Partial-Credit Scoring Methods for Multiple-Choice Tests

Frary, Robert B.

doi:10.1207/s15324818ame0201_5

Cited by 46 publications

(47 citation statements)

References 86 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, Coombs (1953), Coombs, Milholland, and Womer (1956) had examinees specify all alternatives per MC question that they believed were incorrect. Relatedly, Dressel and Schmid (1953) had examinees mark as many of the alternatives as necessary to include the correct answers (see Frary, 1989 for a review). This research, however, was primarily concerned with the psychometric properties of different types of MC tests.…”

Section: Overconfidence and Underconfidencementioning

confidence: 99%

Regulating accuracy on university tests with the plurality option

Higham

2013

Learning and Instruction

View full text Add to dashboard Cite

Section: Overconfidence and Underconfidencementioning

confidence: 99%

Regulating accuracy on university tests with the plurality option

Higham

2013

Learning and Instruction

View full text Add to dashboard Cite

“…Table 2 shows the codes corresponding to the mathematical contents and processes. In the scoring method, each item was awarded equal points (equal scoring) (Frary, 1989;Masters, 1988). Each item is worth 1 point, and in scoring the item total is divided by the number of answers required for its content/process.…”

Section: Discussionmentioning

confidence: 99%

Development of a Preschool Teachers’ Pedagogical Content Knowledge Scale regarding Mathematics

Dağlı

Dağlıoğlu

Atalmis

2020

International Journal of Assessment Tools in Education

View full text Add to dashboard Cite

This study aimed to develop a measurement tool in order to assess preschool teachers' pedagogical content knowledge regarding mathematics. The study was based on 300 preschool teachers working in formal independent kindergartens and nursery classes of primary/secondary schools in the Kahramanmaraş Province of Turkey. Among the participants, 150 were chosen for pre-application and 150 for the main application. The scale consists of five different case studies and a total of 35 items, including dialogues that focus on mathematical content and processes reflected in children's talk during their play. In calculating the reliability of the scale, Cronbach Alpha was found to be .95 for the pre-application and .96 for the main application. For the validity of the scale, exploratory and confirmatory factor analyses were performed. The exploratory factor analysis results revealed the scale to be a single-factor structure. When the factor loads of each relevant item were examined, no item was found to exist with a factor load value of less than .30. After confirmatory factor analysis was performed, the model fit indices of CFI, TLI, RMSEA, and SRMR values were found to be .91, .91, .06 and .06, respectively. These results show the model to be reliable to an acceptable level. Based on the findings, it could be concluded that the scale is an instrument that produces valid and reliable measures, and that it can be used in order to determine the preschool teachers' pedagogical content knowledge regarding mathematics.

show abstract

“…Each of the GUESS questions also asked students to categorize how confident they were in their answers, with a spectrum ranging from Very Confident to Complete Guess, similar to schemes applied in other multiple-choice diagnostics [11]. In order to correlate confidence with correctness we developed a new marking scheme as shown in Table II.…”

Section: Confidence Levelmentioning

confidence: 99%

Development of a General Undergraduate Estimation Skills Survey (GUESS)

Burke¹,

Heiner²

2014

2013 Physics Education Research Conference Proceedings

View full text Add to dashboard Cite

Abstract:We describe the development of a ten-question diagnostic designed to characterize the estimation skills of undergraduate students in science and engineering. In order to establish a baseline and look for possible gains in skill level we have developed a multiple-choice assessment designed to probe student ability and confidence in estimating physical quantities such as mass, size, and time. The diagnostic was administered as a pre-test and post-test to a class of first-year engineers and given to a set of experts to establish its discriminatory power. Item response curves were then used to evaluate each question and multiple-choice answers. The results show that the assessment has the resolution to distinguish between student and expert scores, and that the distribution of expert confidences is qualitatively different than the students in both pre-test and post-test.

show abstract

Partial-Credit Scoring Methods for Multiple-Choice Tests

Cited by 46 publications

References 86 publications

Regulating accuracy on university tests with the plurality option

Regulating accuracy on university tests with the plurality option

Development of a Preschool Teachers’ Pedagogical Content Knowledge Scale regarding Mathematics

Development of a General Undergraduate Estimation Skills Survey (GUESS)

Contact Info

Product

Resources

About