ISYE 6402 Exam 2: Time Series Analysis
Verified and Latest Questions and Answers -
Georgia Tech
1. In an ARIMA(p, d, q) model, what does the parameter ‘d’ signify?
A. The order of the autoregressive part
B. The order of the moving average part
C. The degree of differencing required for stationarity
D. The seasonal period length
Answer: C
Explanation: The parameter ‘d’ represents the number of times the series is differenced to
achieve stationarity.
2. Which plot is primarily used to identify the order ‘p’ of an AR(p) process?
A. Autocorrelation Function (ACF)
B. Partial Autocorrelation Function (PACF)
C. Periodogram
D. Normal Q-Q Plot
Answer: B
Explanation: For an AR(p) process, the PACF cuts off after lag p, making it the primary tool
for identifying the order p.
,3. If the ACF of a series shows a slow linear decay, what is likely true about the
series?
A. It is non-stationary and requires differencing
B. It is stationary
C. It is a white noise process
D. It is an MA(1) process
Answer: A
Explanation: A slow decay in ACF is a classic indicator of non-stationarity, suggesting a
unit root or trend that requires differencing.
4. Which criterion penalizes model complexity more heavily, leading to more
parsimonious models?
A. AIC (Akaike Information Criterion)
B. AICC (Corrected AIC)
C. RMSE (Root Mean Squared Error)
D. BIC (Bayesian Information Criterion)
Answer: D
Explanation: BIC has a larger penalty term (log(n) vs 2) compared to AIC, which favors
simpler models as sample size increases.
5. What is the primary characteristic of an ARCH model?
A. It models the conditional mean as a function of past errors
B. It is used solely for seasonal adjustment
C. It assumes constant variance over time
D. It models the conditional variance as a function of past squared errors
Answer: D
Explanation: ARCH models address volatility clustering by modeling the conditional
variance based on previous squared residuals.
, 6. In a SARIMA(p,d,q)x(P,D,Q)s model, what does ‘s’ represent?
A. The significance level
B. The number of observations per season
C. The standard deviation
D. The smoothing constant
Answer: B
Explanation: ‘s’ represents the seasonal period, such as 12 for monthly data or 4 for
quarterly data.
7. Which test is commonly used to check for the presence of a unit root?
A. Ljung-Box Test
B. Shapiro-Wilk Test
C. Augmented Dickey-Fuller (ADF) Test
D. Durbin-Watson Test
Answer: C
Explanation: The ADF test is used to test the null hypothesis that a unit root is present in a
time series sample, indicating non-stationarity.
8. What is the ‘invertibility’ condition for an MA(1) process: Yt = et + theta*et-1?
A. theta > 0
B. |theta| > 1
C. theta = 0
D. |theta| < 1
Answer: D
Explanation: For an MA(1) process to be invertible, the absolute value of the coefficient
theta must be less than 1.
Verified and Latest Questions and Answers -
Georgia Tech
1. In an ARIMA(p, d, q) model, what does the parameter ‘d’ signify?
A. The order of the autoregressive part
B. The order of the moving average part
C. The degree of differencing required for stationarity
D. The seasonal period length
Answer: C
Explanation: The parameter ‘d’ represents the number of times the series is differenced to
achieve stationarity.
2. Which plot is primarily used to identify the order ‘p’ of an AR(p) process?
A. Autocorrelation Function (ACF)
B. Partial Autocorrelation Function (PACF)
C. Periodogram
D. Normal Q-Q Plot
Answer: B
Explanation: For an AR(p) process, the PACF cuts off after lag p, making it the primary tool
for identifying the order p.
,3. If the ACF of a series shows a slow linear decay, what is likely true about the
series?
A. It is non-stationary and requires differencing
B. It is stationary
C. It is a white noise process
D. It is an MA(1) process
Answer: A
Explanation: A slow decay in ACF is a classic indicator of non-stationarity, suggesting a
unit root or trend that requires differencing.
4. Which criterion penalizes model complexity more heavily, leading to more
parsimonious models?
A. AIC (Akaike Information Criterion)
B. AICC (Corrected AIC)
C. RMSE (Root Mean Squared Error)
D. BIC (Bayesian Information Criterion)
Answer: D
Explanation: BIC has a larger penalty term (log(n) vs 2) compared to AIC, which favors
simpler models as sample size increases.
5. What is the primary characteristic of an ARCH model?
A. It models the conditional mean as a function of past errors
B. It is used solely for seasonal adjustment
C. It assumes constant variance over time
D. It models the conditional variance as a function of past squared errors
Answer: D
Explanation: ARCH models address volatility clustering by modeling the conditional
variance based on previous squared residuals.
, 6. In a SARIMA(p,d,q)x(P,D,Q)s model, what does ‘s’ represent?
A. The significance level
B. The number of observations per season
C. The standard deviation
D. The smoothing constant
Answer: B
Explanation: ‘s’ represents the seasonal period, such as 12 for monthly data or 4 for
quarterly data.
7. Which test is commonly used to check for the presence of a unit root?
A. Ljung-Box Test
B. Shapiro-Wilk Test
C. Augmented Dickey-Fuller (ADF) Test
D. Durbin-Watson Test
Answer: C
Explanation: The ADF test is used to test the null hypothesis that a unit root is present in a
time series sample, indicating non-stationarity.
8. What is the ‘invertibility’ condition for an MA(1) process: Yt = et + theta*et-1?
A. theta > 0
B. |theta| > 1
C. theta = 0
D. |theta| < 1
Answer: D
Explanation: For an MA(1) process to be invertible, the absolute value of the coefficient
theta must be less than 1.
