Econometric Modeling Combining MCMC Algorithm and Random Coefficient Quantile AR Model

Abstract

The current econometric models have the disadvantages of low prediction accuracy and poor model fitting effect. To solve these problems, this study combines Markov chain Monte Carlo algorithm with random coefficient quantile auto-regression model, and optimizes the econometric model based on the fusion algorithm. The results showed that compared with financial time series prediction algorithms, the fusion algorithm improved the prediction accuracy by 4.8% and the computation speed by 6.5 bps. The econometric model based on the fusion algorithm was compared with other models. The results showed that the optimized model improved the prediction accuracy by 10.7% compared to the AdaBoost econometric model. In summary, the fusion algorithm proposed in the study can improve the prediction efficiency of econometric models, accelerate the prediction process, optimize economic benefits, and reduce investment risks for enterprises and individuals.

Keywords

• Econometric model
• Markov chain Monte Carlo algorithm
• random coefficient quantile auto-regressive model
• economic efficiency