Zoltan B. answered 03/20/14
Tutor
4.7
(114)
Researcher whose work has been presented at Ivy League venues
The standard normal distribution is also called the bell curve because of its shape. The idea is that you have the mean (which has a Z value of 0) and then three standard deviations to the right of the mean and three to the left. It looks like this:
http://www.regentsprep.org/Regents/math/algtrig/ATS2/normal67.gif
The Z score represents standard deviations: Imagine for the moment that you have this data set. [2, 4, 6]. The mean is (2+4+6)/3 or 4. The standard deviation is 2.
A bell curve would have the following values:
z of 0, or the mean=4.
1z=4+2
2z=4+2+2
3z=4+2+2+2
The same calculations apply to negative Z scores so -2z=4-2-2=0.
Z scores can be converted into percentiles. This is a good table:
http://assets.openstudy.com/updates/attachments/5141b7e4e4b0d5d99f3e827d-directrix-1363263083814-birdzscore.jpg
Now, you want the Z value associated with the 97th percentile. In other words you want the Z value closest to 0.97 on the chart. I'm going with 0.9699 (only .0001 off). That has a Z value of 1.88. That's how you convert. So a Z value of 1.88 is at the 96.99 percentile, which is the closest to the number you need to find.