DSE Time Series Analysis and Forecasting 2

Question 1

In an ARIMA(p, d, q) model, what does the parameter 'p' represent?

Accepted Answer

The order of the autoregressive component

Answer

The degree of differencing applied to the series

Answer

The order of the moving average component

Answer

The seasonal period of the data

Question 2

Which plot is used to determine the order of the autoregressive term (p) when building an ARIMA model?

Accepted Answer

PACF (Partial Autocorrelation Function) plot

Answer

ACF (Autocorrelation Function) plot

Answer

Histogram of residuals

Answer

Q-Q (quantile-quantile) plot

Question 3

What is the key difference between an AR (AutoRegressive) model and an MA (Moving Average) model?

Accepted Answer

AR models use lagged observed values as predictors; MA models use lagged forecast errors as predictors

Answer

AR models use lagged forecast errors as predictors; MA models use lagged observed values

Answer

AR models require stationarity; MA models can handle non-stationary data directly

Answer

AR models are for seasonal data only; MA models handle non-seasonal data

Question 4

What is the core principle behind exponential smoothing in time series forecasting?

Accepted Answer

Assigning exponentially decreasing weights to past observations so recent data has more influence

Answer

Detecting unit roots by testing residual autocorrelation

Answer

Identifying the dominant seasonal period in the data

Answer

Removing autocorrelation from model residuals before forecasting

Question 5

The Ljung-Box test applied to time series model residuals is used to test for what?

Accepted Answer

Remaining autocorrelation in the residuals

Answer

Normality of the residual distribution

Answer

Heteroscedasticity in the original series

Answer

Cointegration between two time series

Question 6

How is the Akaike Information Criterion (AIC) used in ARIMA model selection?

Accepted Answer

It balances goodness of fit against model complexity to help avoid overfitting

Answer

It tests whether the series is stationary before differencing

Answer

It measures out-of-sample forecast accuracy on a held-out test set

Answer

It detects and flags outliers in the training data

Question 7

The Box-Jenkins methodology is a systematic approach primarily used for what purpose?

Accepted Answer

Identifying, estimating, and diagnostically checking ARIMA models

Answer

Clustering time series by pattern similarity

Answer

Decomposing a series into trend, seasonal, and residual components

Answer

Applying deep learning to multivariate time series forecasting