Statistics & Data Science calculators

52 live statistics & data science calculators inside Science & Research on The Online Calculator 24. Every engine shows its formula, the worked steps behind the default figures, and the standard or dataset the method comes from.

Live Statistics & Data Science tools

• A/B Test & Statistical Sample Size Calculator — Dual-proportion Z-test engine for digital product A/B testing, CRO, and clinical trials: compute required sample size per variant, experiment duration, and minimum detectable effect (MDE).
• Statistical Power Calculator — The probability a test detects an effect that is genuinely there — a function of effect size, sample, and the significance bar.
• Effect Size (Cohen's d) Calculator — The mean difference expressed in standard deviations — effect magnitude without the units, comparable across any measurement scale.
• Effect Size (r) Calculator — What a correlation coefficient means as an effect: r² of shared variance, its t-test, and the Fisher-z confidence interval around it.
• Effect Size (f) Calculator — The effect size for ANOVA: standard-deviation-of-means scaled by residual SD, converted here from the more commonly reported η².
• Confidence Interval (Mean) Calculator — The Confidence Interval for Mean Calculator works out confidence interval from your sample mean, standard deviation and sample size. It also reports sample mean, margin of error and standard error, with the formula and every step shown.
• Confidence Interval (Proportion) Calculator — The interval around an observed percentage — poll numbers, conversion rates, defect shares — from normal-approximation sampling theory.
• Margin of Error Calculator — The Margin of Error (MOE) Calculator works out margin of error from your sample size, sample percentage and total population. It also reports confidence interval, standard error and sample size, with the formula and every step shown.
• Z-Score Calculator — The Z-Score & Normal Probability Calculator works out standard score from your raw value, mean and standard deviation. It also reports percentile rank ), right tail probability p and two-tailed p-value, with the formula and every step shown.
• T-Score Calculator — The mean-difference signal measured against noise, calibrated for small samples by the t-distribution’s heavier tails.
• Chi-Square Calculator — The per-cell engine of the independence/goodness-of-fit test: squared deviation scaled by expected count.
• F-Statistic Calculator — Variance between groups divided by variance within them — the ANOVA ratio that asks whether group means part further apart than their own scatter.
• ANOVA Calculator — Planning an analysis of variance: given groups, per-group n and an expected η², whether the omnibus F test will actually see the effect.
• Two-Way ANOVA Calculator — The share one quantity represents of another — the core reading behind two-way anova — with a second value folded in for direct comparison.
• MANOVA Calculator — The share one quantity represents of another — the core reading behind manova — with a second value folded in for direct comparison.
• Repeated Measures Calculator — The blend for repeated measures: weighted mean with the weights shown explicitly, so nobody has to guess whether line one counted.
• Within-Subject Calculator — The share one quantity represents of another — the core reading behind within-subject — with a second value folded in for direct comparison.
• Between-Subject Calculator — The share one quantity represents of another — the core reading behind between-subject — with a second value folded in for direct comparison.
• Mixed Design Calculator — The share one quantity represents of another — the core reading behind mixed design — with a second value folded in for direct comparison.
• Post-Hoc Test Calculator — The share one quantity represents of another — the core reading behind post-hoc test — with a second value folded in for direct comparison.
• Bonferroni Correction Calculator — You ran many tests on one dataset, so the chance of at least one false positive inflates; Bonferroni divides the significance budget by the number of tests.
• Holm–Bonferroni Correction Calculator — Holm sorts your p-values and applies shrinking multipliers (m, m−1, …) — uniformly more powerful than Bonferroni with the same family-wise error guarantee.
• Benjamini–Hochberg FDR Calculator — When screening hundreds of hypotheses, BH caps the share of false findings among everything you call significant, instead of capping the chance of any single false positive.
• Type I Error Rate Calculator — Type I error is rejecting a true null — crying wolf. α is the rate you accept when the null is in fact true.
• Type II Error Rate Calculator — Type II error is failing to reject a false null — letting a real effect walk. β is its rate; power is 1 − β.
• P-Value Interpretation Calculator — A p-value is the probability of data this extreme if the null were true — not the probability the finding is false. This calculator converts it with a prior.
