Crash Course in Forecasting: Time Series Forecasting Quiz
This article contains quiz questions on the topic of Time Series Forecasting
- What is Time Series Forecasting?
- a. A technique to analyze cross-sectional data
- b. A technique to analyze panel data
- c. A technique to analyze time-dependent data
- d. A technique to analyze spatial data
Answer: c. A technique to analyze time-dependent data
2. What is the purpose of time series forecasting?
- a. To analyze the relationship between two or more variables
- b. To predict future values of a variable based on its past values
- c. To analyze the impact of an intervention on a variable
- d. To forecast the behavior of a variable in a particular market
Answer: b. To predict future values of a variable based on its past values
3. What is the difference between a stationary and non-stationary time series?
- a. Stationary time series have a constant mean and variance over time, while non-stationary time series have a changing mean and variance over time.
- b. Stationary time series have a changing mean and variance over time, while non-stationary time series have a constant mean and variance over time.
- c. Stationary time series have a constant mean over time, while non-stationary time series have a changing mean over time.
- d. Stationary time series have a changing mean over time, while non-stationary time series have a constant mean over time.
Answer: a. Stationary time series have a constant mean and variance over time, while non-stationary time series have a changing mean and variance over time.
4. What is the purpose of differencing in time series forecasting?
- a. To remove the trend and seasonality in a time series
- b. To reduce the number of observations in a time series
- c. To make a non-stationary time series stationary
- d. To smooth out the noise in a time series
Answer: c. To make a non-stationary time series stationary
5. What is the difference between AR and MA models in time series forecasting?
- a. AR models consider the effect of past values of the variable on its current value, while MA models consider the effect of past errors on its current value.
- b. AR models consider the effect of past errors on its current value, while MA models consider the effect of past values of the variable on its current value.
- c. AR models consider the effect of future values of the variable on its current value, while MA models consider the effect of future errors on its current value.
- d. AR models consider the effect of future errors on its current value, while MA models consider the effect of future values of the variable on its current value.
Answer: a. AR models consider the effect of past values of the variable on its current value, while MA models consider the effect of past errors on its current value.
6. What is the difference between ARIMA and SARIMA models in time series forecasting?
- a. ARIMA models are used for non-seasonal time series data, while SARIMA models are used for seasonal time series data.
- b. SARIMA models are used for non-seasonal time series data, while ARIMA models are used for seasonal time series data.
- c. ARIMA models consider the effect of past values of the variable and past errors on its current value, while SARIMA models consider the effect of past values of the variable, past errors, and seasonal factors on its current value.
- d. SARIMA models consider the effect of past values of the variable and past errors on its current value, while ARIMA models consider the effect of past values of the variable, past errors, and seasonal factors on its current value.
Answer: a. ARIMA models are used for non-seasonal time series data, while SARIMA models are used for seasonal time series data.
7. Which of the following is a characteristic of ARIMA models?
- a) It is a non-parametric model
- b) It is a linear model
- c) It requires that the time series be stationary
- d) It is not suitable for seasonal time series
Answer: c) It requires that the time series be stationary
8. Which of the following is a characteristic of exponential smoothing (ES) models?
- a) It can handle non-linear trends
- b) It can handle seasonal time series
- c) It requires that the time series be stationary
- d) It can handle non-monotonic trends
Answer: a) It can handle non-linear trends
9. Which of the following is an advantage of ARIMA models over ES models?
- a) It can handle multiple seasonal periods
- b) It is easier to interpret the parameters
- c) It can handle non-linear trends
- d) It is computationally faster
Answer: a) It can handle multiple seasonal periods
10. Which of the following is true regarding ARIMA and ES models?
- a) ARIMA models always outperform ES models
- b) ES models always outperform ARIMA models
- c) The performance of the models depends on the specific time series being forecasted
- d) ARIMA and ES models have the same forecasting accuracy
Answer: c) The performance of the models depends on the specific time series being forecasted