User:Josefpktd/Statsmodels
 | This is not a Wikipedia article: It is an individual user's work-in-progress page, and may be incomplete and/or unreliable. For guidance on developing this draft, see Wikipedia:So you made a userspace draft. Find sources: Google (books · news · scholar · free images · WP refs) · FENS · JSTOR · TWL |
Statsmodels ...
| Developer(s) | community project, main developers Josef Perktold and Skipper Seabold |
|---|---|
| Stable release | 0.3.1
/ 2011-08-24 |
| Written in | Python |
| Operating system | Cross-platform |
| Type | Statistical analysis |
| License | BSD-new license |
| Website | http://statsmodels.sourceforge.net/ |
scikits.statsmodels is a Python package for statistical analysis and econometrics. It is based on Numpy and Scipy and can be used as a library or for interactive scripting. It covers many basic statistical models for estimation, descriptive statistics and statistical tests. Some basic models that we would expect in a general statistical package are still missing.
The origin of statsmodels is a python package originally written by Jonathan Taylor, which was for some time included in scipy. During Google Summer of Code 2009, Skipper Seabold and Josef Perktold corrected, tested and enhanced stats.models and released it as a new package. Since then, the coverage of statistical and econometric methods has been expanded, the 0.3 release saw the addition of basic time series models, with Wes McKinney as major new contributor [1], [2].
Features
[edit]The latest release includes the following features [3]
- Linear models: Generalized least squares (including weighted least squares and least squares with autoregressive errors), ordinary least squares.
- Generalized linear models with support for all of the one-parameter exponential family distributions.
- Discrete choice models such as Poisson, Probit, Logit, Multinomial Logit based on maximum likelihood estimation.
- Robust linear models with support for several M-estimators.
- Time series analysis: includes descriptive statistics, autoregressive models (AR), autoregressive moving average models (ARMA) and vector-autoregressive models (VAR)
- (Univariate) kernel density estimators
- some datasets that are used for examples and in testing.
- PyDTA: Tools for reading Stata .dta files into numpy arrays.
- statistical tests and regression diagnostic tests
See also
[edit]
References
[edit]- ^ Skipper Seabold: Statsmodels - Statistical Modelling in Python, presentation Scipy 2010 conference
- ^ Wes McKinney: Time series analysis in Python with statsmodels , presentation Scipy 2011 conference
- ^ 0.3.1 release notes
External links
[edit]- documentation on sourceforge
- listing in python package index
- github source code repository
- Skipper Seabold, Josef Perktold: Statsmodels - Statistical Modelling in Python, presentation Scipy 2010 conference
- Wes McKinney, Josef Perktold, Skipper Seabold: Time series analysis in Python with statsmodels, Scipy 2011 conference