2, 4, 6, 8
Sxx = 120 − 20²/4
20.
The sample (unbiased) variance is , where .
This page is easier if you are comfortable with:
When the data is a sample from a larger population, dividing by tends to underestimate the population variance. Dividing by corrects this bias, which is why is called the unbiased estimator.
First find , the sum of squared deviations from the mean. A convenient way is .
The sample standard deviation is . Calculators usually give both versions. The population version is in mean, variance and standard deviation, it is used in the one-sample t statistic and the confidence interval for a mean, and coding of data shows how it scales.
This page is part of Averages and spread in Statistics. Topics that work alongside it: Mean, variance and standard deviation, One-sample t statistic, Confidence interval for a mean (σ unknown), Coding of data, Estimated mean of grouped data and Mean.
The sample (unbiased) variance divides by n − 1 instead of n. It gives a better estimate of the population variance from a sample.
Their sum 8 divided by n − 1 = 2 gives the sample variance 4.
These examples are worked by hand, step by step, so you can compare your own working.
Find the sample variance of 1, 2, 3, 4, 5.
Find the population variance of the same data and compare.
Find the sample variance of 2, 4, 6.
A few situations come up again and again. Knowing them saves time and helps you spot answers that cannot be right.
Sxx = 120 − 20²/4
20.
s² = Sxx/(n − 1)
6.6667.
s²
2.5.
s
1.5811.
s² = Sxx/(n − 1), with Sxx = Σx² − (Σx)²/n. Dividing by n − 1 makes it unbiased.
Σx = 20, Σx² = 120, n = 4.
Divide by 3.
Σx = 15, Σx² = 55, n = 5.
√2.5.
n ✗
n − 1 ✓
Unbiased.
no square ✗
(Σx)²/n ✓
Formula.
s² ✗
√s² ✓
Standard deviation.
possible ✗
never ✓
Sum of squares.
Try each one on paper, then open the answer. Use the solver above to see the full working.
20
5
8
3
5
1
Unlimited fresh questions with instant marking. Choose a level, work it out on paper, then type your answer.
Solve: …
s² = Sxx/(n − 1).
To make s² unbiased for σ².
Σx² − (Σx)²/n.
The square root of s².
one-sample t statistic.
confidence interval, σ unknown.
More in Statistics and the formula sheets.