Field-testing is an essential yet often resource-intensive step in the development of high-quality educational assessments. I introduce an innovative method for field-testing newly written exam items by substituting human examinees with artificially intelligent (AI) examinees. The proposed approach is demonstrated using 466 four-option multiple-choice English grammar questions. Pre-trained transformer language models are fine-tuned based on the 2-parameter logistic (2PL) item response model to respond like human test-takers. Each AI examinee is associated with a latent ability θ, and the item text is used to predict response selection probabilities for each of the four response options. For the best modeling approach identified, the overall correlation between the true and predicted 2PL correct response probabilities was .82 (bias = 0.00, root mean squared error = 0.18). The study results were promising, showing that item response data generated from AI can be used to calculate item proportion correct, item discrimination, conduct item calibration with anchors, distractor analysis, dimensionality analysis, and latent trait scoring. However, the proposed approach did not achieve the level of accuracy obtainable with human examinee response data. If further refined, potential resource savings in transitioning from human to AI field-testing could be enormous. AI could shorten the field-testing timeline, prevent examinees from seeing low-quality field-test items in real exams, shorten test lengths, eliminate test security, item exposure, and sample size concerns, reduce overall cost, and help expand the item bank. Example Python code from this study is available on Github: https://github.com/hotakamaeda/ai_field_testing1.

The purpose of this study was to examine motivational constructs and the effect of physical activity engagement on health behaviors in college students who were required to take a 15-week lifetime physical fitness (LPF) course for graduation. A total of fifty-eight first and second year college students aged between 17 and 23 years (M=18.72; SD=1.09). Paper and pencil questionnaires were anonymously administered at the beginning and at the end of the 15-week long spring 2012 semester. Analysis of the differences between the beginning and the end of the semester was completed. Physical activity behaviors and Behavioral Regulations variables did not change across time (p > .05). Appearance (d = -0.34, p = .013) and fitness (d = -0.37, p = .006) reasons for participating in physical activity and all Theory of Planned Behavior variables decreased over time (d = -0.32 to - 0.41, p < .05). Changes in attitude toward physical activity negatively predicted changes in alcohol consumption (r = -.261 to -.357). This study sustains the already existing literature that supports the positive impact of LPF courses offered to college students.

The purpose of this study was to determine the effect of stand-biased desks on the physical activity and sedentary behavior of third, fourth and sixth grade students across the school year. Methods: This within classroom crossover design study used teacher-determined allocation for seating within each classroom. Half of the students used a stand-biased desk and half used a sitting desk. Five-day hip-worn accelerometer assessments were completed at baseline and at the end of each nine-week intervention period. A mixed effects model was used to determine the differences in the percentage of time spent active and sedentary. Results: A total of 22, 36 and 41 students in 3rd, 4th and 6th grades, respectively, completed this study (57.1% male, 79.3% White). Regardless of the desk type, students became more sedentary (p < 0.001) and less active (p < 0.001) in the classroom as the school year progressed. After controlling for baseline activity, there was a significant interaction between the type of desk and time (p = 0.029). Students who spent a higher percentage of their classroom time sedentary engaged in less sedentary behavior when using a stand-biased desk compared to the traditional desk. Conclusion: The standing desk intervention was effective in mitigating the increase in sedentary behavior for those who started the school year more sedentary.