diff --git a/paper.bib b/paper.bib
index a7073d9abbdab8260d88611c79fb883a6e32be77..64dbbd447f5d1c114ec15afeac9f6e1e597ce01a 100755
--- a/paper.bib
+++ b/paper.bib
@@ -102,3 +102,22 @@
   year={1990},
   organization={Wiley Online Library}
 }
+
+@book{hu2006theory,
+  title={The theory of response-adaptive randomization in clinical trials},
+  author={Hu, Feifang and Rosenberger, William F},
+  volume={525},
+  year={2006},
+  publisher={John Wiley \& Sons}
+}
+
+@article{emery1998optimal,
+  title={Optimal experiment design},
+  author={Emery, Ashley F and Nenarokomov, Aleksey V},
+  journal={Measurement Science and Technology},
+  volume={9},
+  number={6},
+  pages={864},
+  year={1998},
+  publisher={IOP Publishing}
+}
diff --git a/paper.md b/paper.md
index abea4ef04456dc5db79797551014d7fc29b0d2b3..8afca0fc5ef91fb92083522442698a9031779deb 100755
--- a/paper.md
+++ b/paper.md
@@ -50,9 +50,9 @@ It easily integrates with the Jupyter notebook environment and provides tools fo
 # Review of adaptive sampling
 
 #### Experiment design uses Bayesian sampling because the computational costs are not a limitation.
-Optimal experiment design (OED) is a field of statistics that minimizes the number of experimental runs needed to estimate specific parameters, and thereby, it reduces the costs of experimentation.
+Optimal experiment design (OED) is a field of statistics that minimizes the number of experimental runs needed to estimate specific parameters, and thereby, it reduces the costs of experimentation.[@emery1998optimal]
 It works with many degrees of freedom and can consider constraints, for example, when the sample space contains settings that are practically infeasible.
-One form of OED is response-adaptive design, which concerns adaptive sampling designs for statistical experiments.
+One form of OED is response-adaptive design[@hu2006theory], which concerns adaptive sampling designs for statistical experiments.
 Here the acquired data (i.e., the observations) are used to adjust the experiment as it is in process.
 In a typical non-adaptive experiment, decisions on how to sample are made and fixed in advance.