Another way to look at outliers is by first standardizing them to a normal distribution with a mean of 0 and standard deviation of 1. Using standard normal form is convenient, since the properties of the distribution never change, and some critical cut-off points can be committed to memory. For example, for a standard normal distribution, quartile 1 is always at -.67 and quartile 3 is always at +.67, so it is easy to compute the interquartile range to memory, which is 1.34. Using the interquartile range rule to identify outliers means that we will take 1.5 times this amount to derive the value of 2.01, so we will be considering any data point above .67+2.01=2.68, or -.67-2.01=-2.68, to be a possible outlier. This is ...