For those of you who don't know, I've written some code that can calculate statistics based on a collection of typings. For example, if you've been typed as an introvert 10/12 times the code can tell you the probability of getting a result that strong or stronger by random chance. In the case of the prior example the probability would be .0386. The code works for dichotomies (two groups of eight types) as well as any other symmetric grouping of the 16 types.
I'd like to start a statistical typology project in order to formulate type definitions from the ground up. The way it could work is that once I have a representative of each type, I could break people up into groups (E vs. I for example) and observe the traits that members of the same have in common and compare and contrast the qualities between groups.
Thus far, I've been generating spreadsheets for people that display all of the typings of themselves they've received from different sources.
Here's an example spreadsheet: https://docs.google.com/spreadsheets/d/1HtNnW9bY6d6SNQ9oN1iCzkb1y-ufWngYpJEvJ-uvQCo/edit?usp=sharing
If you're interested in the project and/or would like a spreadsheet, please let me know. Also, feel free to voice any questions or concerns in a comment below.