new Difference In Differences notebook (pymc-devs#424)

* initial commit of DiD notebook * add most of the modelling and inference content * add the counterfactual inference stuff * god damn pre-commit checks * fix spelling in myst.md * more spelling changes * why is this so difficult? * still?! * fixes to model description * fix typo in code block * remove unused imports + better data plot * data plot just right now * fix typo: region -> reason * addressing feedback * "differences in differences" -> "difference in differences" * add "panel data" to tags * proper use of rng according to style guide * add link to the PR in the authors section * add example, more links, more references to papers * fix missing reference and malformed link * minor changes in explanation of DiD schematic
Sriatunckfbs · Oct 6, 2022 · ba37aaa · ba37aaa
1 parent b84c42e
commit ba37aaa
Show file tree

Hide file tree

Showing 5 changed files with 1,763 additions and 0 deletions.
diff --git a/examples/causal_inference/DAG_difference_in_differences.png b/examples/causal_inference/DAG_difference_in_differences.png
diff --git a/examples/causal_inference/difference_in_differences.ipynb b/examples/causal_inference/difference_in_differences.ipynb
diff --git a/examples/causal_inference/make_DAG_difference_in_differences.py b/examples/causal_inference/make_DAG_difference_in_differences.py
@@ -0,0 +1,17 @@
+import daft
+import matplotlib.pyplot as plt
+
+plt.rcParams.update({"text.usetex": True})
+
+pgm = daft.PGM()
+pgm.add_node("treat", "treatment", 0, 0.5, aspect=1.8)
+pgm.add_node("y", "outcome", 0, -0.5, aspect=1.5)
+pgm.add_node("t", "time", -1, 0, aspect=1.2)
+pgm.add_node("g", "group", 1, 0, aspect=1.2)
+pgm.add_edge("t", "y")
+pgm.add_edge("g", "y")
+pgm.add_edge("t", "treat")
+pgm.add_edge("g", "treat")
+pgm.add_edge("treat", "y")
+pgm.render()
+pgm.savefig("DAG_difference_in_differences.png", dpi=500)
diff --git a/examples/references.bib b/examples/references.bib
@@ -47,6 +47,16 @@ @book{berry1996statistics
   year          = {1996},
   publisher     = {Duxbury Press}
 }
+@article{bertrand2004much,
+  title         = {How much should we trust differences-in-differences estimates?},
+  author        = {Bertrand, Marianne and Duflo, Esther and Mullainathan, Sendhil},
+  journal       = {The Quarterly journal of economics},
+  volume        = {119},
+  number        = {1},
+  pages         = {249--275},
+  year          = {2004},
+  publisher     = {MIT Press}
+}
 @book{breen1996regression,
   title         = {Regression models: Censored, sample selected, or truncated data},
   author        = {Breen, Richard and others},
@@ -78,6 +88,12 @@ @article{caprani2010gev
   url           = {https://www.sciencedirect.com/science/article/pii/S016747300900071X},
   author        = {Colin C. Caprani and Eugene J. OBrien}
 }
+@misc{card1993minimum,
+  title         = {Minimum wages and employment: A case study of the fast food industry in New Jersey and Pennsylvania},
+  author        = {Card, David and Krueger, Alan B},
+  year          = {1993},
+  publisher     = {National Bureau of Economic Research Cambridge, Mass., USA}
+}
 @misc{carpenter2016hierarchical,
   title         = {Hierarchical partial pooling for repeated binary trials},
   author        = {Carpenter, Bob and Gabry, J and Goodrich, B},
@@ -114,6 +130,12 @@ @article{collinswilson2019
   issn          = {2050-084X},
   publisher     = {eLife Sciences Publications, Ltd}
 }
+@book{cunningham2021causal,
+  title         = {Causal inference: The Mixtape},
+  author        = {Cunningham, Scott},
+  year          = {2021},
+  publisher     = {Yale University Press}
+}
 @article{efron1975data,
   title         = {Data analysis using Stein's estimator and its generalizations},
   author        = {Efron, Bradley and Morris, Carl},
@@ -240,6 +262,12 @@ @misc{hogg2010data
   archiveprefix = {arXiv},
   primaryclass  = {astro-ph.IM}
 }
+@book{huntington2021effect,
+  title         = {The effect: An introduction to research design and causality},
+  author        = {Huntington-Klein, Nick},
+  year          = {2021},
+  publisher     = {Chapman and Hall/CRC}
+}
 @article{iacobucci2016mean,
   title         = {Mean centering helps alleviate ``micro'' but not ``macro'' multicollinearity},
   author        = {Iacobucci, Dawn and Schneider, Matthew J and Popovich, Deidre L and Bakamitsos, Georgios A},
@@ -530,6 +558,15 @@ @book{wilkinson2005grammar
   issn          = {1431-8784},
   isbn          = {978-0-387-24544-7}
 }
+@article{wing2018designing,
+  title         = {Designing difference in difference studies: best practices for public health policy research},
+  author        = {Wing, Coady and Simon, Kosali and Bello-Gomez, Ricardo A},
+  journal       = {Annu Rev Public Health},
+  volume        = {39},
+  number        = {1},
+  pages         = {453--469},
+  year          = {2018}
+}
 @article{Yao_2018,
   doi           = {10.1214/17-ba1091},
   url           = {https://doi.org/10.1214\%2F17-ba1091},