diff --git a/arviz/plots/hdiplot.py b/arviz/plots/hdiplot.py
index 7b75370175..9595e865b0 100644
--- a/arviz/plots/hdiplot.py
+++ b/arviz/plots/hdiplot.py
@@ -71,7 +71,9 @@ def plot_hdi(
     backend : {"matplotlib","bokeh"}, optional
         Select plotting backend.
     backend_kwargs : bool, optional
-        These are kwargs specific to the backend being used. Passed to ::``
+        These are kwargs specific to the backend being used, passed to
+        :meth:`mpl:matplotlib.axes.Axes.plot` or
+        :meth:`bokeh:bokeh.plotting.figure.Figure.patch`.
     show : bool, optional
         Call backend show function.
 
diff --git a/arviz/stats/stats.py b/arviz/stats/stats.py
index 8ee4b41f39..3cf12af256 100644
--- a/arviz/stats/stats.py
+++ b/arviz/stats/stats.py
@@ -156,6 +156,14 @@ def compare(
     --------
     loo : Compute the Pareto Smoothed importance sampling Leave One Out cross-validation.
     waic : Compute the widely applicable information criterion.
+    plot_compare : Summary plot for model comparison.
+
+    References
+    ----------
+    .. [1] Vehtari, A., Gelman, A. & Gabry, J. Practical Bayesian model evaluation using
+        leave-one-out cross-validation and WAIC. Stat Comput 27, 1413–1432 (2017)
+        see https://doi.org/10.1007/s11222-016-9696-4
+
     """
     names = list(dataset_dict.keys())
     if scale is not None: