Measurement ScaleBefore planning a questionnaire or survey, test developers identify the scale of measurement of their data to make sure that they are in alignment with the objectives of the study. Th

Item Facility Index and Item Discrimination PSY3700 Multimedia Assessment and Psychometrics ©20 16 South University 2 Item Facility Index and Item Discrimination Item Facility Index and Discrimination Item Facility Index Item facility index is the ratio of wrong responses to the total number of responses (Rust & Golombok , 2009). Item difficulty is assessed by the percentage of examinees who respond correctly to each item.

This percentage is then compared against the optimal difficulty level, usually expressed as an index score halfway between the actual percentage of corr ect responses and the level of success that could be expected due to chance alone. For example, a multiple -choice test with five possible responses would be expected to have a correct response chance rate of 20%. That is, the chance of getting the item cor rect would be 1 in 5 or 0.20 (20%). Using the strategy outlined, the maximum of 100% (expressed as 1) success level plus the chance performance level of 0.20, the total divided by 2 (the halfway point), renders an item difficulty index score of .60. Items that fall within the range of difficulty from 0.30 to 0.70 tend to be the best ones for revealing an array of performance differences across participants (Kaplan & Saccuzzo, 2013). Thus, a multiple -choice test with five items would have an index score of 0 .60, which falls in the acceptable range. Item Discrimination Item discrimination is a type of item analysis, an umbrella term for a group of statistical procedures used to sort test items so that the best -fit items can be retained in the overall pool of items (Gregory, 2013). Each item on a test or survey should effectively separate high and low scorers. To do that, test items should be neither too easy nor too difficult. The item discrimination index is used to compare the performances of examinees in t he upper and lower ranges of the distribution of scores. Ideally, the best test item is passed by the higher scorers and failed by the low scorers (Gregory, 2013). To conduct an item discrimination index for test items, a correlation between the item scor es and the test scores is calculated. This correlation can reveal whether test items are related to the total test score and whether they are contributing to the overall test. Also, the items should correlate with each other. The higher the correlation, th e better. The threshold correlation for making this determination is 0.2 or higher. If the correlation coefficient is lower, the items should be removed or rewritten as they are contributing little to the variance of the test (Rust & Golombok, 2009). An important benefit of using the item discrimination index is to ascertain the likelihood that more examinees falling in the lower range of scores will get the item correct than in the higher range and vice - versa. If this occurs, the item is believed to have poor discrimination because it fails to support the assumption that examinees in the higher range will be more likely to endorse the item correctly than their lower counterparts. Likewise, it violates the assumption that those in the lower range will be m ore likely to give the wrong answer. Hence, the item does not make a valuable contribution to the goal of the test which is to reveal individual differences across test takers (Gregory, 2013). PSY3700 Multimedia Assessment and Psychometrics ©20 16 South University 3 Item Facility Index and Item Discrimination Item Facility Index and Discrimination References Gregory, R. (2013). Psychological testing: History, principles, and applications (7th ed.). Boston, MA: Pearson. Kaplan, R., & Saccuzzo, D. (2013). Psychological testing: Principles, applications, & issues (8th ed.). Belmont, CA: Wadsworth. Rust, J., & Golombok, S. (2009). Modern psychometrics: The science of psychological assessment (3rd ed.). New York, NY: Taylor & Francis. © 201 6 South University