Statistics calculators

Find the mean, median, mode and range of a list of numbers, with each one worked out step by step.

Minimum, Q1, median, Q3 and maximum, plus the IQR and outliers, with a labeled box plot and every step.

Sample or population standard deviation and variance from a list of numbers, every step written out.

Sample and population variance from a list of values or a frequency table, with the standard deviation and every step.

Find how many standard deviations a value sits from the mean, plus its percentile.

Find probabilities above, below or between values on a normal curve, or the value for a given percentile.

Probability of exactly, at most, at least or between x successes in n trials, with a chart and every step.

nPr, nCr and counts with repetition, with exact answers, a step-by-step diagram and a list of every arrangement.

Apply the 68-95-99.7 rule to any mean and standard deviation, and see where a value falls.

Get the p-value from a z, t, chi-square or F statistic, one- or two-tailed, with the reasoning shown.

Critical values of z, t, chi-square and F for any significance level, one- or two-tailed.

One-sample, two-sample and paired t-tests with the t statistic, p-value, effect size and every step shown.

One-way ANOVA for three or more groups: the ANOVA table, F, p-value, effect size and Tukey comparisons, with every step.

Test of independence for a table of counts, or goodness of fit, with expected counts, the p-value and every step.

One- and two-proportion z-tests, including A/B tests, with the p-value, confidence interval and every step.

Pearson or Spearman correlation for paired data, with r², a significance test and every step shown.

Find the line of best fit, R², the slope test and predictions with intervals, with every step shown.

Fit a standard (calibration) curve to your lab standards and read off the concentration of unknown samples.

Confidence intervals for a mean or a proportion, from raw data or summary statistics, with the margin of error explained.

Work out how many responses you need for a given confidence level and margin of error.

Turn 0-10 survey responses into a Net Promoter Score, with promoters, passives and detractors broken out.