MCQs

Disclaimer:

Educational Use Only:

The website links provided are to be used strictly for educational and knowledge-gaining purposes only.

No Misuse:

Do not misuse the links or the information contained therein for any commercial, illegal, or unethical activities.

Respect for Websites and Businesses:

Respect the intellectual property and business interests of the websites and their owners. Do not attempt to alter, copy, or redistribute content without proper authorization.

Acknowledge Value of Knowledge:

Recognize and value the knowledge and resources shared by these websites. Use the information responsibly and ethically.

No Endorsement:

The provision of these links does not imply endorsement of the linked sites, their content, or their products and services. Users are responsible for evaluating the suitability and accuracy of the information.

User Responsibility:

By accessing these links, you agree to use the information at your own risk and to comply with all applicable laws and website terms of use.

Overall MCQs for Reference

Which component of ARIMA is identified using the partial autocorrelation function (PACF) plot?
a. Moving Average (MA)
b. Autoregressive (AR)
c. Differencing (I)
d. Seasonality
Answer: b. Autoregressive (AR)geeksforgeeks+1
What does the parameter ‘d’ represent in ARIMA(p, d, q)?
a. AR order
b. Differencing order
c. MA order
d. Season length
Answer: b. Differencing orderapxml+2
Which plot helps determine the MA order (q) in manual ARIMA selection?
a. Line plot
b. PACF plot
c. ACF plot
d. Histogram
Answer: c. ACF plotgeeksforgeeks+1
In the context of ARIMA, what is ‘stationarity’?
a. Data with constant trend
b. Data with consistent seasonality
c. Data with constant mean and variance over time
d. Data without random noise
Answer: c. Data with constant mean and variance over timeapxml+1
What is the first step in manually selecting ARIMA parameters?
a. Model fitting
b. Determine stationarity
c. Calculate AIC
d. Grid search
Answer: b. Determine stationaritygeeksforgeeks+1
The primary purpose of differencing in ARIMA is to:
a. Remove seasonality
b. Make the series stationary
c. Reduce noise
d. Increase forecast accuracy
Answer: b. Make the series stationaryapxml+1
When PACF cuts off after lag k and ACF tails off, what ARIMA order is suggested?
a. AR(k)
b. MA(k)
c. ARMA(1,1)
d. SARIMA
Answer: a. AR(k)people.duke+1
How do you determine the minimum differencing required?
a. ACF plot inspection
b. Unit root test or visual inspection
c. Grid search
d. Cross-validation
Answer: b. Unit root test or visual inspectionmachinelearningplus+1
What indicates that further differencing may be needed after first differencing?
a. Series becomes stationary
b. Remaining trend in the series
c. Residuals are white noise
d. Low AIC
Answer: b. Remaining trend in the seriesgeeksforgeeks+1
Over-differencing the series may cause:
a. Loss of information and poor forecasting
b. High accuracy
c. Better residuals
d. Model simplicity
Answer: a. Loss of information and poor forecastingmilvus+1
What criterion is commonly used to compare manually fitted ARIMA models?
a. RMSE
b. MAPE
c. AIC (Akaike Information Criterion)
d. Variance
Answer: c. AIC (Akaike Information Criterion)linkedin+2
When both ACF and PACF tail off, which ARIMA model is recommended?
a. AR model
b. MA model
c. ARMA model
d. SARIMA model
Answer: c. ARMA modelpeople.duke+1
What should the residuals of a good ARIMA model resemble?
a. Trend pattern
b. White noise
c. Seasonal variation
d. Linear growth
Answer: b. White noisemachinelearningplus+1
To select parameter ‘p’ manually, you look for:
a. ACF cut-off point
b. PACF cut-off point
c. Minimum RMSE
d. Maximum AIC
Answer: b. PACF cut-off pointapxml+1
Which process is often used for structured parameter testing in manual ARIMA?
a. Random forest algorithm
b. Grid search of (p, d, q)
c. Neural networks
d. PCA
Answer: b. Grid search of (p, d, q)linkedin+1
If the ACF “cuts off” after lag 2 and PACF “tails off,” what model component is likely present?
