Can i use ordered quantile normalization, to normalize a dataset for univariate ACE model? I think not, but if i could, that would be really good.
Thanks in advance!
Can i use ordered quantile normalization, to normalize a dataset for univariate ACE model? I think not, but if i could, that would be really good.
Thanks in advance!
Printer-friendly version
I guess you are referring to OQN. This seems like it should be fine. Why do you think it wouldn't work?
I am just not sure how to interpret the results, if i do an ace on the transformed data. I am not sure the results could be directly applied to the untransformed dataset. As i see (also not sure, i probably should study the field a lot more, but i have to finish this particular study today today) every non-linear transformation of the original data can modify how the ML function will fit on the raw data, in a way so its derivatives will also change, and that way the results. But for log or sqrt its easy to see what the transformation really means, and how it changes the data. But i am no expert at all, and also i think even if it changes the results somewhat, it wouldnt be really significant. I just never used OQN, and not that familiar with the techique, so i've had concerns.