论文标题
使用Box-Jenkins Arima模型预测和分析印度军事支出
Forecasting and Analyzing the Military Expenditure of India Using Box-Jenkins ARIMA Model
论文作者
论文摘要
经济数据统计方法论领域的进步已经铺平了其朝着设计有效的军事管理政策的艰苦需求的道路。就2019年的军事造型而言，印度被评为第三大国家。因此，本研究旨在利用盒子 - 珍金斯·阿里玛（Jenkins Arima）模型进行时间序列预测印度军事支出的时间序列。该模型是在1960年至2019年的60年印度军事支出的SIPRI数据集上生成的。分析了该模型的产生趋势，该模型最能适应预测。该研究强调了最低AIC值，并涉及ADF测试（增强的Dickey-Fuller），以将支出数据转换为固定形式以进行模型生成。它还侧重于绘制剩余误差分布以进行有效的预测。这项研究提出了一个Arima（0,1,6）模型，用于对印度军事支出的最佳预测，其准确度为95.7％。因此，该模型充当移动平均值（MA）模型，并预测到2024年，印度军事支出的稳态指数增长为36.94％。
The advancement in the field of statistical methodologies to economic data has paved its path towards the dire need for designing efficient military management policies. India is ranked as the third largest country in terms of military spender for the year 2019. Therefore, this study aims at utilizing the Box-Jenkins ARIMA model for time series forecasting of the military expenditure of India in forthcoming times. The model was generated on the SIPRI dataset of Indian military expenditure of 60 years from the year 1960 to 2019. The trend was analysed for the generation of the model that best fitted the forecasting. The study highlights the minimum AIC value and involves ADF testing (Augmented Dickey-Fuller) to transform expenditure data into stationary form for model generation. It also focused on plotting the residual error distribution for efficient forecasting. This research proposed an ARIMA (0,1,6) model for optimal forecasting of military expenditure of India with an accuracy of 95.7%. The model, thus, acts as a Moving Average (MA) model and predicts the steady-state exponential growth of 36.94% in military expenditure of India by 2024.
