I need help computing an #interraterReliability score for a dataset of ratings that had more than one response format and that has some missing data.
Here's a reproducible toy example with more info: "How to clean redundancies and missings in rater dataset and then compute reliability (e.g., Cohen's kappa) using R?"
How to clean redundancies and missings in rater dataset and then compute reliability (e.g., Cohen's kappa) using R?
I've nearly 10,000 rows of numeric and text ratings about various items from up to 5 raters. I need to 1. Clean the data (particularly redundancies and empty ratings) 2. Compute inter-rater reliabi...