# How to find variance using Python

0
11

This article was originally published on Built In by Eric Kleppen.

Variance is a powerful statistic used in data analysis and machine learning. It is one of the four main measures of variability along with range, interquartile range (IQR) and standard deviation. Understanding variance is important because it gives you insight into the spread of your data and can be used to compare differences in sample groups or identify important modeling features. Variance is also used in machine learning to understand changes in model performance due to using different samples of training data.

Calculating variance is easy using Python. Before diving into the Python code, I’ll first explain what variance is and how you can calculate it. By the end of this tutorial you’ll have a better understanding of why variance is an important statistic, along with several methods for calculating it using Python.

## What is variance?

Variance is a statistic that measures dispersion. Low variance indicates that values are generally similar and do not vary widely from the mean while high variance indicates values are more widely dispersed from the mean. You can use variance on either a sample set or the entire population as the calculation takes in all data points in the given set. Although the calculation differs slightly when you’re looking at a sample versus population, you can calculate the variance as the average of the squared differences from the mean.

Since the variance is a squared value, it can be difficult to interpret compared to other measures of variability like standard deviation. Regardless, reviewing variance can be helpful; doing so can make it easier for you to decide which statistical tests to use with your data. Depending on the statistical tests, uneven variance between samples could skew or bias results.

One of the popular statistical tests that applies variance is called the analysis of variance (ANOVA) test. An ANOVA test is used to gauge whether any of the group means are significantly different from one another when analyzing a categorical independent variable and a quantitative dependent variable. For example, say you want to analyze whether social media use impacts hours of sleep. You could break social media use into different categories like low use, medium use and high use, then run an ANOVA test to gauge whether there are statistical differences between the group means. The test can show whether results are explained by group differences or individual differences.

## How do you find the variance?

Calculating the variance for a data set can differ based on whether the set is the entire population or a sample of the population.

The formula for calculating the variance of an entire population looks like this:

σ² = ∑ (Xᵢ— μ)² / N

An explanation of the formula:

• σ² = population variance
• Σ = sum of…
• Χᵢ = each value
• μ = population mean
• Ν = number of values in the population
• Using an example range of numbers, let’s walk through the calculation step by step.

Example range of numbers: 8, 6, 12, 3, 13, 9

Find the population mean (μ):

Calculate deviations from the mean by subtracting the mean from each value.

Square each deviation to get a positive number.

Sum the squared values.

Divide the sum of squares by N or n-1.

Since we’re working with the entire population, we’ll divide by N. If we were working with a sample of the population, we would divide by n-1.

69.5/6 = 11.583

There we have it! The variance of our population is 11.583.

## Why use n-1 when calculating the sample variance?

Applying n-1 to the formula is called Bessel’s correction, named after Friedrich Bessel. When using samples, we need to calculate the estimated variance for the population. If we used N instead of n-1 for the sample, the estimate would be biased, potentially underestimating the population variance. Using n-1 will make the variance estimate larger, overestimating variability in samples, thus reducing biases.

Let’s recalculate the variance pretending the values are from a sample:

As we can see, the variance is larger!

## Calculating variance using Python

Now that we’ve done the calculation by hand, we can see that completing it for a large set of values would be very tedious. Luckily, Python can easily handle the calculation for very large data. We will explore two methods using Python:

• Write our own variance calculation function
• Use Pandas’ built-in function

Writing a variance function

As we begin to write a function to calculation variance, think back to the steps we took when calculating by hand. We want the function to take in two parameters:

• population: an array of numbers
• is_sample: a Boolean to alter the calculation depending on whether we’re working with a sample or population

Start by defining the function that takes in the two parameters.

Next, add logic to calculate the population mean.

After calculating the mean, find the differences from the mean for each value. You can do this in one line using a list comprehension.

Next, square the differences and sum them.

Lastly, calculate the variance. Using an If/Else statement, we can utilize the is_sampleparameter. If is_sampleis true, calculate variance using (n-1). If it is false (the default), use N:

We can test the calculation using the range of numbers we crunched by hand:

## Finding variance using Pandas

Although we can write a function to calculate variance in less than 10 lines of code, there is an even easier way to find variance. You can do it in one line of code using Pandas. Let’s load up some data and work through a real example of finding variance.