I have this medical data:
Every row corresponds to a patient. Different parameters from voice patients have been measured. The first fifteen columns from the data set indicate the fundamental frequency of different vowels. The fundamental frequency is characteristic in each person, so its value varies among different people but it should be the same in different vowels of the same person.
In every row of the dataset, I would like to calculate the variance among the first fifteen columns and eliminate values which are outliers. I would like to replace these values for missing values in these cases.
Is there someone who can help me with that?
Thank you so much!!!