A correlation of -1.67 between two scores shows that the research must be a mistake.

The internal validity of a study of students who had the lowest achievement test scores could be threatened by statistical regression.

If the standard deviation on an intelligence test (mean 100) is 10, then about two-thirds of the midrange scores fall between 90 and 110.

If the level of significance is set at .01, the results of the study would be due to chance rather than treatment less than one time out of one hundred.

Standard Scores or Standardized Scores:

These scores express a person's distance from the mean, in terms of standard deviation of the distribution. They are continuos and have equality of units and allow for comparison between individuals.

Standard Scores:

1. Z-Scores
2. T-Scores

Correlation Coefficient:

A statistical measure of relationship does not show causation. It shows if two sets of data are related. The Pearson r is the most commonly used tool to predict the correlation, on interval and ratio data. Correlation coefficient can range from +1 (positive correlation) to -1 (negative correlation). When a correlation exists, by knowing one score you can predict another score most of the time.

Regression:

A major purpose of testing is prediction. Regression is the primary statistical tool for this purpose. Regression analysis provides an equation that describes the relationship between the two variables.