Multiple choice questions are traditionally expensive to produce. Recent advances in large language models (LLMs) have led to fine-tuned LLMs that generate questions competitive with human-authored questions. However, the relative capabilities of ChatGPT-family models have not yet been established for this task. We present a carefully-controlled…

The multiple-choice (MC) item format has been widely used in educational assessments across diverse content domains. MC items purportedly allow for collecting richer diagnostic information. The effectiveness and economy of administering MC items may have further contributed to their popularity not just in educational assessment. The MC item format…

Exams constitute the predominant form of summative assessment in undergraduate biology education, with the assumption that exam performance should reflect student conceptual understanding. Previous work highlights multiple examples in which students can answer exam problems correctly without the corresponding conceptual understanding. This…

A latent class model for handling the items in Birenbaum and Tatsuoka's study is described. A method to derive the optimal scoring rule when multiple choice test items are used is illustrated. Remedial training begins after a determination is made as to which of several erroneous algorithms is being used. (Author/DWH)

Twenty-four students who scored 650 or more on the Scholastic Aptitude Test Mathematics test (SAT-M) were asked to think aloud while solving 13 mathematics items in either multiple-choice or free-response format. Strategies students used to solve the items were classified as either algorithmic or insightful. Data analyses indicated that items in…

In this report, selection theory is used as a theoretical framework from which mathematical algorithms for tailored testing are derived. The process of tailored, or adaptive, testing is presented as analogous to personnel selection and rejection on a series of continuous variables that are related to ability. Proceeding from a single common-factor…

The aim of this study was to show that the superiority of corrected-for-guessing scores over number right scores as true score estimates depends on the ability of examinees to recognize situations where they can eliminate one or more alternatives as incorrect and to omit items where they would only be guessing randomly. Previous investigations…

The study was designed to examine the similarity of response options generated by different item writers using a systematic approach to item writing. The similarity of response options to student responses for the same item stems presented in an open-ended format was also examined. A non-systematic (subject matter expertise) approach and a…

On well-constructed multiple-choice tests, the most serious threat to measurement is not variation in item discrimination, but the guessing behavior that may be adopted by some students. Ways of ameliorating the effects of guessing are discussed, especially for problems in latent trait models. A new item response model, including an item parameter…

An earlier study was extended and replicated to examine the feasibility of generating multiple-choice test questions by transforming sentences from prose instructional material. In the first study, a computer-based algorithm was used to analyze prose subject matter and to identify high-information words. Sentences containing selected words were…

The results of this study are consistent with a two-stage model of learning chemistry, a multi-dimensional subject, in which students accumulate knowledge in stage one, and then restructure their knowledge in stage two. When cognitive, metacognitive and achievement variables were subjected to a predictive discriminant analysis (PDA) procedure,…

The feasibility of generating multiple-choice test questions by transforming sentences from prose instructional materials was examined. A computer-based algorithm was used to analyze prose subject matter and to identify high-information words. Sentences containing selected words were then transformed into multiple-choice items by four writers who…

Several measurement theorists have convincingly argued that methods of writing test questions, particularly for criterion-referenced tests, should be based on operationally defined rules. This study was designed to examine and further refine a method for objectively generating multiple-choice questions for prose instructional materials. Important…

The technology of transforming sentences from prose instruction into test questions was examined by comparing two methods of selecting sentences (keyword vs. rare singleton), two types of question words (nouns vs. adjectives), and two foil construction methods (writer's choice vs. algorithmic). Four item writers created items using each…

Twenty multiple-choice vocabulary items and 20 free-response vocabulary items were administered to 660 college students. The free-response items consisted of the stem words of the multiple-choice items. Testees were asked to respond to the free-response items with synonyms. A computer algorithm was developed to transform the numerous…