Observer agreement for timed-event sequential data: A comparison of time-based and event-based algorithms

Observer agreement is often regarded as the sine qua non of observational research. Cohen's kappa is a widely used index and is appropriate when discrete entities-such as a turn-of-talk or a demarcated time interval-are presented to pairs of observers to code. kappa-like statistics and agreement matrices are also used for the timed-event sequential data produced when observers first segment and then code events detected in the stream of behavior, noting onset and offset times. Such kappa s are of two kinds: time-based and event-based. Available for download is a computer program (OASTES; Observer Agreement for Simulated Timed Event Sequences) that simulates the coding of observers of a stated accuracy and then computes agreement statistics for two time-based kappa s (with and without tolerance) and three event-based kappa s (one implemented in The Observer, one in INTERACT, and one in GSEQ). On the basis of simulation results presented here, and due to the somewhat different information provided by each, the reporting of both a time-based and an event-based kappa is recommended.