This study validated and evaluated the feasibility of a web-based electronic behavior assessment system, ‘eBA’, designed to facilitate collaboration between caregivers and service providers (behavior analysts) in conducting indirect functional behavior assessment (FBA). In Phase 1, the content and the web architecture of the eBA were validated and refined through a formative evaluation by five behavior analysts. In Phase 2, the eBA system was pilot tested with 10 service providers and 10 caregivers using a post-test only control group design to examine the efficiency and quality of the system and identify the levels of satisfaction with the system by the service providers and caregivers. The results indicated that the eBA system components were appropriate to conduct indirect FBA and useful for use by caregivers and service providers collaboratively, gathered quality information, and showed higher levels of caregiver and service provider satisfaction, compared to traditional paper-pencil format of assessment.

The credibility of unsupervised exams, one of the biggest challenges of e-learning, is currently maintained by proctoring. However, little has been done to determine whether expensive and inconvenient proctoring is necessary. The purpose of this quantitative study was to determine whether the use of security mechanisms, based on the taxonomy of cheating reduction techniques rooted in the fraud triangle theory, can be an effective alternative to proctoring. A quasi-experimental 1 group sequential design was used to answer the research questions whether the format, proctored versus unproctored, order in which the exams are administered, course delivery mode, and instructor make a difference in student performance. The archival scores of 850 Californian community college students on 2 sets of equivalent proctored and unproctored web-based exams in face-to-face, hybrid, and online introductory statistics courses taught by 7 instructors were compared. The format effect was tested with repeated-measures ANOVA; the order, course delivery mode and instructor effects were tested with mixed ANOVA. No significant difference in scores in Set 1, and significantly lower scores on unproctored exams in Set 2 indicated that the used security mechanisms allowed for maintaining the credibility of the exams without proctoring. There was no significant difference in scores across the course delivery modes in both sets and instructors in Set 2, but significant order effect was observed. Further research on order effect was recommended. With the use of the utilized security mechanisms education will get an inexpensive and convenient way to increase the credibility of unsupervised web-based exams, and the society will gain more online college graduates with credentials that reflect their knowledge.

Yes / Assessment of children for school readiness is a crucial process that requires extensive effort to select the sequence of tests most appropriate for the particular case to be investigated. Indeed, the success of the assessment depends highly on the diversity, flexibility, and comprehensiveness of the tests available and the ability of the applied system to decide on the specific sequence of tests to be utilized for each child based on his/her skills which should be discovered dynam- ically as the assessment progresses. Given the huge search space for the test cases to be utilized in the assessment process, it is preferred to apply an optimization technique capable of finding an appropriate test case that better fits the skills of a given child. It was decided to use a genetic algorithm (GA)-based approach for the optimization process. Any other optimization technique could have been used and utilizing the GA is a personal decision to complement the framework developed for this paper. GAs have been widely and successfully used in various application domains. Fortunately, the results reported in this paper demonstrate the effective- ness of the utilized GA in handling the assessment process to decide on school readiness. Assessment of a person’s abilities and skills is an important task for organizations. Examples include evaluating a child’s readiness for school or determining an employee’s aptitude for a position. The assessment involves various parameters related to the test subject’s aptitude, such as motor skills, linguistic development, or deductive capabilities, among others. The assessment may be conducted by various bodies, such as public education systems, commercial testing companies, and recruiters. To facilitate the assessment process in a systematic way less influenced by the attitude of a specific domain expert, it is preferred to develop and employ web-based assessment systems which integrate the skills of professional domain experts. A recent innovation is an adaptive web-based stealth assessment that analyzes the subject’s skill and dynamically adapts the assessment tests accordingly. A web-based stealth assessment is used for evaluating school readiness of a child by having the child play a series of games comparing the child’s per- formance with a database of performance results for a population. The web-based stealth assessment includes a processor for processing the child’s performance data, for comparing the performance data with the performance results of the population, and for applying a GA to determine the most appropriate next test for the child.

A major challenge that faces most families is effectively anticipating how ready to start school a given child is. Traditional tests are not very effective as they depend on the skills of the expert conducting the test. It is argued that automated tools are more attractive especially when they are extended with games capabilities that would be the most attractive for the children to be seriously involved in the test. The first part of this thesis reviews the school readiness approaches applied in various countries. This motivated the development of the sophisticated system described in the thesis. Extensive research was conducted to enrich the system with features that consider machine learning and social network aspects. A modified genetic algorithm was integrated into a web-based stealth assessment tool for school readiness. The research goal is to create a web-based stealth assessment tool that can learn the user's skills and adjust the assessment tests accordingly. The user plays various sessions from various games, while the Genetic Algorithm (GA) selects the upcoming session or group of sessions to be presented to the user according to his/her skills and status. The modified GA and the learning procedure were described. A penalizing system and a fitness heuristic for best choice selection were integrated into the GA. Two methods for learning were presented, namely a memory system and a no-memory system. Several methods were presented for the improvement of the speed of learning. In addition, learning mechanisms were introduced in the social network aspect to address further usage of stealth assessment automation. The effect of the relatives and friends on the readiness of the child was studied by investigating the social communities to which the child belongs and how the trend in these communities will reflect on to the child under investigation. The plan is to develop this framework further by incorporating more information related to social network construction and analysis. Also, it is planned to turn the framework into a self adaptive one by utilizing the feedback from the usage patterns to learn and adjust the evaluation process accordingly.

A major challenge that faces most families is effectively anticipating how ready to start school a given child is. Traditional tests are not very effective as they depend on the skills of the expert conducting the test. It is argued that automated tools are more attractive especially when they are extended with games capabilities that would be the most attractive for the children to be seriously involved in the test. The first part of this thesis reviews the school readiness approaches applied in various countries. This motivated the development of the sophisticated system described in the thesis. Extensive research was conducted to enrich the system with features that consider machine learning and social network aspects. A modified genetic algorithm was integrated into a web-based stealth assessment tool for school readiness. The research goal is to create a web-based stealth assessment tool that can learn the user's skills and adjust the assessment tests accordingly. The user plays various sessions from various games, while the Genetic Algorithm (GA) selects the upcoming session or group of sessions to be presented to the user according to his/her skills and status. The modified GA and the learning procedure were described. A penalizing system and a fitness heuristic for best choice selection were integrated into the GA. Two methods for learning were presented, namely a memory system and a no-memory system. Several methods were presented for the improvement of the speed of learning. In addition, learning mechanisms were introduced in the social network aspect to address further usage of stealth assessment automation. The effect of the relatives and friends on the readiness of the child was studied by investigating the social communities to which the child belongs and how the trend in these communities will reflect on to the child under investigation. The plan is to develop this framework further by incorporating more information related to social network construction and analysis. Also, it is planned to turn the framework into a self adaptive one by utilizing the feedback from the usage patterns to learn and adjust the evaluation process accordingly.

Mémoire numérisé par la Division de la gestion de documents et des archives de l'Université de Montréal.

Mémoire numérisé par la Division de la gestion de documents et des archives de l'Université de Montréal