What is negative or corrective scoring?

Corrective scoring attempts to eliminate the effects of guessing through penalising incorrect responses or applying a general formula to all scores. For example, in order to subtract marks for incorrect answers, the following scoring system might be used:

+1 for the correct answer
-1 for an incorrect answer
0 for no answer.

Alternatively, questions could be scored as normal, and a formula for guess correction could be applied at the end. A standard formula is

SCORE = Right – Wrong/n-1.
Right = the number of correct answers.
Wrong = the number of incorrect answers.
N = total number of alternatives per item (including the correct answer)

So, if a student answered 35 questions correctly on a 50-question test in which each item had 4 alternatives, the raw score after correction would be calculated as follows:

Score = 35 – 15/(4-1)
Score = 30.

However, corrective (or negative) scoring is a contentious issue, and some experts feel that corrective scoring is unnecessary if the assessment has been well-constructed with good coverage of course content and a sufficient number of questions of varying difficulty. If you do decide to use corrective scoring, it is important to alert students to this, so that they can alter their test-taking strategies accordingly.

For a discussion of the perceived merits and disadvantages of corrective scoring, read the series of messages entitled "negative marks" located in the computer-assisted-assessment mailbase list.

Also of interest would be Martin Bush's paper: Alternative Marking Schemes for On-Line Multiple Choice Tests (provided with permission)

See also the section on guessing.