Upload a CSV, pick one numeric column, and get every plausible distribution fitted by maximum likelihood, ranked by AIC, tested for goodness of fit, and drawn over your own histogram with a Q-Q plot. Free.
Free analyses run on up to 10,000 rows. Larger files are randomly sampled to that size — sign up to analyze your full dataset.
Fitting candidate distributions by maximum likelihood...
Sent to — ranked candidate fits with parameters and AIC, goodness-of-fit tests, the winner drawn over your histogram, a Q-Q plot, R code, and AI insights.
Analyze another fileEach candidate distribution is fitted to your column by maximum likelihood — closed-form estimators for the normal, lognormal, exponential, uniform and poisson, and a two-pass Nelder-Mead search for the gamma, weibull and negative binomial. Candidates whose support does not contain your data are skipped with a stated reason, and a search that does not converge is reported as a failure rather than as a fit with whatever parameters it stopped on. The fits are ranked by AIC (with BIC alongside) within family, then tested: Kolmogorov-Smirnov plus a directly computed Anderson-Darling statistic for continuous candidates, a Pearson chi-square on merged integer cells for discrete ones. The winner is drawn over the observed histogram bin by bin and plotted as a Q-Q plot against the observed quantiles.
Use it when you need a named distribution with parameters — to feed a simulation, size a queue or a buffer, set a reliability or service-level target, or decide whether counts are overdispersed.
Not for asking whether a column is normal enough for a t-test or whether it contains outliers — the normality and outlier screening tool answers that. Not for data that mixes distinct regimes, and not for a time series with trend or seasonality, where the shape of the residuals rather than the raw column is the thing to fit.
Built for: Analysts, operations researchers, actuaries, reliability and capacity engineers, and anyone choosing an input distribution for a model
Typical data source: Any spreadsheet or CSV with one numeric column of measurements, durations, sizes, or counts
One numeric column of measurements, durations, amounts, or counts. For example, API response times:
Minimum 20 rows · Best with 200-20,000 values in a single numeric column
Standard-library analysis: what distribution does my data follow? Map one numeric column and every plausible candidate shape is fitted to it by maximum likelihood — normal, lognormal, gamma, weibull, exponential and uniform, plus poisson and negative binomial when the values are counts. The candidates are ranked by AIC and BIC, each is put to a goodness-of-fit test, the winner is drawn over the observed histogram bin by bin, and a Q-Q plot shows where the fit holds and where it breaks. Candidates whose support does not contain your data are skipped with a stated reason rather than fitted to nonsense, and a search that fails to converge is reported as a failure rather than as a fit.
Every fitted candidate ranked by AIC with its parameters, so you can see both the winner and how close the runners-up came.
The winning distribution drawn over your actual histogram, bin by bin — where the bars match, the shape describes your data.
Observed quantiles against predicted ones; departures from the diagonal show exactly where the fit stops working.
Formal tests for each candidate, read alongside what your sample size does to their power.
How the fits were estimated, which candidates were skipped and why, and the limits of what a fitted distribution can claim.
Plain-English interpretation — what the numbers mean, what's significant, and what to do next.
What distribution should I put into my model?
Map the column you want to simulate. Every applicable candidate is fitted by maximum likelihood and ranked by AIC, so you get named parameters you can feed straight into a simulation — and an honest statement of how much better the winner really is than the runner-up.
See our FAQ for details on pricing, data privacy, and how the analysis works. Every report includes a Methodology section showing the statistical test, assumptions checked, and diagnostics run.
Run any analysis on your own data — validated R analyses, interactive reports, AI insights, and PDF export.
Try Free — No Credit CardTell us what went wrong, in your own words. We capture the page you're on automatically, so no need to describe where you are.