Evaluating ARIMA Model Residuals

Hard Time-series Analysis Model Evaluation

Consider a time-series dataset of monthly sales figures for a retail company over the past five years. The analysis includes fitting an ARIMA model to the data, resulting in the estimate of coefficients and their respective significance levels. After evaluating the residuals of the ARIMA model, it was found that the residuals are normally distributed but exhibit autocorrelation.

In assessing the model performance using the AIC (Akaike Information Criterion) and BIC (Bayesian Information Criterion), the following values were obtained: AIC = 150 and BIC = 155. To check the adequacy of the model, a Ljung-Box test was performed, yielding a p-value of 0.01.

Given this context, which of the following statements regarding the model evaluation and appropriateness is correct?

The model is appropriate as the residuals are normally distributed.

The model is inadequate due to the presence of autocorrelation in the residuals.

The AIC and BIC values indicate that this model is the best among the compared models.

Hint

Submitted3.1K

Correct2.1K

% Correct68%