Estimating the Effectiveness of University Training Programs on Student Achievement Using Generalized Linear Models (GLM): An Applied Evaluation Study

Khalid Talib  Othman; Mahmood Shakir  Khashman; Mohammed Abdulkadher  fadhil; Zahraa Ali  Jaafar

Authors

Khalid Talib Othman College of Medicine, Iraqi University
Mahmood Shakir Khashman College of Medicine, Iraqi University
Mohammed Abdulkadher fadhil College of Medicine, Iraqi University
Zahraa Ali Jaafar College of Medicine, Iraqi University

Keywords:

Generalized Linear Model, Training Effectiveness, Student Achievement, Program Evaluation, Higher Education

Abstract

Generalized Linear Models (GLM) is applied in this paper as a statistical assessment framework to estimate the effect of university training programs on student achievements. The study seeks to know the effects that well-structured training programs have on the academic achievements of undergraduate students from different fields. Data used in this research was achieved through academic records and post-training performance survey data from three public universities with 500 students. GLM permits both continuous and categorical dependent variables, therefore making provisions for more flexible modeling of academic achievement data.[1] Training duration, type of program, previous GPA, gender, and academic department were used as predictor variables in the study. There was an explicitly significant positive relationship between the intensity of training and post-program academic achievement. Students who have attended more than 40 hours of structured training showed by a mean GPA improvement of 0.35 points that GPAs compared to untrained peers. Besides, gender and academic discipline showed moderating effects on the relationship between training and performance (see Table 1). The findings highlight structured skill-based university programs aimed at In conclusion, the results of this study draw attention to the effectiveness of structured skill-based university programs on improving learning outcomes and students’ academic record. Furthermore, we specifically recommend the universities to implement a system of continuous assessment as a part of the training curriculum and to adopt the evaluation and monitoring systems based on Generalized Linear Models. This particular model used in our research provides an example of statistically sound and reproducible approach for educational administrators who search for data-driven continuous quality improvement solutions.

References

S. J. Aziz, N. H. Mahmood, R. M. H. Salih, and F. O. H. Rasool, “Significant factors influencing students’ perceptions towards university teachers’ evaluations using a generalized linear model,” The Scientific Journal of Cihan University–Sulaimaniya, vol. 8, no. 1, pp. 423–448, 2024.

I. Owusu-Darko, I. K. Adu, and N. K. Frempong, “Application of generalized estimating equation (GEE) model on students’ academic performance,” Applied Mathematical Sciences, vol. 8, no. 68, pp. 3359–3374, 2014.

B. R. Subedi, N. Reese, and R. Powell, “Measuring teacher effectiveness through hierarchical linear models: Exploring predictors of student achievement and truancy,” Journal of Education and Training Studies, vol. 3, no. 2, pp. 34–43, 2015.

H. P. Pinheiro, M. Rodrigues-Motta, and G. Franco, “Modelling performance of students with generalized linear mixed models,” in Proc. 29th Int. Workshop Statistical Modelling, vol. 2, pp. 133–136, 2014.

G. W. Fulmer and M. S. Polikoff, “Tests of alignment among assessment, standards, and instruction using generalized linear model regression,” Educational Assessment, Evaluation and Accountability, vol. 26, no. 3, pp. 225–240, 2014.

F. Al-Maamari, “Response rate and teaching effectiveness in institutional student evaluation of teaching: A multiple linear regression study,” Higher Education Studies, vol. 5, no. 6, pp. 9–20, 2015.

A. Basso and G. di Tollo, “A generalised linear model approach to predict the result of research evaluation,” in Mathematical and Statistical Methods for Actuarial Sciences and Finance: MAF 2016, Cham: Springer Int. Publishing, 2017, pp. 29–41.

L. Fontana, C. Masci, F. Ieva, and A. M. Paganoni, “Performing learning analytics via generalised mixed-effects trees,” Data, vol. 6, no. 7, p. 74, 2021.

R. Froud, S. H. Hansen, H. K. Ruud, J. Foss, L. Ferguson, and P. M. Fredriksen, “Relative performance of machine learning and linear regression in predicting quality of life and academic performance of school children in Norway: Data analysis of a quasi-experimental study,” Journal of Medical Internet Research, vol. 23, no. 7, e22021, 2021.

K. Harini and K. K. S. Rekha, “Evaluating performance of identifying at-risk students and learning achievement model using accuracy and F-measure by comparing logistic regression, generalized linear model and gradient boost machine algorithm,” in Proc. 2022 Int. Conf. for Advancement in Technology (ICONAT), 2022, pp. 1–7.

M. El Jihaoui, O. E. K. Abra, and K. Mansouri, “Factors affecting student academic performance: A combined factor analysis of mixed data and multiple linear regression analysis,” IEEE Access, 2025.

M. J. H. Molla, H. K. Maity, B. Chakraborty, S. M. Obaidullah, and S. Sen, “Generalization of logistic regression to improve prediction: An application on training and placement data,” SN Computer Science, vol. 6, no. 7, p. 791, 2025.

A. Kaliba, “Factors influencing school performance in the state of Louisiana, US: A generalized additive (mixed) model approach,” US: A Generalized Additive (Mixed) Model Approach, Oct. 29, 2024.

A. Kumar and A. K. Prabhakar, “Comparison of stacking, boosting, generalized linear, and neural network models for estimating scour depth around spur-dykes,” Iranian Journal of Science and Technology, Transactions of Civil Engineering, pp. 1–16, 2025.

M. Sladekova, V. L. Poupa, and A. P. Field, “Sources of bias in general linear models: Evaluating the analytic practice in psychological research,” PsyArXiv, 2024.