Monday, February 17, 2014

Just a bit about Z-scores

Remember the normal distribution is symmetrical. It's a bell shaped curve. The standard normal distribution has mean 0 and standard deviation of 1. 

A "Z-score" is a certain number of standard deviations from the mean than an data value is.  Each Z-score has a corresponding probability that an observed value is less than that many standard deviations from the mean.

For example

Z-score of 1.28..  P(observed value  is less than 1.28) = .90 (that is obtained from a standard normal chart)

Z-score of -1.28  P(observed value is less than -1.28) = .10

notice there is .10 to the right of 1.28 and .10 to the left of -1.28. That makes sense since the distribution is symmetrical.

No comments:

Post a Comment