Agriculture, Vol. 14, Pages 654: Enhancing Predictive Accuracy in European Agricultural Tractor Residual Value Estimation: A Double Square Root Regression Reappraisal

Determining the residual value of tractors is imperative for comprehensive cost analyses within the agricultural machinery sector. Despite numerous studies offering various models and independent variables, the double square root regression approach, originally developed by Cross and Perry and adapted by ASABE for North American contexts, has been widely utilized. However, factors such as the complexity of OEM portfolios, steep price increases due to compliance with diesel emission regulations, and limited data availability in Europe and its market specificities necessitate improvements in predictive accuracy. This study evaluates different tractor cohort alternatives beyond engine horsepower to enhance predictive robustness. Incorporating brand and powertrain type alongside engine power significantly improved model performance and exhibited the strongest robustness, as evidenced by reduced the root mean square error (RMSE) and increased R-squared values. These findings contribute to the refinement of tractor residual value estimation models, offering valuable insights for stakeholders in the agricultural machinery industry.

Apr 23, 2024 - 21:11
 0  80
Agriculture, Vol. 14, Pages 654: Enhancing Predictive Accuracy in European Agricultural Tractor Residual Value Estimation: A Double Square Root Regression Reappraisal

Agriculture, Vol. 14, Pages 654: Enhancing Predictive Accuracy in European Agricultural Tractor Residual Value Estimation: A Double Square Root Regression Reappraisal

Agriculture doi: 10.3390/agriculture14050654

Authors: Herranz-Matey Ruiz-Garcia

Determining the residual value of tractors is imperative for comprehensive cost analyses within the agricultural machinery sector. Despite numerous studies offering various models and independent variables, the double square root regression approach, originally developed by Cross and Perry and adapted by ASABE for North American contexts, has been widely utilized. However, factors such as the complexity of OEM portfolios, steep price increases due to compliance with diesel emission regulations, and limited data availability in Europe and its market specificities necessitate improvements in predictive accuracy. This study evaluates different tractor cohort alternatives beyond engine horsepower to enhance predictive robustness. Incorporating brand and powertrain type alongside engine power significantly improved model performance and exhibited the strongest robustness, as evidenced by reduced the root mean square error (RMSE) and increased R-squared values. These findings contribute to the refinement of tractor residual value estimation models, offering valuable insights for stakeholders in the agricultural machinery industry.

What's Your Reaction?

like

dislike

love

funny

angry

sad

wow

Lema Kefyalew Studying a Ph.D. in Civil Engineering (Hydraulic Engineering). Studying Master of Project Management (MPM). Graduated with MSc in Civil Engineering (Hydraulic Engineering). Followed a 12 month Software Engineering program at ALX_Africa (Holberton school). Graduated with BA degree in Management. Graduated with BSc degree in Civil Engineering.