Add examples for 'classic' causal inference datasets

Suggestion by @juanitorduz... Rather than just applying the package to synthetic datasets, it would be good to apply the methods to classic datasets / causal inference problems. This also gives people some faith that the package produces sensible (or at least similar) results as other people's implementations.

Sources

• data from the book Mastering Metrics is available here http://www.masteringmetrics.com/resources/

RDD: drinking example

See https://matheusfacure.github.io/python-causality-handbook/16-Regression-Discontinuity-Design.html#

• Frequentist model
• Bayesian model
• Add reference/details of original study

SC: Proposition 99 example

• grab data
• Frequentist model
• Bayesian model

ITS: Add simple example to match the CausalImpact docs

• Generate similar data
• Add the example to its_pymc.ipynb
• Add the example to its_skl.ipynb

DiD: Add the 'bank failure' dataset + analyses

• add data
• add Bayesian analysis
  • add case when we have multiple measurements over time (see #76)
• add Frequentist analysis

This will almost certainly require code changes. At the moment there is a hard wired constraint that there is just a single pre and post observation

Start by reviewing the existing RDD and DiD analyses, the Mastering Metrics data, and the linked causal inference examples. Then inspect its_pymc.ipynb and its_skl.ipynb, along with the hard-wired single pre/post observation constraint. Done means adding the requested datasets and frequentist or Bayesian analyses, documenting the RDD study, and completing the ITS notebook examples.