Predicting Teaching Effectiveness of University Faculty using Multiple Linear Regression

• Main Authors: Traballo, Roel C., Dasig, Daniel D., Taduyo, Mary Ann B., Cervantes, Mary Ellaine R., Guarin, Rudolph Val F., Gatpandan, Mengvi P., Calantoc, John Denver, Talion, Fernando I., Claricia, Eleonora E., Gatpandan, Paulino H., Dalimot, Michael
• Format: Conference Proceeding
• Language: English
• Subjects: Education; Employment; faculty evaluation; Knowledge discovery; Knowledge Discovery in Databases; Linear regression; Multiple Linear Regressions; Programming; Surveys; teaching effectiveness
• ISSN: 2770-0682
• DOI: 10.1109/HNICEM60674.2023.10589165

This study utilized multiple linear regressions to measure and predict the teaching effectiveness of university faculty. The researchers also utilized Knowledge Discovery in Databases and Python programming. Multiple linear regression analysis was performed to answer research concerns as to whether classroom observation, employment status, and total respondents would influence the efficacy of teaching effectiveness based on the average rating, and whether or not the response rate could be predicted by professor classroom observation, employment status, and total respondents. A dataset of over 135 student ratings collected in the college from a Faculty Evaluation Report (FER) spanning the period from 2016 to 2019 was used in the analysis. The study found that, after running the Multiple Linear Regression, the model has a much higher R-square value which implied that this model with the specified sets of independent variables explained the 94.50% result used in the model of the independent variable. The researchers recommend conducting the needs assessment survey of permanent faculty members which aims to identify the reasons or their sentiments to improve their teaching effectiveness.