DSE Time Series Analysis and Forecasting

Question 1

What property of a time series indicates that its statistical properties such as mean and variance remain constant over time?

Accepted Answer

Stationarity

Answer

Autocorrelation

Answer

Seasonality

Answer

Heteroscedasticity

Question 2

Which statistical test is most commonly used to check whether a time series is stationary by testing for a unit root?

Accepted Answer

Augmented Dickey-Fuller (ADF) test

Answer

Chi-square test

Answer

F-test

Answer

Shapiro-Wilk test

Question 3

What does the Autocorrelation Function (ACF) measure in time series analysis?

Accepted Answer

The correlation between a time series and a lagged version of itself

Answer

The correlation between two different time series

Answer

The rate of change in a time series over time

Answer

The strength of seasonal patterns in a time series

Question 4

What is the primary purpose of differencing in time series analysis?

Accepted Answer

To make a non-stationary series stationary

Answer

To remove outliers from the data

Answer

To add seasonal components to the model

Answer

To smooth random fluctuations

Question 5

In classical time series decomposition, which component represents patterns that repeat at fixed, known intervals such as monthly or yearly cycles?

Accepted Answer

Seasonal component

Answer

Trend component

Answer

Residual component

Answer

Cyclic component

Question 6

In time series analysis, what characterizes a 'white noise' series?

Accepted Answer

A series of uncorrelated observations with zero mean and constant variance

Answer

A series with a strong upward trend

Answer

A series with high seasonality and regular cycles

Answer

A series that has been differenced exactly once

Question 7

What does the 'I' in ARIMA stand for, and what does it indicate about the model?

Accepted Answer

Integrated — the number of differencing operations applied to achieve stationarity

Answer

Independent — that the error terms are independent of each other

Answer

Interval — the time interval between observations

Answer

Inversed — that the series has been log-transformed