Assessment terms beginning with I

This is a measurement glossary, not a general HR glossary. It covers the vocabulary that appears the moment you open a score report or challenge a vendor's claim — reliability, validity, norms, cut scores, item statistics and fairness analysis — because that is the vocabulary buyers are handed without explanation and the one that decides whether a number can carry a decision.

• Incremental validity

  Also called Incremental prediction, Added validity

  Incremental validity is the additional predictive accuracy an assessment contributes beyond the procedures already in use. It is the only validity figure that answers a purchasing question: a test that predicts performance well but measures the same thing as the interview you already run adds nothing to the decision, however strong its own coefficient.

  Read the full entry

• Interrater reliability

  Also called Inter-rater reliability, Rater agreement

  Interrater reliability is the degree to which two independent raters judging the same person or the same piece of work arrive at the same score. It sets a ceiling on everything built from those ratings: a criterion no two raters agree on cannot be predicted well by any test, however good the test is.

  Read the full entry

• Item analysis

  Also called Classical item statistics

  Item analysis is the statistical review of how each question in a test performed. Two numbers carry most of it: difficulty, the proportion of candidates who answered correctly, and discrimination, the correlation between getting that question right and scoring well on the test overall. Weak items are revised or retired on this evidence.

  Read the full entry

• Item response theory

  Also called IRT, Latent trait theory

  Item response theory models the probability of a given answer as a function of the candidate's underlying ability and the question's own parameters — usually difficulty, discrimination and, for multiple choice, guessing. Because ability and item difficulty are placed on the same scale, scores from different sets of questions remain comparable.

  Read the full entry