0 courses selected
Flow sampling: an essential way to learn what people think of your service at the very best time - just after they use it (13 Feb 17)
This step by step guide shows how to gather the views of people when they visit your offices
An essential pre-condition of obtaining reliable information from surveys is to select a properly representative sample of the survey population or the group of people who are about to be studied.
The most reliable way of doing this is by drawing a random (or probability) sample. Here every member of the survey population has an equal chance of being selected to take part in a study. This way there would be no built in bias, which would make it more likely that some people would be selected than others.
But what happens when you want to survey people as they visit an area office or at the point at which they receive a service? Here you don’t have the luxury of being able to select every nth person on a list.
You could leave out cards on counters to be filled in, or hand out questionnaires whenever staff have time to spare, but these approaches will not usually result in reliable results.
The solution is to choose an appropriate sample of the flow of people using a service during a given period of time e.g. every tenth visitor to an office over the period of one month.
However, there are several problems associated with flow sampling:
Variations in the flow of visitors over time
The sample must be drawn over a period which takes into account variations in the number and type of user of a service e.g. some local offices may be much busier on some days than others or different kinds of people may visit at different times. It is also important to avoid untypical weeks such as public holiday periods.
The best way to deal with this is to
Like to read more or make a comment? Log in or register below
Why not join the discussion!
Or even better still offer your own advice and tell us about things that others can learn from.
We moderate comments lightly so bear with us and we'll get your thoughts listed as soon as we can.
You must be logged in to post comments.
Not registered yet? Simply fill in the box below.
