Scholarlink

Life expectancy models are crucial in shaping the social and financial landscapes of nations worldwide. Numerous studies highlight the profound implications these projections have on societal challenges and the governance of global healthcare infrastructures. In this study, we assess various time series models for predictive life expectancy in India. The models considered in this research include ARMA (AutoRegressive-Moving Average), AR (Auto-Regressive), SARIMA (Seasonal AutoRegressive Integrated Moving Aver-age), Simple Exponential Smoothing (SES), ARIMA (AutoRegressive Integrated Moving Average), Holt’s method and Holt-Winter’s method. The evaluation is performed on time series data, utilizing metrics like accuracy, precision, mean absolute error (MAE), and root mean square error (RMSE). Through rigorous experimentation and analysis, the strengths and weakness-es of each model are identified, providing insights into their effectiveness for different types of time series forecasting models. The ARMA model has proven to be the most accurate and reliable for predicting life expectancy. Additionally, potential avenues for model enhancement and future research directions are discussed, highlighting the importance of ongoing advancements in time series modeling techniques. This study underscores the significance of selecting appropriate models for accurate predictions.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction of Life Expectancy for India Using Time Series Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Needa Ansari,
  • Samir Patel

摘要

Life expectancy models are crucial in shaping the social and financial landscapes of nations worldwide. Numerous studies highlight the profound implications these projections have on societal challenges and the governance of global healthcare infrastructures. In this study, we assess various time series models for predictive life expectancy in India. The models considered in this research include ARMA (AutoRegressive-Moving Average), AR (Auto-Regressive), SARIMA (Seasonal AutoRegressive Integrated Moving Aver-age), Simple Exponential Smoothing (SES), ARIMA (AutoRegressive Integrated Moving Average), Holt’s method and Holt-Winter’s method. The evaluation is performed on time series data, utilizing metrics like accuracy, precision, mean absolute error (MAE), and root mean square error (RMSE). Through rigorous experimentation and analysis, the strengths and weakness-es of each model are identified, providing insights into their effectiveness for different types of time series forecasting models. The ARMA model has proven to be the most accurate and reliable for predicting life expectancy. Additionally, potential avenues for model enhancement and future research directions are discussed, highlighting the importance of ongoing advancements in time series modeling techniques. This study underscores the significance of selecting appropriate models for accurate predictions.