Monday, February 10: using 1.5*IQR method
finding a "standard deviation" (what is it and why do we care?)
data used:
(1.5 IQR) mlb.teams=c(228, 216, 165, 150, 148, 140, 127, 119, 117, 115, 114, 114, 107, 104, 90, 89, 89, 83, 81, 80, 78, 76, 73, 72, 72, 67, 60, 58, 36, 22)
(1.5 IQR) age of mundt from first day
sd (5 data points from puzzle book)
Tuesday, February 11: using 2 sd method...which data is best, and which data is different?
for each question, unless otherwise stated:
A. make a quick boxplot.
B. determine which method to use for outliers.
C. find possible outliers. (list these)
D. explain which ones to remove.
test data from here.
p91, 4: tornadoes. A, B, C, D
p92, 15: population growth A, B, C, D. (treat the groups as separate).
note. when comparing two sets of data and looking for outliers, we should use the same method on both, whether or not they appear to need different ones. consider your data carefully here, and pick which one you think is a better choice...
p93, 18: how tall answer the actual question in the book.
p98, 43: gas usage A, B, C, D. Yes, this is a little cruel.
p70, 35: MPG A, B, C, D (treat the groups as separate)
Wednesday, February 12: Data set with outliers
Thursday, February 13: Data Set removing outliers
Friday, February 14: Data Set removing outliers