I have one column contains a lot of Missing Values , around 80% of the values are missing. Is there a good way to compensate those missing values based on the valid 20% while maintaining the integrity of the data?
If you had 20% missing then you probably could do something but I do not think you can replace 80% of the missing data out of 20%. Even if you do it somehow the reliability of those data would be really questionable. overall what you get from those 20% are representative of those 20% and not the missing values.
Thanks for both of you for your replies .
As for Pouya question regarding the cause for the missing values , I'm afraid that I myself don't know what are the causes since I was asked to find suitable solution to tackle this issue.
And for Amin's suggestion . I think as u said , it will damage the integrity of the data and the result will be questionable. I think we will try to deal with only the available 20% and produce better results.
Thanks a lot for both of u
- Badges
- Science topic
- Similar topics
- Analytical Chemistry
- Column