diff --git a/R/man/performance_metrics.Rd b/R/man/performance_metrics.Rd
index 435ffcd..8bd8ed9 100644
--- a/R/man/performance_metrics.Rd
+++ b/R/man/performance_metrics.Rd
@@ -13,7 +13,7 @@ performance_metrics(df, metrics = NULL, rolling_window = 0.1)
 will use c('mse', 'rmse', 'mae', 'mape', 'coverage').}
 
 \item{rolling_window}{Proportion of data to use in each rolling window for
-computing the metrics. Should be in [0, 1].}
+computing the metrics. Should be in [0, 1] to average.}
 }
 \value{
 A dataframe with a column for each metric, and column 'horizon'.
@@ -32,14 +32,18 @@ A subset of these can be specified by passing a list of names as the
 `metrics` argument.
 
 Metrics are calculated over a rolling window of cross validation
-predictions, after sorting by horizon. The size of that window (number of
-simulated forecast points) is determined by the rolling_window argument,
-which specifies a proportion of simulated forecast points to include in
-each window. rolling_window=0 will compute it separately for each simulated
-forecast point (i.e., 'mse' will actually be squared error with no mean).
-The default of rolling_window=0.1 will use 10% of the rows in df in each
-window. rolling_window=1 will compute the metric across all simulated
-forecast points. The results are set to the right edge of the window.
+predictions, after sorting by horizon. Averaging is first done within each
+value of the horizon, and then across horizons as needed to reach the
+window size. The size of that window (number of simulated forecast points)
+is determined by the rolling_window argument, which specifies a proportion
+of simulated forecast points to include in each window. rolling_window=0
+will compute it separately for each horizon. The default of
+rolling_window=0.1 will use 10% of the rows in df in each window.
+rolling_window=1 will compute the metric across all simulated forecast
+points. The results are set to the right edge of the window.
+
+If rolling_window < 0, then metrics are computed at each datapoint with no
+averaging (i.e., 'mse' will actually be squared error with no mean).
 
 The output is a dataframe containing column 'horizon' along with columns
 for each of the metrics computed.
diff --git a/R/man/rolling_mean.Rd b/R/man/rolling_mean.Rd
deleted file mode 100644
index b422503..0000000
--- a/R/man/rolling_mean.Rd
+++ /dev/null
@@ -1,21 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/diagnostics.R
-\name{rolling_mean}
-\alias{rolling_mean}
-\title{Compute a rolling mean of x}
-\usage{
-rolling_mean(x, w)
-}
-\arguments{
-\item{x}{Array.}
-
-\item{w}{Integer window size (number of elements).}
-}
-\value{
-Rolling mean of x with window size w.
-}
-\description{
-Right-aligned. Padded with NAs on the front so the output is the same
-size as x.
-}
-\keyword{internal}
diff --git a/R/man/rolling_mean_by_h.Rd b/R/man/rolling_mean_by_h.Rd
new file mode 100644
index 0000000..4215139
--- /dev/null
+++ b/R/man/rolling_mean_by_h.Rd
@@ -0,0 +1,25 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/diagnostics.R
+\name{rolling_mean_by_h}
+\alias{rolling_mean_by_h}
+\title{Compute a rolling mean of x, after first aggregating by h}
+\usage{
+rolling_mean_by_h(x, h, w, name)
+}
+\arguments{
+\item{x}{Array.}
+
+\item{h}{Array of horizon for each value in x.}
+
+\item{w}{Integer window size (number of elements).}
+
+\item{name}{String name for metric in result dataframe.}
+}
+\value{
+Dataframe with columns horizon and name, the rolling mean of x.
+}
+\description{
+Right-aligned. Computes a single mean for each unique value of h. Each mean
+is over at least w samples.
+}
+\keyword{internal}