• Bayes Factor Calculator — The Bayes factor compares how predicted the observed data are by two competing hypotheses — evidence independent of any significance threshold.
• Bayesian Credible Interval Calculator — Tempo arithmetic for bayesian credible interval: millisecond beat and bar lengths plus the real-time span of any number of beats.
• Prior Distribution Calculator — The share one quantity represents of another — the core reading behind prior distribution — with a second value folded in for direct comparison.
• Posterior Distribution Calculator — The share one quantity represents of another — the core reading behind posterior distribution — with a second value folded in for direct comparison.
• Likelihood Ratio Calculator — The share one quantity represents of another — the core reading behind likelihood ratio — with a second value folded in for direct comparison.
• Sensitivity Calculator — Sensitivity is the share of genuinely positive cases the test catches — its ability to avoid false reassurance.
• Specificity Calculator — Specificity is the share of truly-negative people the test correctly clears — its ability to avoid false alarms.
• Positive Predictive Value Calculator — PPV answers the question patients actually ask: given a positive result, what is the chance I truly have it?.
• Negative Predictive Value Calculator — NPV is the probability that a person with a negative result truly does not have the condition — the reassurance number.
• ROC AUC Calculator — The share one quantity represents of another — the core reading behind roc auc — with a second value folded in for direct comparison.
• Cohen's Kappa Calculator — Kappa scores inter-rater reliability after subtracting the agreement random raters would hit by luck.
• Intraclass Correlation Calculator — The share one quantity represents of another — the core reading behind intraclass correlation — with a second value folded in for direct comparison.
• Cronbach's Alpha Calculator — Cronbach’s alpha estimates how consistently a set of items measures the same underlying construct.
• McDonald's Omega Calculator — The share one quantity represents of another — the core reading behind mcdonald's omega — with a second value folded in for direct comparison.
• Factor Loading Calculator — The blend for factor loading: weighted mean with the weights shown explicitly, so nobody has to guess whether line one counted.
• Eigenvalue Calculator — The share one quantity represents of another — the core reading behind eigenvalue — with a second value folded in for direct comparison.
• Explained Variance Calculator — The share one quantity represents of another — the core reading behind explained variance — with a second value folded in for direct comparison.
• Principal Component Calculator — The share one quantity represents of another — the core reading behind principal component — with a second value folded in for direct comparison.
• Cluster Silhouette Calculator — The share one quantity represents of another — the core reading behind cluster silhouette — with a second value folded in for direct comparison.
• Elbow Method Calculator — The share one quantity represents of another — the core reading behind elbow method — with a second value folded in for direct comparison.
• K-Means Convergence Calculator — The share one quantity represents of another — the core reading behind k-means convergence — with a second value folded in for direct comparison.
• Hierarchical Cluster Calculator — The share one quantity represents of another — the core reading behind hierarchical cluster — with a second value folded in for direct comparison.
• DBSCAN Epsilon Calculator — Activity × factor arithmetic for dbscan epsilon: the kg CO₂e total, the offset price tag, and the scale marker (trees) that makes tonnes tangible.
• Regression Coefficient Calculator — The share one quantity represents of another — the core reading behind regression coefficient — with a second value folded in for direct comparison.
• Multiple R-Squared Calculator — The share one quantity represents of another — the core reading behind multiple r-squared — with a second value folded in for direct comparison.
• Adjusted R-Squared Calculator — The share one quantity represents of another — the core reading behind adjusted r-squared — with a second value folded in for direct comparison.

Reading a Statistics & Data Science result

A number on its own is the weakest thing a calculator can give you, so these tools pair each output with the comparison that gives it meaning: the gap to a target, the band the value falls in, or what a realistic swing in one input does to the answer. When a figure looks wrong, that is usually the fastest place to check — re-run it with one input moved and see whether the change lines up with the formula printed above the result.

Related sub-topics in Science & Research

• Physics Laboratory — 51 live tools.
• Chemistry Lab — 50 live tools.