7. Statistical Data Analysis

Full list of references in Chapter 7 of the IPython Cookbook, the definitive guide to high-performance scientific computing and data science in Python, by Dr. Cyrille Rossant, Packt Publishing, 400 pages, 2014.

Books

• Python for Data Analysis by Wes McKinney

Packages

• statsmodels.

Frequentism and Bayesanism

• Must-read: a series of posts by Jake Vanderplas.
• Misuses of Frequentist methods.

Hypothesis testing

• Statistical hypothesis testing.
• Credible interval.
• MAP estimation.
• Conjugate prior.
• Prior probability.
• Jeffreys prior.

Correlations

• Correlation does not imply causation.
• Pearson correlation.

Statistical tests

• Chi2 test in SciPy.
• Contingency table.
• Chi square test.

Maximum likelihood

• Maximum likelihood.
• Kolmogorov-Smirnov test.
• Goodness of fit.

Kernel Density Estimation

• Kernel Density Estimation.
• Bias-variance dilemma.
• A post about KDE by Jake Vanderplas.

Bayesian programming

• PyMC model fitting.
• A great PyMC tutorial which we largely took inspiration from.
• A must-read free ebook on the subject, by Cameron Davidson-Pilon, entirely written in the IPython notebook!.
• The Monte-Carlo Markov Chain method.
• The Metropolis-Hastings algorithm.

Linear regression

• Regression analysis.
• Least squares method.

R

• The IPython R magic.
• Rpy2.
• Official introduction to R.
• R tutorial.
• CRAN: Comprehensive R Archive Network, containing many packages for R.
• IPython and R tutorial.