diff --git a/README.adoc b/README.adoc
index 6076e76..370a175 100644
--- a/README.adoc
+++ b/README.adoc
@@ -1,6 +1,6 @@
 = Monster Hunter scripts
 
-This repository contains scripts for calculating probalities and expected
+This repository contains scripts for calculating probabilities and expected
 values for rewards and carves in Monster Hunter games.
 
 == Dependencies
@@ -20,7 +20,12 @@ quest rewards, carves, capture, and shiny drops. An expected value of
 8% means that on average, you would get 8 of the item from 100 quests. Note
 that this is different from the probability of getting at least one, which
 will be lower and is a pain to calculate when there can be different number
-of rewards.
+of rewards. It also takes into account Carving and Luck skills. The main
+value shown assumes no food or armor skills. For Carves the extra values
+listed on the right are for felyne skills Carver Lo, Carver Hi, then armor
+skills Carving Master and Carving God. For quest rewards the extra values
+are for food/armor skills Lucky Cat/Good Luck and Ultra Lucky Cat/Great Luck.
+The totals at the end list the range from no skills to the best skill.
 
 For more manual calculations, mhprob.py can be used directly. The quest
 "Plain Dangerous" in 3U has 2 fixed rewards in A, one in B. Diablos hardhorns
@@ -31,3 +36,12 @@ have a 5% chance:
 
 For great luck, you would replace 69 with 90. The output includes both expected
 value and probability of getting at least one.
+
+== Math
+
+Monster hunter rewards can be modeled using the Binomial distribution. The most
+popular method I've seen online is to calculate the probability of getting at
+least one. I prefer to use expected (mean) value, which is easier to calculate
+and provides a more intuitive quantity. For
+more information see the
+link:http://en.wikipedia.org/wiki/Binomial_distribution#Mean_and_variance[Wikipedia article].