Originally posted by SG4247
View Post
The SD tends to get smaller as the sample size grows.
Klem's 80 and 108 data points is unusually large making his data more meaningful than most of our tests.
As he indicates, one is free to draw his own inferences from the data. Eighty data points for one set and 108 for the other seriously ups the temptation to declare the difference in average meaningful.
On the other hand, some hard line statisticians might say that the less than one standard deviation between the two means we cannot tell the difference.
What the data does say, however, is that we have a lot of confidence that the less troublesome neck tension only method gives at least as good accuracy as does crimping.
Comment