Sensitivity Analysis of Time Series Models to Parameter Changes in Sinusoidal Dummy Data

This study investigates the sensitivity of various time series models to changes in parameters within sinusoidal dummy data. Sinusoidal dummy data, a common tool in time series analysis, is used to represent periodic patterns. By systematically altering parameters such as amplitude, frequency, and phase shift, we aim to understand how these changes impact the performance of different models. Sensitivity analysis is conducted by generating multiple datasets with varying parameter values and evaluating the models' performance using metrics such as mean squared error (MSE), mean absolute error (MAE), and root mean squared error (RMSE). The impact of parameter changes on model accuracy, prediction intervals, and robustness is examined.