The Relationship between New Energy Vehicle Price and Aftermarket-Parts Price Based on The GLM Regression Analysis

Shouchen Ding, Tianli Zu, Puchao Li, Bing Xue2024 · DOI

Abstract

Since the penetration rate of new energy vehicles (NEVs) is gradually increasing in the vehicle market, the industry has entered an era of fast growth. This research aims to figure out the relationship between the price of NEVs and the price of aftermarket parts, providing a data-driven framework for automotive pricing strategies.

Introduction

Traditional research into vehicle pricing focuses heavily on manufacturing capital, such as raw materials, labor, and factory overhead. However, there is a significant gap in understanding how the "aftermarket" ecosystem—the parts required for maintenance and repair—correlates with the initial purchase price.

In the rapidly growing Chinese NEV market, the technical architecture is fundamentally different from Internal Combustion Engine Vehicles (ICEVs). NEVs rely on battery packs and electric drives rather than engines, leading to fewer maintenance items but highly specialized supply chains for core components. This study seeks to quantify how these parts-level pricing strategies ripple up to affect the terminal price of the entire vehicle.

Methodology and Data

The study utilizes a robust, proprietary dataset from the China Automotive Technology and Research Center (CATARC), covering 422 vehicle models with approximately 3,000 detailed parts per vehicle. The researchers employed a two-pronged statistical approach:

  1. GLM Regression: To handle the complexity of the data, forward stepwise regression was used. This method introduces variables to the model only if they improve the goodness of fit ($R^2$) while excluding those that introduce excessive collinearity.
  2. Data Pre-processing: To normalize the data and reduce the impact of outliers, a logarithmic transformation was applied to the parts prices.
  3. Support Vector Machine (SVM): To validate the regression results, the team used SVM with both Linear and Radial Basis Function (RBF) kernels to improve classification accuracy across different price ranges.
Table 1: Descriptive statistics of the variables used in the study, including 422 observations across various vehicle segments.

Key Results and Analysis

The final multiple linear regression model achieved an $R^2$ of 0.8151, explaining over 81% of the variance in vehicle pricing. Key findings include:

  • Significant Predictors: Power system parts, common maintenance parts, and configuration parts were all confirmed to have a statistically significant positive correlation with the total vehicle price ($P < 0.05$).
  • The "Configuration" Premium: For every 1% increase in the price of "configuration parts," the total vehicle price increases by approximately 55 CNY.
  • Maintenance Divergence: The paper highlights a stark difference between NEVs and ICEVs; for example, the maintenance cost of a fuel-powered BYD Tang is 2.5 times higher than its pure electric counterpart over 60,000 kilometers.
  • Vehicle Positioning: Mid-to-high-end cars command a premium of approximately 73,889 CNY over mid-to-low-end models, independent of specific parts costs.
Table 2: Regression coefficients for configuration parts (Log_pzjpjj) and common maintenance parts (log_cywbjpjj), showing high statistical significance.

Conclusion

This research demonstrates that aftermarket parts pricing is a significant predictor of NEV sticker prices. While the model provides a strong technical foundation, it is limited by its exclusion of "soft" market factors such as brand prestige, political atmosphere, and global market dynamics. Future studies should integrate these environmental and policy-driven factors to provide an even more accurate pricing strategy support system for the automotive industry.

Summary updated

Abstract

Since the penetration rate of the new energy vehicles (NEVs) are gradually increasing in the vehicle market, the industry of NEVs have already entered an era of fast growth. This research aims to figure out the relationship between the price of NEVs and the price of aftermarket parts which is based
BibTeX
@misc{ding2024relationship,
  author = {Shouchen Ding and Tianli Zu and Puchao Li and Bing Xue},
  title = {{The Relationship between New Energy Vehicle Price and Aftermarket-Parts Price Based on The GLM Regression Analysis}},
  year = {2024},
  doi = {10.4108/eai.15-12-2023.2345341},
}
Figure