rguo12 / research_in_python

This repository includes all the data analyses I carry out for my general exams reading, Spring 2015

Statistical Research In Python

In the Spring of 2015, I committed to carrying out my general exams in a way that made a contribution to public knowledge. I'm summarizing every book and article I read on AcaWiki (the full list is here).

This repository on Github includes all the data analyses I carry out in the quantitative section on "Statistical Methods for Computational Social Science."

--J. Nathan Matias, PhD Student, MIT Media Lab & Center for Civic Media

Code Examples

To execute these code examples, you will need to have jupyter notebook 3.0, along with standard Python data/stats libraries pandas, statsmodels, numpy, seaborn, and scipy.

Basic Analysis in Python

• Downloading Sample R Datasets and Doing Descriptive Statistics

Regression Models for Categorical and Limited Dependent Variables.

Long, J. Scott. 1997. Regression Models for Categorical and Limited Dependent Variables. 1 edition. Thousand Oaks: SAGE Publications, Inc.

Methods Matter: Improving causal Inference in Educational and Social Science Research

Murnane, Richard J., and John B. Willett. 2010. Methods Matter: Improving causal Inference in Educational and Social Science Research, Oxford University Press.

• Regression Discontinuity Analysis
• Instrumental Variables Estimation in Python
• Using Instrumental-Variables Estimation to Recover the Treatment Effect in Quasi-Experiments

Applied Longitudinal Data Analysis

Singer, Judith D., and John B. Willett. 2003. Applied Longitudinal Data Analysis: Modeling Change and Event Occurrence. Oxford university press.

• Multi-Level Models (Fixed and Random Effects)
• Fitting Discrete Time Hazard/Survival Models