Consider two cricketers whose average score per game is 40. One player consistently scores around 40, while the other scores zero in one game and then a century in the next game. Even though the averages are similar, there is definitely a difference between the two individuals. How do we measure this difference?

Standard Deviation is one of the most important concepts within the realm of statistics. And every data scientist should know it well. An Online Data Science and AI Course will make sure you get the hang of it through various projects. This blog post tells you everything about Standard Deviation in simple language with practical examples.

What Is Standard Deviation?

Standard Deviation indicates how much variation there is in relation to the mean. When Standard Deviation is low, this suggests that most numbers appear near the mean. If Standard Deviation is high, then most numbers are far away from the mean.

A Simple Example

Take two classes where students scored these marks on a test.

• Class A: 48, 49, 50, 51, 52

• Class B: 20, 35, 50, 65, 80

In both classes, the mean mark is 50. However, in Class A, all the students had marks around 50; thus, the standard deviation is low at 1.4. On the other hand, in Class B, there is variability among the marks; therefore, the standard deviation is high at 21.2. The mean conceals the entire tale, but standard deviation tells it all.

How Is It Calculated?

You do not need to be afraid of the formula. The steps are easy.

• Step 1: Find the mean of all values.

• Step 2: Subtract the mean from each value to see how far each one is.

• Step 3: Square each difference, so negative numbers do not cancel positive ones.

• Step 4: Find the average of these squared differences. This is called variance.

• Step 5: Take the square root of the variance. That is your standard deviation.

In Python, you can do this in one line with NumPy using np.std(data) or with Pandas using df['column'].std().

Real-World Examples

Weather: If the temperature of a place ranges from 28 to 32 degrees per day, the standard deviation will be small. However, if there is a variation ranging from 5 to 40 degrees per day, then the standard deviation will be high. This way, it becomes easy for us to know which clothes we should take along with us.

Stock market: Investors employ Standard Deviation when evaluating their investments' risks. Securities with higher Standard Deviations experience volatile changes in prices, while those with lower values have steady price movements.

Delivery services: Delivery time prediction is critical when using the application. When food arrives within 30 minutes with a low standard deviation, clients will be sure about the delivery time. High standard deviation indicates variability, where food may arrive within 15 minutes or 60 minutes.

Manufacturing: The factory producing 100g packets examines the standard deviation of weights. A low standard deviation indicates high-quality standards.

Salaries: In any corporation, a large standard deviation in salary demonstrates a huge disparity between employees' earnings.

The 68-95-99.7 Rule

When data follows a bell-shaped curve (normal distribution), standard deviation gives a handy rule.

• About 68% of values fall within 1 standard deviation of the mean.

• About 95% fall within 2 standard deviations.

• About 99.7% fall within 3 standard deviations.

This rule is also used to find outliers. A value more than 3 standard deviations away is unusual and needs a closer look.

Conclusion

Standard Deviation is an easy-to-use yet highly effective technique. It shows the accuracy of your average value and variability within your dataset. Whether you analyze climate change, financial investments, or logistics and payroll, it aids your decision-making process.

However, if you seek knowledge about how these concepts are applied using modern techniques, then the AI Tools Course in India provides professional guidance along with practical work and job placement services.