The Number of Options in a Multiple-Choice Test Item and the Psychometric Characteristics.

Abstract

Traditionally, multiple-choice test items(MCIs) have been written with four or five response options, and measurement textbooks have recommended this. However, in the recent past, many studies have theoretically and empirically found that three options are just as effective, and may be the optimal number of options for MCIs. This study investigated and compared the effect of two  number of options (noOPT) formats, five options versus three options, on test and item psychometric characteristics. A Mathematics Achievement Test (MAT) was administered twice, first with five options, and then with three options per item.  The study used a sample of one hundred and fifty-nine (159)Primary Six pupils in state government-owned schools in Bayelsa State, South-South Nigeria. The study revealed that noOPT significantly affected mean test scores, mean test difficulty and test discrimination indices, but not internal consistency reliability coefficient. Generally the findings provided more evidence to support the use of three option.

Keywords: number of options (noOPT), psychometric characteristics, item difficulty index, item discrimination index, test reliability