Tools › Statistics

Statistics

12 tools in 8 sections. Each tool page shows the method with the numbers substituted, its references and the published examples it reproduces.

Descriptive and Outliers 1

  • Data Summary and Outliers Descriptive statistics, normality tests and outlier tests for the columns of a pasted table: n, missing cells, mean, standard deviation, standard error and the 95 % t…

Hypothesis Tests 2

  • Hypothesis Tests The common tests of means, proportions, counts and group differences, each reported the way a statistics section of a report wants it: the hypotheses, the statistic with…
  • A/B Test Analysis of an online controlled experiment with a control and up to four treatments, for conversion rates (visitors and conversions per variant) or a continuous metric…

Regression and Modelling 2

  • Regression and Curve Fitting Fits a model to pasted x–y data by least squares and reports what a statistics package would: the fitted equation written out with its numbers, the coefficients with…
  • Logistic Regression and Classification Fits a binary logistic regression by maximum likelihood to pasted data (response 0/1 or two labels, numeric and categorical predictors with dummy coding) and reports…

Distributions 1

  • Distribution Fitting Fits the normal, lognormal, two-parameter Weibull, exponential and gam⁠ma distributions (and optionally the three-parameter Weibull) to one pasted sample by maximum…

Forecasting 1

  • Forecasting Forecasts a pasted time series by the standard smoothing methods (naive, seasonal naive, moving average, simple exponential smoothing, Holt's linear or damped trend,…

Surveys and Sampling 2

  • Survey Analysis Tabulation of survey responses pasted as respondent rows (a header line of column names, then one line per respondent; optional count and weight columns) or as a ready…
  • Sample Size and Power Sample size, power and detectable effect for the common study designs: one-sample, paired and two-sample means (exact noncentral t, Welch for unequal variances, z when…

Uncertainty and Monte Carlo 2

  • Uncertainty Propagation The uncertainty of a computed result from the uncertainties of its inputs, two ways: the GUM law of propagation of uncertainty (JCGM 100, first-order Taylor expansion…
  • Sensitivity Analysis Which inputs of a model drive its result: a formula in plain syntax is swept over a variable table (base, low, high) for the one-at-a-time swings and the tornado diagram…

Probability 1

  • Kelly Criterion The Kelly criterion for a repeated opportunity with a known payoff: the probability the quoted payoff implies, the edge against your own estimate of the true…