Student attrition is an important issue for higher education as it brings about grave costs to both students and institutions. This article investigates the 2-year persistence rate of students enrolled at a large 4-year public institution in California in Fall 2016 to Fall 2020. Predictors considered include student demographic information, socioeconomic variables, academic preparation, and their academic performance at the institution. Two analytical approaches are used, discrete-time survival analysis and random forest (RF). The results indicate that academic performance variables after enrollment are most strongly associated with 2-year persistence. In particular, monitoring and providing help promptly to students with earned-units below 6 or GPA below 2.0 in the first term may prevent them from dropping out. Among socioeconomic variables available for analysis, first-generation status seems to be more directly related to student attrition. It is also illustrated how the RF model may be used to provide individualized prediction of 2-year persistence.
AulckL. S.NambiD.VelagapudiN.BlumenstockJ. E.WestJ. D. (2019). Mining university registrar records to predict first-year undergraduate attrition. In Proceedings of the 12th International Conference on Educational Data Mining (pp. 9–18). https://filesericed.gov/fulltext/ED599235.pdf
2.
BeemerJ.SpoonK.FanJ. J.StronachJ.FrazeeJ. P.BohonA. J.LevineR. A. (2018). Assessing instructional modalities: Individualized treatment effects for personalized learning. Journal of Statistics Education, 26(1), 31–39. https://doi.org/10.1080/10691898.2018.1426400
3.
BerensJ.SchneiderK.GörtzS.OsterS.BurghoffJ. (2019). Early detection of students at risk – predicting student dropouts using administrative student data from German universities and machine learning methods. Journal of Educational Data Mining, 11(3), 1–41. https://doi.org/10.2139/ssrn.3275433
4.
BonetG.WaltersB. R. (2016). High impact practices: Student engagement and retention. CUNY Academic Works, 224–235. https://academicworks.cuny.edu/cgi/viewcontent.cgi?article=1101&context=kb_pubs
5.
BonifroF. D.GabbrielliM.LisantiG.ZingaroS. P. (2020). Student dropout prediction. In Artificial intelligence in education (pp. 129–140). https://pmc.ncbi.nlm.nih.gov/articles/PMC7334184/
6.
BreimanL. (1999). Random forests – Random features (Technical Report No. 567). University of California. https://www.stat.berkeley.edu/∼breiman/random-forests.pdf
7.
BreimanL. (2001). Random Forests. Machine Learning, 45, 5–32. https://doi.org/10.1023/A:1010933404324
8.
CafriG.LiL.PaxtonE. W.FanJ. (2018). Predicting risk for adverse health events using Random Forest. Journal of Applied Statistics, 45(12), 2279–2294. https://doi.org/10.1080/02664763.2017.1414166
9.
CaruanaR.KarampatziakisN.YessenalinaA. (2008). An empirical evaluation of supervised learning in high dimensions. In Proceedings of the 25th International Conference on Machine Learning (pp. 96–103). https://doi.org/10.1145/1390156.1390169
10.
CaruanaR.Niculescu-MizilA. (2006). An empirical comparison of supervised learning algorithms. In Proceedings of the 23rd International Conference on Machine Learning (pp. 161–168). https://doi.org/10.1145/1143844.11438
11.
ChaiK.GibsonD. (2015). Predicting the risk of attrition for undergraduate students with time based modelling. In 12th Cognition and Exploratory Learning in Digital Age(pp. 109–116). http://files.eric.ed.gov/fulltext/ED562154.pdf
12.
ClarkT. G.BradburnM. J.LoveS. B.AltmanD. G. (2003). Survival analysis part I: Basic concepts and first analyses. British Journal of Cancer, 89(2), 232–238. https://doi.org/10.1038/sj.bjc.6601118
13.
CouronnéR.ProbstP.BoulesteixA. L. (2018). Random Forest versus logistic regression: A large-scale benchmark experiment. BMC Bioinformatics, 19, Article 270. https://doi.org/10.1186/s12859-018-2264-5
14.
CoxD. R. (1972). Regression models and life-tables. Journal of the Royal Statistical Society Series B: Statistical Methodology, 34(2), 187–202. https://doi.org/10.1111/j.2517-6161.1972.tb00899.x
15.
DelenD. (2010). A comparative analysis of machine learning techniques for student retention management. Decision Support Systems, 49(4), 498–506. https://doi.org/10.1016/j.dss.2010.06.003
16.
DeviK.RatnooS. (2022). Predicting student dropouts using Random Forest. Journal of Statistics and Management Systems, 25(7), 1579–1590. https://doi.org/10.1080/09720510.2022.2130570
17.
DynarskiS. M.HemeltS. W.HymanJ. M. (2015). The missing manual: Using national student clearinghouse data to track postsecondary outcomes. Educational Evaluation and Policy Analysis, 37(1). https://doi.org/10.3386/w19552
18.
FoxE. W.HillR. A.LeibowitzS. G.OlsenA. R.ThornbrughD. J.WeberM. H. (2017). Assessing the accuracy and stability of variable selection methods for random forest modeling in ecology. Environmental Monitoring and Assessment, 189(7), Article 316. https://doi.org/10.1007/s10661-017-6025-0
19.
