Make the intent-to-treat terminology clearer (#1020)

* Make the intent-to-treat terminology clearer

Signed-off-by: Joon Ro <joon.ro@outlook.com>
Co-authored-by: Keith Battocchi <kbattocchi@gmail.com>

Author: joonro

notebooks/CustomerScenarios/Case Study - Recommendation AB Testing at An Online Travel Company.ipynb

@@ -55,7 +55,7 @@
     "\n",
     "A direct A/B test is infeasible because the website cannot force users to become members. Likewise, the travel company can’t look directly at existing data, comparing members and non-members, because the customers who chose to become members are likely already more engaged than other users. \n",
     "\n",
-    "**Solution:** The company had run an earlier experiment to test the value of a new, faster sign-up process. EconML's IV estimators can exploit this experimental nudge towards membership as an instrument that generates random variation in the likelihood of membership. This is known as an **intent-to-treat** setting: the intention is to give a random group of user the \"treatment\" (access to the easier sign-up process), but not not all users will actually take it. \n",
+    "**Solution:** The company had run an earlier experiment to test the value of a new, faster sign-up process. EconML's IV estimators can exploit this experimental nudge towards membership as an instrument that generates random variation in the likelihood of membership. This is known as an **intent-to-treat** setting: the intention is to give a random group of users the \"treatment\" (membership sign-up), but not all users will actually take it. \n",
     "\n",
     "EconML's `IntentToTreatDRIV` estimator model takes advantage of the fact that not every customer who was offered the easier sign-up became a member to learn the effect of membership rather than the effect of receiving the quick sign-up."
    ]
@@ -772,4 +772,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 2
-}
+}