a. MA(2)
b. AR(2)
c. Differencing needed
d. No ARMA needed
Answer: a. MA(2)people.duke+1
What is the result of under-differencing a time series?
a. Stationary series
b. Persistent trends remain
c. Overfitting
d. Lower complexity
Answer: b. Persistent trends remaingeeksforgeeks+1
Which test is typically used to assess stationarity before ARIMA modeling?
a. Jarque-Bera test
b. Augmented Dickey-Fuller test
c. Shapiro-Wilk test
d. Levene’s test
Answer: b. Augmented Dickey-Fuller testmachinelearningplus+1
In ARIMA, an appropriate value for q is suggested by:
a. ACF cut-off after lag q
b. PACF cut-off after lag p
c. Grid search outputs
d. Visualization only
Answer: a. ACF cut-off after lag qapxml+1
What happens if both p and q are too high?
a. Simpler model
b. Overfitting and loss of generalization
c. Better forecast
d. Underfitting
Answer: b. Overfitting and loss of generalizationdataaspirant+1
What does ‘parsimonious model’ mean in ARIMA selection?
a. Model with maximum parameters
b. Model with minimal necessary parameters
c. Model with all lags included
d. Model with no differencing
Answer: b. Model with minimal necessary parameterscorporatefinanceinstitute+1
If residuals display autocorrelation, what does it suggest?
a. Model properly fit
b. Need for model refinement
c. Stationary data
d. Lower AIC
Answer: b. Need for model refinementmachinelearningplus+1
What makes AIC a preferred criterion for model selection?
a. Only measures fit
b. Balances goodness of fit and complexity
c. Computes autocorrelation
d. Uses differencing only
Answer: b. Balances goodness of fit and complexitylinkedin+2
During manual parameter selection, what does the term ‘diagnostics’ refer to?
a. Model scoring
b. Residual analysis and checking assumptions
c. Feature selection
d. Random error
Answer: b. Residual analysis and checking assumptionsmachinelearningplus+1
If ACF and PACF both show sharp cut-offs at the same lag, what can you suspect?
a. Pure AR process
b. Pure MA process
c. Over-differencing
d. ARMA process
Answer: d. ARMA processpeople.duke+1
Manual grid search in ARIMA parameter selection aims to:
a. Automate modeling
b. Test combinations of (p, d, q) for best fit
c. Assess seasonal order only
d. Reduce forecast interval
Answer: b. Test combinations of (p, d, q) for best fitlinkedin+1
What is the best strategy to avoid overfitting during manual selection?
a. Use maximum lags
b. Use information criteria like AIC/BIC for balance
c. Eliminate residuals
d. Ignore diagnostics
Answer: b. Use information criteria like AIC/BIC for balancelinkedin+2
Why are lower orders for p and q usually attempted first?
a. Simpler models are more interpretable and less prone to overfitting
b. Simpler models always fail
c. Computational reasons only
d. Easier plot reading
Answer: a. Simpler models are more interpretable and less prone to overfittingapxml
What should be checked after fitting each ARIMA candidate model?
a. Seasonality
b. Residual plots for randomness
c. Forecast horizon
d. Data volume
Answer: b. Residual plots for randomnessmachinelearningplus+1
Which information criterion is an alternative to AIC for ARIMA selection?
a. RMSE
b. MAPE
c. BIC (Bayesian Information Criterion)
d. MAE
Answer: c. BIC (Bayesian Information Criterion)geeksforgeeks+2
What is a likely outcome of including unnecessary lag terms (overparameterization)?
a. Parsimonious model
b. Loss of degrees of freedom and increased variance
c. Simpler diagnostics
d. White noise residuals
Answer: b. Loss of degrees of freedom and increased variancecorporatefinanceinstitute+1
Which ARIMA parameter helps capture shocks in the data?
a. p
b. d
c. q
d. S
Answer: c. qmilvus+1
Why is seasonality handled separately in ARIMA modeling?
a. ARIMA can only capture trends
b. Seasonality requires seasonal differencing or SARIMA extension
c. It is unnecessary for AI solutions
d. It reduces differencing requirement
Answer: b. Seasonality requires seasonal differencing or SARIMA extensionscribd+1
