[SciPy-User] ANN: statsmodels 0.4.3
Fri Jul 6 11:29:11 CDT 2012
We are pleased to announce the release of statsmodels 0.4.3.
statsmodels is a general purpose statistics and econometrics package
written in Python with some optional Cython extensions.
Compared to release 0.4.0, this release contains bug-fixes, code and
documentation cleanup, some enhancements, and improved compatibility
across platforms and compatibility with python 3.2.3, pandas 0.8 and
numpy 1.6.2. More details are below.
We recommend upgrading to 0.4.3
Josef and Skipper
The only change compared to 0.4.2 is for compatibility with python
3.2.3 (changed behavior of 2to3).
This is a bug-fix release that affects mainly Big-Endian machines.
* discrete_model.MNLogit: fix summary method
* examples in documentation: correct file path
* tsa.filters.hp_filter: don't use umfpack on Big-Endian machine (scipy bug)
* the remaining fixes are in the test suite, either precision problems
on some machines or incorrect testing on Big-Endian machines.
This is a backwards compatible (according to our test suite) release with
bug fixes and code cleanup.
* build and distribution fixes
* lowess correct distance calculation
* genmod correction CDFlink derivative
* adfuller _autolag correct calculation of optimal lag
* het_arch, het_lm : fix autolag and store options
* GLSAR: incorrect whitening for lag>1
* add lowess and other functions to api and documentation
* rename lowess module (old import path will be removed at next release)
* new robust sandwich covariance estimators, moved out of sandbox
* compatibility with pandas 0.8
* new plots in statsmodels.graphics
- ABLine plot
- interaction plot
What it is
Statsmodels is a Python package that provides a complement to scipy
for statistical computations including descriptive statistics and
estimation and inference for statistical models.
* linear regression models: Generalized least squares (including
weighted least squares and
least squares with autoregressive errors), ordinary least squares.
* glm: Generalized linear models with support for all of the one-parameter
exponential family distributions.
* discrete: regression with discrete dependent variables, including
Logit, Probit, MNLogit, Poisson, based on maximum likelihood
* rlm: Robust linear models with support for several M-estimators.
* tsa: models for time series analysis
- univariate time series analysis: AR, ARIMA
- vector autoregressive models, VAR and structural VAR
- descriptive statistics and process models for time series analysis
* nonparametric : (Univariate) kernel density estimators
* datasets: Datasets to be distributed and used for examples and in testing.
* stats: a wide range of statistical tests
- diagnostics and specification tests
- goodness-of-fit and normality tests
- functions for multiple testing
- various additional statistical tests
- Tools for reading Stata .dta files into numpy arrays.
- printing table output to ascii, latex, and html
* miscellaneous models
* sandbox: statsmodels contains a sandbox folder with code in various stages of
developement and testing which is not considered "production ready".
This covers among others Mixed (repeated measures) Models, GARCH
models, general method
of moments (GMM) estimators, kernel regression, various extensions
panel data models, generalized additive models and information
Where to get it
The master branch on GitHub is the most up to date code
Source download of release tags are available on GitHub
Binaries and source distributions are available from PyPi
Installation from sources
See INSTALL.txt for requirements or see the documentation
Modified BSD (3-clause)
The official documentation is hosted on SourceForge
We are providing a Windows htmlhelp file (statsmodels.chm) that is now
distributed, available at
It can be copied or moved to the installation directory of
statsmodels (site-packages\statsmodels in a typical installation), and can then
be opened from the python interpreter ::
>>> import statsmodels.api as sm
Discussion and Development
Discussions take place on our mailing list.
We are very interested in feedback about usability and suggestions for
Bug reports can be submitted to the issue tracker at
More information about the SciPy-User