Between Dec 19, 2024 and Jan 2, 2025, datasets can be submitted to DRUM but will not be processed until after the break. Staff will not be available to answer email during this period, and will not be able to provide DOIs until after Jan 2. If you are in need of a DOI during this period, consider Dryad or OpenICPSR. Submission responses to the UDC may also be delayed during this time.

Browsing by Author "Divgi, D. R."

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Estimating reliabilities of computerized adaptive tests
    (1989) Divgi, D. R.
    This paper presents two methods for estimating the reliability of a computerized adaptive test (CAT) without using item response theory. The required data consist of CAT and paper-pencil (PP) scores from identical or equivalent samples, and scores for all examinees on one or more covariates. Multiple R's and communalities are used to compute the ratio of CAT and PP reliabilities. When combined with the PP reliability calculated by a conventional procedure, these ratios yield estimates of CAT reliability. Index terms: computerized adaptive testing, item response theory, predictive validity, reliability, tailored testing.
  • Thumbnail Image
    Item
    Group dependence of some reliability indices for mastery tests
    (1980) Divgi, D. R.
    Reliability indices for mastery tests depend not only on true-score variance but also on mean and cutoff scores. This dependence was examined in the case of three decision-theoretic indices: (1) the coefficient of agreement; (2) kappa; and (3) the proportion of correct decisions. The binomial error model was assumed, with a two-parameter beta distribution for true scores. The reliability indices were computed at five values of the mean, four values of KR-21, and four cutoff scores. Results show that the dependence of kappa on mean and cutoff scores is opposite to that of the proportion of correct decisions, which is linearly related to average threshold loss. Moreover, kappa can be very small when most examinees are classified correctly. Thus, objections against the classical reliability coefficient apply even more strongly to kappa.
  • Thumbnail Image
    Item
    A minimum chi-square method for developing a common metric in item response theory
    (1985) Divgi, D. R.
    The θ scale in item response theory has arbitrary unit and origin. When a group of items is calibrated twice, estimates from one calibration must be transformed to the metric of the other. A new method is presented for doing so. It is simpler than an earlier method based on test characteristic curves, and makes more complete use of available information.
  • Thumbnail Image
    Item
    Model-free evaluation of equating and scaling
    (1981) Divgi, D. R.
    Standardized tests are equated and scaled in order that scores on different tests can be compared. If one test yields higher expected scaled scores than another, the scale is biased against those who take the latter test. The amount of bias, defined as the difference between expected values, depends on ability. This paper presents two methods for estimating this relationship and the bias in the scale, using a predictor as the measure of ability. The resulting evaluation is absolute in the sense that the scale is judged according to its own properties and not by comparison with an arbitrarily designated criterion scale. Moreover, there is no need to assume a particular theoretical model to be correct. An application of the methods showed that the Rasch model is not suitable for vertical equating of multiple-choice tests.