FriedmanJ. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451
20.
FriedmanJ. H. (2002). Stochastic gradient boosting. Computational Statistics & Data Analysis, 38(4), 367–378. https://doi.org/10.1016/S0167-9473(01)00065-2
21.
HeL.LevineR.FanJ.BeemerJ.StronachJ. (2018). Random Forest as a predictive analytics alternative to regression in institutional research. Practical Assessment, Research & Evaluation, 23(1). https://files.eric.ed.gov/fulltext/EJ1173275.pdf
22.
JacksonC. H.SharplesL. D.ThompsonS. G. (2010). Survival models in health economic evaluations: Balancing fit and parsimony to improve prediction. The International Journal of Biostatistics, 6(1), Article 34. https://doi.org/10.2202/1557-4679.1269
23.
JamesG.WittenD.HastieT.TibshiraniR. (2021). An introduction to statistical learning with applications in R (2nd ed.). Springer.
24.
KalbfleischJ. D.PrenticeR. L. (1980). The statistical analysis of failure time data.John Wiley and Sons, New York.
25.
KimK.TsiatisA. A. (1990). Study duration for clinical trials with survival response and early stopping rule. Biometrics, 46(1), 81–92. https://doi.org/10.2307/2531632
26.
MadaniA.HagageM.ElbeihS. F. (2022). Random Forest and logistic regression algorithms for prediction of groundwater contamination using ammonia concentration. Arabian Journal of Geosciences, 15, Article 1619. https://doi.org/10.1007/s12517-022-10872-2
27.
MalleyJ. D.KruppaJ.DasguptaA.MalleyK. G.ZieglerA. (2012). Probability machines: Consistent probability estimation using nonparametric learning machines. Methods of Information in Medicine, 51(1), 74–81. https://doi.org/10.3414/ME00-01-0052
28.
MatzS.BukowC. S.PetersH.DeaconsC.DinuA.StachlC. (2023). Using machine learning to predict student retention from socio-demographic characteristics and app-based engagement metrics. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-32484-w
29.
MuchlinskiD.SirokyD.HeJ.KocherM. (2016). Comparing random forest with logistic regression for predicting class-imbalanced civil war onset data. Political Analysis, 24(1), 87–103. https://doi.org/10.1093/pan/mpv024
30.
MullerK.NymanM.SquadereJ.FeuerE.SokolowskiK.RotellaL. (2017). Examining predictors of first year college student retention. The New York Journal of Student Affairs, 17(1), Article 2. https://commons.library.stonybrook.edu/cgi/viewcontent.cgi?article=1017&context=nyjsa
31.
National Center for Education Statistics. (2022). Undergraduate retention and graduation rates. The condition of education 2022, indicator report. U.S. Department of Education. https://nces.ed.gov/programs/coe/pdf/2022/ctr_508.pdf
32.
PedlerM. L.WillisR.NieuwoudtJ. E. (2020). A sense of belonging at university: Student retention, motivation and enjoyment. Journal of Further and Higher Education, 46(3), 397–408. https://doi.org/10.1080/0309877X.2021.1955844
33.
SanbornJ.JonesH. E.ManzeM.TwisteT.FreudenbergN. (2024). The cumulative impact of unmet essential needs on indicators of attrition: Findings from a public university population-based sample of students in the Bronx, NY. Journal of Urban Health: Bulletin of the New York Academy of Medicine, 101(4), 764–774. https://doi.org/10.1007/s11524-024-00872-w
34.
ShaoL.LeongM.LevineR. A.StronachJ.FanJ. J. (2022). Machine learning methods for course enrollment prediction. Strategic Enrollment Management Quarterly, 10(2), 11–29. https://eric.ed.gov/?id=EJ1356234
35.
SingerJ. D.WillettJ. B. (1993). It's about time: Using discrete-time survival analysis to study duration and the timing of events. Journal of Educational Statistics, 18(2), 155–195. https://doi.org/10.2307/1165085
36.
SinghR.MukhopadhyayK. (2011). Survival analysis in clinical trials: Basics and must-know areas. Perspectives in Clinical Research, 2(4), 145–148. https://doi.org/10.4103/2229-3485.86872
37.
SlomaM.SyedF. J.NematiM.XuK. S. (2021). Empirical comparison of continuous and discrete-time representations for survival prediction. Proceedings of Machine Learning Research, 146, 118–131. https://pmc.ncbi.nlm.nih.gov/articles/PMC8232898/
38.
TintoV. (2006). Research and practice of student retention: What next?Journal of College Student Retention: Research, Theory & Practice, 8(1), 1–19. https://doi.org/10.2190/4YNU-4TMB-22DJ-AN4W
39.
VillanoR.HarrisonS.LynchG.ChenG. (2018). Linking early alert systems and student retention: A survival analysis approach. Higher Education, 76, 903–920. https://doi.org/10.1007/s10734-018-0249-y
40.
ZhuhadarL.DadayJ.MarklinS.KesslerB.HelbigT. (2019). Using survival analysis to discovering pathways to success in mathematics. Computers in Human Behavior, 92, 487–495. https://doi.org/10.1016/j.chb.2017.12.016
