update with Ben's requests

Signed-off-by: Nathaniel <NathanielF@users.noreply.github.com>

Author: NathanielF

causalpy/pymc_experiments.py

@@ -1802,6 +1802,7 @@ def weighted_percentile(self, data, weights, perc):
         """
         perc : percentile in [0-1]!
         """
+        assert 0 <= perc <= 1
         ix = np.argsort(data)
         data = data[ix]  # sort data
         weights = weights[ix]  # sort weights
@@ -1811,6 +1812,13 @@ def weighted_percentile(self, data, weights, perc):
         return np.interp(perc, cdf, data)
 
     def plot_balance_ecdf(self, covariate, idata=None, weighting_scheme=None):
+        """
+        Plotting function takes a single covariate and shows the
+        differences in the ECDF between the treatment and control
+        groups before and after weighting. It provides a visual
+        check on the balance achieved by using the different weighting
+        schemes
+        """
         if idata is None:
             idata = self.idata
         if weighting_scheme is None:

causalpy/pymc_models.py

@@ -414,7 +414,8 @@ def build_model(self, X, t, coords):
 
     def fit(self, X, t, coords):
         """Draw samples from posterior, prior predictive, and posterior predictive
-        distributions.
+        distributions. We overwrite the base method because the base method assumes
+        a variable y and we use t to indicate the treatment variable here.
         """
         self.build_model(X, t, coords)
         with self:

docs/source/_static/classes.png

@@ -82,7 +82,8 @@ @incollection{forde2024nonparam
   editor    = {PyMC Team},
   booktitle = {PyMC examples},
   doi       = {10.5281/zenodo.5654871},
-  year = {2024}
+  year      = {2024}
+}
 
 @book{shadish_cook_cambell_2002,
   title={Experimental and quasi-experimental designs for generalized causal inference},