For discussions related to modeling, machine learning and deep learning. Related packages include caret, modelr, yardstick, rsample, parsnip, tensorflow, keras, cloudml, and tfestimators.
Dear community,
I have a dataset (catergorical, yes or no) with about 1000 objects, with a distribution of 60% yes. I analysed 30 objects I took from their dataset and their representation of yes versus no 80% vs 20%. Is there an R package that tests the overrepresentation of objects in this model? I was thinking os something taking 30 objects randomly ( for example, 1000 times) and then testing how likely it is to get the representation I obtained experimentally. Thanks in advance for your help. I hope my question is clear...