I want to thank all of those who responded with information regarding Excel's
calculation of skewness.
I have now centered on a method not used by Excel.
Calculating the second moment of the data as:
second moment = sum(X-XBar)^2 and the
third moment = sum(X-XBar)^3 and the
fourth moment = Sum(X-XBar)^4
population sd.dev = sqr ( second/n)
sample sd.dev = sqr ( second/(n-1) )
I now find that different individuals calculate the skewness as
skewness = third moment / ((n-1)*(sample st.dev)^3)
skewness = (third moment/n) / (sample st.dev^3)
skewness = (third moment/n) / (pop st.dev^3)
skewness = (third moment/n) / second moment^3
skewness = third moment/n / (second moment/n)^3
Since my mind seems to be "spinning" from all the replies, I would like to
know which of the above formulas (if any) are the most accepted.
Thanks in advance for any help you can give.
Dr. Robert C. Knodt
1414 37th Street
Bellingham, WA 98229
[log in to unmask]
"Some books are to be tasted, others to be swallowed and some few to be
chewed and digested." -- Francis Bacon
|