1. What is Cohen’s Kappa? Why is it a better estimate of inter-judge agreement t

1. What is Cohen’s Kappa? Why is it a better estimate of inter-judge agreement than a simple percentage of agreement measure? 2. Can a research laboratory (where participants would typically participate in psychological experiments) be an appropriate setting for naturalistic observation? In what situations might this be reasonable? Why would a researcher want to use a laboratory as the preferred setting to observe “natural” behavior? What would be an example of two studies where the only difference between them is that one used naturalistic observation to assess the dependent measure, and the other used an “unnatural” measure (e.g., written self-report) to assess the same dependent construct? Could you think of a situation in which participants are knowingly interacting with the experimenter in a laboratory setting, but the data being collected are still considered “natural behaviors?”

You may also like