CASE-DRIVEN REFORM OF APPLIED STATISTICS TEACHING THROUGH QUANTILE REGRESSION OF FOREST TREE GROWTH
Keywords:
Applied statistics, Quantile regression, Forestry education, Case-based learning, Tree height, Teaching reformAbstract
In graduate applied-statistics courses, knowing how to run a regression does not necessarily prepare students to choose a model for a forestry problem or explain what its estimates mean. We describe a case-based teaching plan built around the height–diameter relationship in a mixed larch–birch stand. The source project reports measurements for 677 trees in four plots, including diameter at breast height, total height, live-crown height, and crown dimensions. The proposed course asks students to examine data quality, fit ordinary least squares (OLS) and quantile regressions, and compare findings across species and plots with different management histories. By working through 19 conditional quantiles (0.05–0.95), students can see where an average relationship leaves important variation unexplained. The teaching sequence includes preparatory exercises, collaborative analyses, and a management-oriented briefing, supported by an assessment rubric. We distinguish results mentioned in the project materials from estimates that students would need to verify with the original observations. In particular, differences between thinned and untreated plots cannot, by themselves, establish an effect of thinning. This article sets out a teaching design rather than reporting an intervention trial; classroom learning outcomes remain to be evaluated. The case illustrates how statistical computation can be taught alongside ecological interpretation, reproducibility, and caution in drawing conclusions.References
[1] Ning J, Wang G, Xu N, et al. Study on growth of basal area increment of individual trees in broad-leaved secondary forest based on quantile regression model. Journal of Central South University of Forestry & Technology, 2023, 43(12): 24-34. DOI: 10.14067/j.cnki.1673-923x.2023.12.003.
[2] Miao Z, Widagdo F R A, Dong L, et al. Prediction of branch growth using quantile regression and mixed-effects models: An example with planted Larix olgensis Henry trees in Northeast China. Forest Ecology and Management, 2021, 496: 119407. DOI: 10.1016/j.foreco.2021.119407.
[3] Miao Z, Li F, Zhao X, et al. Utilizing quantile regressions to predict vertical distribution of branch size in Larix olgensis Henry. Forest Ecosystems, 2025, 13(1): 100300. DOI: 10.1016/j.fecs.2025.100300.
[4] Wang Y, Zhao W, Zhang Q, et al. Predicting tree height-diameter relationship from relative competition levels using quantile regression models for Chinese fir (Cunninghamia lanceolata) in Fujian Province, China. Forests, 2020, 11(2): 183. DOI: 10.3390/f11020183.
[5] Koenker R. Quantile regression: 40 years on. Annual Review of Economics, 2017, 9: 155-176. DOI: 10.1146/annurev-economics-063016-103651.
[6] Rosier G. The case method evaluated in terms of higher education research: A pilot study. The International Journal of Management Education, 2022, 20(3): 100660. Article identifier: S1472811722000623. https://www.sciencedirect.com/science/article/pii/S1472811722000623.
[7] Zea-Camano J D, Soto J R, Arce J E, et al. Improving the modeling of the height-diameter relationship of tree species with high growth variability: Robust regression analysis of Ochroma pyramidale. Forests, 2020, 11(3): 313. DOI: 10.3390/f11030313.
[8] Chiou C R, Cheng C P, Yang S I. Comparison of parametric and nonparametric methods for estimating size-density relationships in old-growth Japanese cedar plantations. Forests, 2020, 11(6): 625. DOI: 10.3390/f11060625.