diff --git a/README.md b/README.md
index 0431d2e..b686a22 100644
--- a/README.md
+++ b/README.md
@@ -90,12 +90,12 @@ Possible features to pass to `flows2features` include:
 * `IAT`: A flow is represented as a timeseries of inter-arrival times between
   packets, *i.e.*, elapsed time in seconds between any two packets in the flow.
 
+[comment]: <> (I think this is a better way to describe the statistics as it corresponds to how the data appears in the code)
 * `STATS`: A flow is represented as a set of statistical quantities. We choose
   12 of the most common such statistics in the literature: flow duration, number of
-  packets sent per second, number of bytes per second, and various statistics on
-  packet sizes within each flow: mean, standard deviation, inter-quartile range,
-  minimum, and maximum. Finally, the total number of packets and total number
-  of bytes for each flow.
+  packets sent per second, number of bytes per second, mean, standard deviation,
+  first quartile, median, third quartile, minimum, maximum total number of packets,
+  and total number of bytes for each flow.
 
 * `SIZE`: A flow is represented as a timeseries of packet sizes in bytes, with one
   sample per packet.
diff --git a/src/netml/pparser/parser.py b/src/netml/pparser/parser.py
index 663cca2..eb3244f 100644
--- a/src/netml/pparser/parser.py
+++ b/src/netml/pparser/parser.py
@@ -428,8 +428,8 @@ def _get_IAT_SIZE(flows):
 
 
 def _get_STATS(flows):
-    """get basic stats features, which includes duration, pkts_rate, bytes_rate, mean,
-    median, std, q1, q2, q3, min, and max.
+    """get basic stats features, which is: [duration, pkts_rate, bytes_rate, mean,
+    std, q1, median, q3, min, max, num_pkts, and num_bytes].
 
     Parameters
     ----------
@@ -443,7 +443,9 @@ def _get_STATS(flows):
         each value is five-tuple
     """
 
-    features = []
+    features = [] # could potential initialize the list to : 
+    # ["duration", "pkts_rate", "bytes_rate", "mean", "std", "q1", "median", "q3", "min", "max", "num_pkts", "num_bytes"]
+    # so that it is clear to users what each term means
     fids = []
     for fid, pkts in flows:
         sizes = [len(pkt) for pkt in pkts]