Prediction of the Household Consumption in China by Linear Regression

Junyu Qian

doi:10.54097/cmrft933

Authors

Junyu Qian Nanjing Foreign Language School, Nanjing, China

DOI:

https://doi.org/10.54097/cmrft933

Keywords:

Household consumption; Multiple linear regression; Log-linear Trend Model.

Abstract

Household consumption plays a crucial role in economic growth and accounts for a large proportion of GDP. So, making accurate predictions of household consumption trends is highly important to predict macroeconomic activity. This paper estimates the impact of disposable income per head and the Gini coefficient on household consumption in China by a multiple linear regression equation. It is constructed based on annual data coming from the CEI website during the recent 20 years. The multiple linear regression equation is calculated by the Excel software to get the coefficients of each determinant. The paper also predicts the disposable income per head using Log-linear Trend Model, which is used to input into the multiple linear regression equation and get the final prediction of household consumption. Moreover, a VIF method is used to prove the effectiveness of the multiple linear regression equation. The results show that both variables have significant positive effects and the household consumption will have a slight increase in 2025.

References

[1] The Global Economy. Household consumption as percent of GDP [Internet]. 2024 [cited 2026 Apr 14]. Available from: The World Bank.

[2] Chai A, Moneta A. Retrospectives: Engel curves. J Econ Perspect. 2010;24(1):225–240.

[3] Friedman M. Theory of the consumption function. 2018.

[4] Deaton A, Muellbauer J. An almost ideal demand system. Am Econ Rev. 1980;70(3):312–326.

[5] Campbell JY, Mankiw NG. Consumption, income, and interest rates: Reinterpreting the time series evidence. NBER Macroecon Annu. 1989;4:185–216.

[6] China Economic Net. Gini coefficient (2005–2024) and disposable income per resident (2005–2025) [Internet]. [cited 2026 Apr 14]. Available from: National Bureau of Statistics of China.

[7] James G, Witten D, Hastie T, Tibshirani R, Taylor J. Linear regression. In: An Introduction to Statistical Learning: With Applications in Python. Cham: Springer; 2023. p. 69–134.

[8] Wooldridge JM. Introductory econometrics: A modern approach. 2016.

[9] Gallant AR. Nonlinear regression. Am Stat. 1975;29(2):73–81.

[10] Ariyo AA, Adewumi AO, Ayo CK. Stock price prediction using the ARIMA model. In: Proc 16th UKSim-AMSS Int Conf Comput Model Simul. IEEE; 2014. p. 106–112.