The number of samosas sold by a vendor each hour for 5 hours was: 25, 28, 30, 26, 80. If the average sale per hour is usually around 25-30, what is the outlier and why? | ANSWER: 80 is the outlier because it is much higher than the usual sales range of 25-30 samosas per hour.

MCQ

Quick Quiz

Which of these lists contains an outlier?

5, 6, 7, 8, 9

10, 11, 10, 12, 11

2, 3, 20, 4, 5

100, 101, 102, 103

The Correct Answer Is:

In option C, 20 is much larger than the other numbers (2, 3, 4, 5), making it an outlier. The other options have numbers that are all close to each other.

Real World Connection

In the Real World

Outliers are used a lot in banking and online payments like UPI! If someone usually spends ₹500 a day but suddenly tries to send ₹50,000, that's an outlier. Banks use this to detect fraud and protect your money. Similarly, weather scientists look for outlier temperatures to predict extreme weather events.

Key Vocabulary

Key Terms

DATA POINT: A single piece of information or value. | DATA SET: A collection of data points. | RANGE: The difference between the highest and lowest values in a data set. | ANOMALY: Something that deviates from what is standard, normal, or expected (similar to an outlier).

What's Next

What to Learn Next

Great job understanding outliers! Next, you can learn about 'Mean, Median, and Mode'. These concepts help us understand the 'center' of a data set and how outliers can affect these central values.