Good question. "cpk, Why are you taking only 8th value & not average of 8th & 9th? There are 16 observations, L(50)=(16+1)*50/100=8.5 So shouldn’t we take average of 8 & 9 which will be – 8th= 20 + 10/6 = 21.67
8 is the middle number on 16. you would take 8.5 – when 17 is the size. so you would do the calculation above when the size was 17.
But when there are 16 observations, then we compute the median using average of 8th & 9th? isn’t?
I didn’t understand this question. What if the distribution was like this (or very close to this) 0,0,10,10,10,10,10,21,29,30,30,30,30,40,40,40 (sum = 340, average = 21.25, median = 25)