Practical Validity
The practical validity of g as a predictor of educational, economic, and social outcomes is more far-ranging and universal than that of any other known psychological variable. The validity of g is greater the greater the complexity of the task.
A test's practical validity is measured by its correlation with performance on some criterion external to the test, such as college grade-point average, or a rating of job performance. The correlation between test scores and a measure of some criterion is called the validity coefficient. One way to interpret a validity coefficient is to square it to obtain the variance accounted by the test. For example, a validity coefficient of .30 corresponds to 9 percent of variance explained. This approach has, however, been criticized as misleading and uninformative, and several alternatives have been proposed. One arguably more interpretable approach is to look at the percentage of test takers in each test score quintile who meet some agreed-upon standard of success. For example, if the correlation between test scores and performance is .30, the expectation is that 67 percent of those in the top quintile will be above-average performers, compared to 33 percent of those in the bottom quintile.
Read more about this topic: g Factor (psychometrics)
Famous quotes containing the words practical and/or validity:
“The ordinary literary man, even though he be an eminent historian, is ill-fitted to be a mentor in affairs of government. For ... things are for the most part very simple in books, and in practical life very complex.”
—Woodrow Wilson (1856–1924)
“Once one is caught up into the material world not one person in ten thousand finds the time to form literary taste, to examine the validity of philosophic concepts for himself, or to form what, for lack of a better phrase, I might call the wise and tragic sense of life.”
—F. Scott Fitzgerald (1896–1940)