tladeras’s avatartladeras’s Twitter Archive—№ 2,165

    1. …in reply to @ibddoctor
      @ibddoctor @CMastication A checklist does exist to some extent, but it's different for different data types. There are some obvious ones for categorical data, like looking for structural zeros, but in reality EDA is part of a conversation with the data collectors.
      Permalink On twitter.com Twitter logo tladeras’s avatar Mood +2 🙂
  1. …in reply to @tladeras
    @ibddoctor @CMastication The other thing to keep in mind is that some machine learning methods (such as Random Forests) require the training data to have balanced outcomes, so methods of choice also figures into a good EDA. #rstats
    On twitter.com Twitter logo tladeras’s avatar ♻️ 2 Retweets ❤️ 1 Favorite Mood +4 🙂