A Machine Learning Approach to Evaluate Variables of Math Anxiety in STEM Students

The relationships between math anxiety and other variables such as students' motivation and confidence have been extensively studied. The main purpose of the present study was to employ a machine learning approach to provide a deeper understanding of variables associated with math anxiety. Specifically, we applied classification and regression tree models to weekly survey data of science, technology, engineering, and mathematics (STEM) students enrolled in calculus. The tree models accurately identified that the level of confidence is the primary predictor of math anxiety. Students with low levels of confidence expressed high levels of math anxiety. The academic level of students and the number of weekly hours studied were the next two predictors of math anxiety. The junior and senior students had lower math anxiety. Also, those with a higher number of hours studied were generally less anxious. Weekly tree diagrams provided a detailed analysis of the interrelations between math anxiety and variables including academic level, number of hours studied, gender, motivation, and confidence. We noticed that the nature of such interrelations can change during the semester. For instance, in the first week of the semester, confidence was the primary factor, followed by academic level and then motivation. However, in the third week, the order of the interrelation changed to confidence, academic level, and course level, respectively. In summary, decision tree models can be used to predict math anxiety and to provide a more detailed analysis of data associated with math anxiety.

Analysis of Anxiety, Motivation, and Confidence of STEM Students during the COVID-19 Pandemic

The current COVID-19 pandemic has largely impacted the academic performance of several college students. The present study is concerned with the effects of the COVID-19 pandemic on students pursuing a STEM (science, technology, engineering, and mathematics) degree. We collected weekly survey data (w=9) of students (n=53) taking calculus courses during the COVID-19 pandemic. Using the self-reported survey data, we investigated the temporal variations in the levels of anxiety, motivation, and confidence of STEM students. Studies on temporal changes to math anxiety are scarce. The present work aims to fill this gap by analyzing longitudinal survey data associated with math anxiety. Furthermore, using descriptive and inferential statistical methods such as one-way ANOVA, we analyzed the data with respect to gender and academic level. Our results indicated that male and freshman/sophomore (F/Sp) STEM students had higher levels of increased anxiety due to COVID-19. Female and F/Sp STEM students had higher levels of motivation, whereas junior/senior (J/S) and male students exhibited higher levels of confidence. Time series analysis of the data indicated that the levels of motivation and confidence significantly dropped toward the end of the semester, whereas the level of anxiety increased in all groups. Also, the use of math resources (such as tutoring and supplemental instruction) has significantly reduced during the COVID-19 pandemic.

Incorporating global dynamics to improve the accuracy of disease models: Example of a COVID-19 SIR model.

Mathematical models of infectious diseases exhibit robust dynamics, such as stable endemic, disease-free equilibriums or convergence of the solutions to periodic epidemic waves. The present work shows that the accuracy of such dynamics can be significantly improved by including global effects of host movements in disease models. To demonstrate improved accuracy, we extended a standard Susceptible-Infected-Recovered (SIR) model by incorporating the global dynamics of the COVID-19 pandemic. The extended SIR model assumes three possibilities for susceptible individuals traveling outside of their community: • They can return to the community without any exposure to the infection. • They can be exposed and develop symptoms after returning to the community. • They can be tested positively during the trip and remain quarantined until fully recovered. To examine the predictive accuracy of the extended SIR model, we studied the prevalence of the COVID-19 infection in six randomly selected cities and states in the United States: Kansas City, Saint Louis, San Francisco, Missouri, Illinois, and Arizona. The extended SIR model was parameterized using a two-step model-fitting algorithm. The extended SIR model significantly outperformed the standard SIR model and revealed oscillatory behaviors with an increasing trend of infected individuals. In conclusion, the analytics and predictive accuracy of disease models can be significantly improved by incorporating the global dynamics of the infection.

Assessment of Retrospective COVID-19 Spatial Clusters with Respect to Demographic Factors: Case Study of Kansas City, Missouri, United States.

Coronavirus disease 2019 (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The United States (U.S.) has the highest number of reported COVID-19 infections and related deaths in the world, accounting for 17.8% of total global confirmed cases as of August 2021. As COVID-19 spread throughout communities across the U.S., it became clear that inequities would arise among differing demographics. Several researchers have suggested that certain racial and ethnic minority groups may have been disproportionately impacted by the spread of COVID-19. In the present study, we used the daily data of COVID-19 cases in Kansas City, Missouri, to observe differences in COVID-19 clusters with respect to gender, race, and ethnicity. Specifically, we utilized a retrospective Poisson spatial scan statistic with respect to demographic factors to detect daily clusters of COVID-19 in Kansas City at the zip code level from March to November 2020. Our statistical results indicated that clusters of the male population were more widely scattered than clusters of the female population. Clusters of the Hispanic population had the highest prevalence and were also more widely scattered. This demographic cluster analysis can provide guidance for reducing the social inequalities associated with the COVID-19 pandemic. Moreover, applying stronger preventive and control measures to emerging clusters can reduce the likelihood of another epidemic wave of infection.