On this page
What this lesson covers
Dispersion measures how widely observations vary around their center; variance averages squared deviations, while standard deviation returns that measure to the data’s original units.
Compare range, mean absolute deviation and median absolute deviation before calculating population and sample variance. The lesson explains the n − 1 sample divisor, outlier sensitivity and approximate square-root-of-time scaling.
How do you calculate measures of dispersion?
Take absolute or squared deviations to prevent cancellation, then choose the population or sample divisor and take a square root for standard deviation.
Mean absolute deviation = sum of absolute distances from the mean / n
- Observation and sample mean
- Number of observations
Population variance = sum of squared distances from population mean / n
- Population mean and number of observations
Sample variance = sum of squared distances from sample mean / (n − 1); sample standard deviation = square root of sample variance
- Sample mean and sample size
- Sample variance and sample standard deviation
For example, Kellbrook’s squared deviations sum to 1008 in percent squared: population variance is 1008 / 8 = 126, while sample variance is 1008 / 7 = 144 and sample standard deviation is √144 = 12%.
Common mistakes
- Averaging signed deviations cannot measure dispersion because they sum to zero.
- Dividing a sample’s squared deviations by n systematically underestimates population variance.
- Assuming Bessel’s correction makes the sample standard deviation unbiased overlooks the bias that remains after taking the square root.
Try a practice question
Choose an answer, then check it to read the explanation for every option.
Continue studying in Quizara
In Quizara the lesson comes with more practice questions on the topic, explanations for every option and an AI tutor for your follow-up questions.
Written by the Quizara Editorial Team under our editorial standards.