New method detects outliers in leukemia data, improving regression accuracy.
The study looked at how to find outliers in data from children with leukemia in Mosul City. Traditional methods using mean and standard deviation can be thrown off by outliers, but using median and mean absolute deviation about the median is more reliable. Testing this new method on leukemia patient data showed it worked better than the old way. So, using median and mean absolute deviation can help make linear regression models fit better.
