Statistics Calculators

Descriptive statistics are quick to compute and easy to misread. The mean of a skewed set says less than the median; a standard deviation means nothing without knowing whether the data is a sample or a population; a confidence interval is not the probability that the true value sits inside it. These calculators give the figures and are explicit about which assumption each one rests on.

Describing a set of numbers

Start with the mean, median and mode calculator for the centre, and the standard deviation calculator or variance calculator for the spread. All three accept numbers separated by commas, spaces, tabs or new lines, so pasting a column out of a spreadsheet works without reformatting. The sample-versus-population choice divides by n-1 or n respectively; sample is the right answer in nearly every real case.

Comparing and inferring

A z-score places one value within a distribution and is the basis of most "is this unusual?" questions. The confidence interval calculator and the margin of error calculator put bounds on an estimate, and the sample size calculator tells you how many responses you need before the bounds are narrow enough to be worth reporting.

Relationships between two variables

The correlation coefficient calculator measures how tightly two sets move together, and the linear regression calculator fits the line and gives its slope, intercept and r-squared. Both come with the same warning, which is worth repeating because it is ignored so often: a strong correlation is not evidence that one thing causes the other.