In the many training courses I run about extracting and narrating the story hidden in data, insights emerge as a crucial focal point. One striking observation I’ve made is that there’s no universal definition of ‘insight’.
We create standards, codes, checklists, and best practices to separate good research from poor research. However, unless we recognise the differences between the theoretical underpinnings of different research methods, we will likely do a bad job.
When I tackle a project for non-trivial cases, I tend to choose one of these, balancing the strength of the technique with the time it takes. But, with all the fuss about Large Language Models, I wondered if I could leverage multiple techniques on a single project. Here is a simple experiment using ChatGPT4.