Statistics for analysts: glossary
The statistical ideas behind everyday analysis: averages, spread, correlation, experiments and significance.
- Mean (Average)The mean is the sum of a set of values divided by how many there are, which is what most people call the average.
- MedianThe median is the middle value when a set of numbers is sorted, so half the values are below it and half are above.
- ModeThe mode is the value that appears most often in a set of data.
- Standard DeviationStandard deviation measures how spread out values are around their mean: a small value means they cluster closely, a large one means they vary a lot.
- PercentileA percentile is the value below which a given percentage of the data falls; the 90th percentile is the value that 90 percent of observations do not exceed.
- CorrelationCorrelation measures how closely two numeric variables move together, on a scale from -1 (opposite) through 0 (unrelated) to +1 (together).
- OutlierAn outlier is a value that is far from the rest of the data, which may be a genuine extreme or an error.
- A/B TestAn A/B test is an experiment that splits users randomly into two groups, shows each a different version, and compares a chosen outcome.
- Statistical SignificanceA result is statistically significant when it would be unlikely to arise by chance alone if there were really no difference, judged against a threshold chosen in advance.
- Confidence IntervalA confidence interval is a range of values that is likely to contain the true figure, given the uncertainty in your sample.
- Cohort AnalysisCohort analysis groups people by a shared starting point, such as the month they signed up, and tracks how each group behaves over time.