Pilot studies are crucial in good study design. A 'pilot study' is a mini version of your full study that is intended to ensure that your main study is maximally successful.
It's incredibly important to get your studies right and piloting your studies is one of the best ways of doing that.
At Positly we recommend you use a sample of 20 or fewer for your first run of an activity to check that the following elements are done well:
You have integrated your study successfully
Your data is showing up as expected
You have targeted the right participants
Your time estimates are accurate
Not only does Positly warn you when you are about to launch a run of your study's activity without piloting, we also provide detailed feedback from participants on the quality of your study as well as statistics around its performance (e.g. average and median time).
If everything works as expected then simply duplicate the pilot study and change the number of desired participants.
In their 2001 paper Edwin & Hundley provide a broad range of additional reasons to first conduct a pilot study:
Develop and test adequacy of research instruments
Assess the feasibility of a (full-scale) study/survey
Design a research protocol
Assess whether the research protocol is realistic and workable
Establish whether the sampling frame and technique are effective
Assess the likely success of proposed recruitment approaches
Identify logistical problems which might occur using proposed methods
Estimate variability in outcomes to help determining sample size
Collect preliminary data
Determine what resources (finance, staff) are needed for a planned study
Assess the proposed data analysis techniques to uncover potential problems
Develop a research question and research plan
Train a researcher in as many elements of the research process as possible
Convince funding bodies that the research team is competent and knowledgeable
Convince funding bodies that the main study is feasible and worth funding
Convince other stakeholders that the main study is worth supporting