Statistics (scipy.stats)

In this tutorial, we discuss many, but certainly not all, features of scipy.stats. The intention here is to provide a user with a working knowledge of this package. We refer to the reference manual for further details.

Note: This documentation is work in progress.

Contents

• Probability distributions
  • Continuous Statistical Distributions
  • Discrete Statistical Distributions
  • Getting help
  • Common methods
  • Random number generation
  • Shifting and scaling
  • Shape parameters
  • Freezing a distribution
  • Broadcasting
  • Specific points for discrete distributions
  • Fitting distributions
  • Performance issues and cautionary remarks
  • Remaining issues
  • Building specific distributions
• Universal Non-Uniform Random Number Sampling in SciPy
  • Introduction
  • Basic concepts of the Interface
  • Generators in scipy.stats.sampling
  • References
• Kernel density estimation
  • Univariate estimation
  • Multivariate estimation
• Multiscale Graph Correlation (MGC)
• Quasi-Monte Carlo
  • Calculate the discrepancy
  • Using a QMC engine
  • Making a QMC engine, i.e., subclassing QMCEngine
  • Guidelines on using QMC

Sample statistics and hypothesis tests

• Analysing one sample
  • Descriptive statistics
  • T-test and KS-test
  • Tails of the distribution
  • Special tests for normal distributions
• Comparing two samples
  • Comparing means
  • Kolmogorov-Smirnov test for two samples ks_2samp
• Resampling and Monte Carlo Methods
  • Introduction
  • Resampling and Monte Carlo methods tutorials
• Hypothesis tests
  • Bartlett’s test for equal variances
  • Chi-square test
  • Chi-square test of independence of variables in a contingency table
  • Dunnett’s test
  • Fisher’s exact test
  • Fligner-Killeen test for equality of variance
  • Friedman test for repeated samples
  • Jarque-Bera goodness of fit test
  • Kendall’s tau test
  • Kurtosis test
  • Levene test for equal variances
  • Normal test
  • Odds ratio for a contingency table
  • Shapiro-Wilk test for normality
  • Skewness test
  • Spearman correlation coefficient