skewness
n. the degree to which a set of scores, measurements, or other numbers are asymmetrically distributed around a central point. A normal frequency distribution of data is shaped like a bell, with equal values for each of its three indices of central tendencyβthe mean, the median, and the mode. Approximately 68% of the scores lie within 1 standard deviation of the mean and approximately 95% of the scores lie within 2 standard deviations of the mean. When a distribution has a few extreme scores toward the high end relative to the low end (e.g., when a test is difficult and few test takers do well), it has a positive skew (or is positively skewed), such that the mean is greater than the mode. When a distribution has a few extreme scores toward the low end relative to the high end (e.g., when a test is easy and most test takers do well), it has a negative skew (or is negatively
skewed).