What process is often needed after selecting an initial ARIMA model?
a. Hyperparameter tuning with neural networks
b. Model refinement by manually adjusting parameters and checking diagnostics
c. PCA
d. Data normalization
Answer: b. Model refinement by manually adjusting parameters and checking diagnosticslinkedin+1
If the best model according to AIC still has autocorrelated residuals, what should you do?
a. Accept the model
b. Adjust p or q and refit
c. Change dataset
d. Add noise
Answer: b. Adjust p or q and refitapxml+1
A time series with a consistent increasing trend that persists after first differencing likely needs:
a. More AR lags
b. MA term
c. Second differencing (d = 2)
d. Abandonment for ARIMA
Answer: c. Second differencing (d = 2)machinelearningplus+1
Which ARIMA parameter(s) should be kept low if data length is short?
a. Only p
b. Only q
c. All: p, d, and q
d. Only d
Answer: c. All: p, d, and qgeeksforgeeks+1
What is indicated by a slowly decaying ACF in the raw series?
a. Stationary process
b. Strong trend, need for differencing
c. Overfitting
d. Correct model
Answer: b. Strong trend, need for differencinggeeksforgeeks+1
For ARIMA, ACF and PACF diagnostics after fitting should show:
a. Significant lags
b. White noise pattern after model fit
c. Trend remains
d. High correlation
Answer: b. White noise pattern after model fitapxml+1
Why is manual ARIMA parameter selection sometimes preferred over automated approaches?
a. More interpretability and better understanding of model assumptions
b. Faster computation
c. Always gives the best model
d. Not preferred
Answer: a. More interpretability and better understanding of model assumptionslinkedin+1
What does the ‘I’ in ARIMA address when modeling a time series?
a. Overfitting
b. Trend and non-stationarity
c. Randomness
d. Seasonality only
Answer: b. Trend and non-stationaritygeeksforgeeks+1
When parameter p is set too high, the model may:
a. Underfit the data
b. Feel random errors only
c. Overfit, reducing generalization on future data
d. Minimize variance
Answer: c. Overfit, reducing generalization on future datacorporatefinanceinstitute+1
The process of checking that residuals are “white noise” after model fitting is called:
a. Forecasting
b. Model diagnostics
c. Differencing
d. Data normalization
Answer: b. Model diagnosticsmachinelearningplus+1
If an ARIMA(1,1,1) still shows autocorrelation in residuals, what’s the next step?
a. Increase d and refit
b. Increase or decrease p or q and recheck
c. Ignore
d. Remove seasonality
Answer: b. Increase or decrease p or q and recheckapxml+1
Which ARIMA parameter directly relates to the number of past errors included?
a. p
b. d
c. q
d. S
Answer: c. qmilvus+1
The best ARIMA model is found manually by:
a. Choosing the highest AIC model
b. Trying various (p, d, q) and comparing model metrics
c. Always setting d=1
d. Not checking residuals
Answer: b. Trying various (p, d, q) and comparing model metricslinkedin+2
Before manual parameter tuning, time-series should be:
a. Highly volatile
b. Stationary, or transformed to be stationary
c. Non-stationary indefinitely
d. Filtered by PCA first
Answer: b. Stationary, or transformed to be stationarymachinelearningplus+2
The ACF of the differenced series is important for determining:
a. p
b. d
c. q
d. S
Answer: c. qgeeksforgeeks+1
Manual ARIMA selection contributes to:
a. Overfitting
b. Model transparency and interpretability
c. Greater forecast variance always
d. No improvement
Answer: b. Model transparency and interpretabilitylinkedin
After the best ARIMA model is selected, what is the final check before forecasting?
a. Plot the residuals and confirm no significant autocorrelation
b. Increase model order
c. Always choose AIC regardless of other diagnostics
d. Ignore model complexity
Answer: a. Plot the residuals and confirm no significant autocorrelationapxml+1

Blog

Systemethic Technologies

Leave a Reply Cancel reply

Useful links

Other Terms & Policies

Contact Info