Describe procedure

docs/methods.md

@@ -24,6 +24,22 @@ The results can be found at [RQ2 results](results_2.md).
 
 <!-- markdownlint-enable MD013 -->
 
+The procedure is as follows:
+
+- At an NBIS Training Liason meeting, introduce this procedure to the people
+  involved in training, as well as advertise in the relevant communication
+- Collect all questions that teachers think are useful anonymously,
+  creating `Data Set 1`
+- Combine `Data Set 1` with the current NBIS questions. Mix these questions
+  randomly. Per question, as the teachers anonymously for reasons why
+  they would be for or against each question.
+  The collection of reasonings per questions results in `Data Set 2`
+- Per question, and its pros and cons, vote anonymously if the question
+  is useful enough to be included in a survey. Allow 'no', 'yes' and neutral
+
+The end product is the set of questions that had more 'yes' than 'no' votes:
+these are the questions that this NBIS community thinks are useful.
+
 The results can be found at [RQ3 results](results_3.md).
 
 ## RQ4: How different are the newly suggested questions from the current ones?