diff --git a/arch/univariate/base.py b/arch/univariate/base.py
index e3fdf10d06..cf2506078d 100644
--- a/arch/univariate/base.py
+++ b/arch/univariate/base.py
@@ -1414,6 +1414,8 @@ def scale(self):
 
     def conf_int(self, alpha=0.05):
         """
+        Parameter confidence intervals
+
         Parameters
         ----------
         alpha : float, optional
@@ -1575,10 +1577,12 @@ def rsquared(self):
 
     @cached_property
     def fit_start(self):
+        """Start of sample used to estimate parameters"""
         return self._fit_indices[0]
 
     @cached_property
     def fit_stop(self):
+        """End of sample used to estimate parameters"""
         return self._fit_indices[1]
 
     @cached_property
diff --git a/arch/univariate/distribution.py b/arch/univariate/distribution.py
index 5f05beabbd..9f3012be36 100644
--- a/arch/univariate/distribution.py
+++ b/arch/univariate/distribution.py
@@ -417,11 +417,11 @@ def ppf(self, pits, parameters=None):
 
 class SkewStudent(Distribution):
     r"""
-    Standardized Skewed Student's [1]_ distribution for use with ARCH models
+    Standardized Skewed Student's distribution for use with ARCH models
 
     Notes
     -----
-    The Standardized Skewed Student's distribution takes two parameters,
+    The Standardized Skewed Student's distribution ([1]_) takes two parameters,
     :math:`\eta` and :math:`\lambda`. :math:`\eta` controls the tail shape
     and is similar to the shape parameter in a Standardized Student's t.
     :math:`\lambda` controls the skewness. When :math:`\lambda=0` the
diff --git a/doc/source/changes/4.0.txt b/doc/source/changes/4.0.txt
index 3a4d16e22d..2905f1711e 100644
--- a/doc/source/changes/4.0.txt
+++ b/doc/source/changes/4.0.txt
@@ -2,8 +2,9 @@
 Version 4
 =========
 
-Since 4.10
-==========
+Release 4.11
+============
+- Added :func:`~arch.univariate.base.ARCHModelResult.std_resid` (:issue:`326`).
 - Error if inputs are not ndarrays, DataFrames or Series (:issue:`315`).
 - Added a check that the covariance is non-zero when using "studentized" confidence intervals.
   If the function bootstrapped produces statistics with 0 variance, it is not possible to