IAI Actuarial Core Principles · Risk Modelling and Survival Analysis · Applications of time series models
Consider the AR(2) process X_t = 1.2 X_{t-1} - 0.2 X_{t-2} + e_t. Which statement is correct?
The process is non-stationary because the characteristic polynomial 1 - 1.2z + 0.2z² has a root at z = 1, a unit root. The other root is 5, but one root on the unit circle is enough to break stationarity.
- AIt is stationary because both roots of the characteristic polynomial lie outside the unit circle
- BIt is stationary because the coefficients sum to less than 2
- CIt is non-stationary because one root of 1 - 1.2z + 0.2z^2 equals 1Correct
- DIt is non-stationary because the second coefficient is negative
- It is stationary because the coefficient of X_{t-1} exceeds 1
Explanation
The characteristic polynomial is 1 - 1.2z + 0.2z^2. At z=1 it gives 1 - 1.2 + 0.2 = 0, so z=1 is a root (the other is z=5). A root on the unit circle means a unit root, so the process is non-stationary. The negative coefficient is irrelevant.
Did you get it right without looking?
One question tells you little. A timed set on Applications of time series models shows your real accuracy, how long you take and where you lose marks.
More Applications of time series models questions
- A time series Y_t is described as ARIMA(1,1,0). Which statement correctly describes the process?
- An MA(1) process is X_t = e_t + 0.5 e_{t-1}, where e_t is white noise with variance 2. What is the autocorrelation at lag 1 and at lag 2?
- An analyst fits an ARIMA model to monthly claim counts and finds the sample autocorrelation function of the raw series decays very slowly fr…
- For an AR(2) process X_t = 0.5 X_{t-1} + 0.2 X_{t-2} + e_t, the lag-1 autocorrelation rho_1 is obtained from the Yule-Walker equations. What…
- In the Box-Jenkins approach to fitting an ARIMA model to a time series, which sequence of stages is correct?
- Consider the process Y_t = 1.5 Y_{t-1} - 0.5 Y_{t-2} + e_t, with e_t white noise. Which statement is correct?