An Algorithm to Improve Test Answer Copying Detection Using the Omega Statistic

The omega (ω) statistic is reputed to be one of the best indices for detecting answer copying on multiple choice tests, but its performance relies on the accurate estimation of copier ability, which is challenging because responses from the copiers may have been contaminated. We propose an algorithm that aims to identify and delete the suspected copied responses through probability sampling and bootstrapping. In doing so, the bias in copier ability estimation will be determined and used to update the ability estimate for calculating the modified omega (ω^m), a new statistic based on the ω. The performance of ω^m and ω were compared in a Monte Carlo simulation study under 40 typical testing conditions (2 test lengths x 4 sample sizes x 5 levels of copying). In almost all conditions, the ω^m had the same or better controlled Type I error and higher power than ω. The increase in power was particularly eminent when the source's estimated ability was higher than the copier and when 20% or 30% of items were copied. These findings support the use of the ω^m as a replacement of ω to detect answer copying in multiple choice exams.     

Are olfactory images sensory in nature?

We investigated the features of olfactory mental images by comparing odour images with perceptual and semantic representations. Participants who were assigned to three groups made similarity judgments about 17 common odours by smelling odours, imagining odours, or on the basis of the meaning of odour source names. In the smelling group, every pair of odours was compared. In the imagining group, imagined odours were compared twice, both before and after associative learning of the odour/name combinations. In the meaning group, the odour source names were compared in terms of general word meanings. Nonmetric multidimensional scaling analysis was applied to each group of similarity data and three-dimensional sensory, mental, and semantic spaces were composed. 17 elements in the mental and semantic spaces were superimposed onto the sensory space by Procrustes rotation. We found that the averaged distances of the 17 elements between the sensory and the mental spaces (either before or after learning) were smaller than those between the sensory and semantic spaces. We suggest that odour images have sensory features, especially after associative learning between perceived odours and their names.     

SOCIOEMOTIONAL AND BEHAVIORAL PROBLEMS IN TODDLERS WITH LANGUAGE DELAY

Toddlers with language delay are at risk for persistent developmental and behavioral difficulties; however, the association between socioemotional/behavior problems and language in young children is not well understood. This study explored socioemotional/behavior problems in a unique sample of toddlers with language delays using a measure developed explicitly for this age group. Toddlers identified by 18 months with receptive and expressive language delay (LD; n = 30) or typical development (TD; n = 61) were evaluated at 18 and 24 months of age using the Infant‐Toddler Social and Emotional Assessment (ITSEA) and the Mullen Scales of Early Learning. Compared to toddlers who had TD, toddlers with LD had significantly more concerning scores at 18 and 24 months on all ITSEA domains. The rate of “clinical concern” on most domains was not high in either group, except that >60% of LD toddlers were in the clinical concern range on the Competence domain. Socioemotional/behavioral problems were dimensionally related to receptive and expressive language, with greater language delay associated with more concerning ITSEA scores. Socioemotional and behavioral problems are related to receptive and expressive language abilities in 18‐ and 24‐month‐olds, indicating the need for screening of both types of concerns in toddlers identified with potential language delays.