Grading on a curve
|This article does not cite any references or sources. (August 2012)|
||This article may contain original research. (March 2010)|
In education, grading on a curve (also known as curved grading, bell curving, or simply curving) is a statistical method of assigning grades designed to yield a pre-determined distribution of grades among the students in a class. The term "curve" refers to the bell curve, the graphical representation of the probability density of the normal distribution (also called the Gaussian distribution), but this method of grading does not necessarily make use of any specific frequency distribution such as the bell-shaped normal distribution.
One method of applying a curve uses these three steps: First, numeric scores (or possibly scores on a sufficiently fine-grained ordinal scale) are assigned to the students. The actual values are unimportant as long as the ordering of the scores corresponds to the ordering of how good the students are. In the second step these scores are converted to percentiles (or some other system of quantiles). Finally, the percentile values are transformed to grades according to a division of the percentile scale into intervals, where the interval width of each grade indicates the desired relative frequency for that grade.
For example, if there are three grades, A, B and C, where A is reserved for the top 10% of students, B for the next 20%, and C for the remaining 70%, then scores in the percentile interval from 0% to 70% get grade C, scores from 71% to 90% get grade B, and scores from 91% to 100% get grade A.
The grading method can thus be tuned to determine the frequency distribution of the grades in advance, and if the intervals are already fixed at the beginning of a course, then so is the number of students who will receive each grade.