I'm doing a PhD in the social sciences and want to use an observational method to analyse audio recordings of social work conversations. I will be using an established behavioural coding manual (the Motivational Interviewing Skills Code 2.5) to assign behavioural codes to the interaction. The problem I have is that I need a way of demonstrating that my coding is reliable. Typically, on studies I have worked on in the past, there would be a small sample of recordings that would be re-coded by at least one other person to establish inter-rater reliability. As a sole researcher, I cannot do this.

Is there a way around this issue?

  • 1
    Please explain why you are a sole researcher. You do have an advisor, don't you? – scaaahu Feb 3 '18 at 13:39
  • It seems inherently impossible to say anything about inter-rater reliability when you only have data from one rater. So, I would say you should start looking into ways to get another rater. Look for a collaborator, or funding to hire someone. Or else accept that you won't be able to establish this. – Nate Eldredge Feb 3 '18 at 17:53

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.