Statistical modeling in Python using statsmodels

We will be hosting Skipper Seabold, one of the primary contributors to statsmodels, to talk about statsmodels and its current capabilities and future directions.

ABSTRACT:

Statsmodels (http://statsmodels.sourceforge.net/) is a Python module that allows users to explore data, estimate statistical models, and perform statistical tests. At this meetup, I will give an overview of statsmodels and describe the typical workflow for data exploration and fitting a statistical model. This will include some working with pandas and matplotlib. We will have a closer look at a few popular models including those for linear regression, discrete choice, nonparametrics, and time series analysis as time allows. I will close with a few words about outstanding contributions to look forward to in the next release and how you can get involved.

Interactive IPython notebooks (http://ipython.org/notebook.html) will be made available, so bring your laptop, if you want to follow along. The material is available at http://github.com/jseabold/pydc

BIO:

I am a PhD candidate in economics at American University in DC and have been co-lead developer of statsmodels for 5 years. I have also made a few contributions to other parts of the SciPy stack including numpy, scipy, and pandas.