Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

Assuming normal distribution, one SD is equivalent to an effect size of 1.0, which is associated with a gain of 34 percentage points from the average. From a simple regression model, if past achievement, a score from E to A grade, predicted a change of one SD in current achievement, a standardized score (mean of 0), can I infer that an increase of one letter grade in past achievement (e.g., C to B) can result in a 34 percentage gain in current achievement? Or would it be more correct to say "can explain about 34 percentage of the variance"?

Any comments appreciated. Thanks!

share|improve this question
The change in the normal CDF moving from 0 to 1 is .34, but the change associated with moving from 1 to 2 is about .136, so there is no constant change in percentage points associated with a change in zs of 1. Other than this, I don't quite follow your question. – gung Jan 17 '13 at 5:36
It doesn't work the way you seem to think. You're confusing a bunch of different things together. – Glen_b Jan 17 '13 at 6:18

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.