Thank you for contributing this code! I am wondering why in v6.4 you chose to leave the 'has_children' binary variable as non-categorical? I understand that the function's default behavior is to interpret a numeric, binary feature such as 'has_children' as non-categorical, but in the context of an analysis would you recommend specifying a variable of that type as 'categorical'? Does it not make a difference because the dissimilarity calculated will be the same either way (1 if the values don't match, 0 if they do)?
Thank you!
Rebecca
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi Marcelo,
Thank you for contributing this code! I am wondering why in v6.4 you chose to leave the 'has_children' binary variable as non-categorical? I understand that the function's default behavior is to interpret a numeric, binary feature such as 'has_children' as non-categorical, but in the context of an analysis would you recommend specifying a variable of that type as 'categorical'? Does it not make a difference because the dissimilarity calculated will be the same either way (1 if the values don't match, 0 if they do)?
Thank you!
Rebecca