FRM Part I · FRM Exam Part I · Nonstationary Time Series
An analyst models monthly log sales of a firm as ln(Y_t) = 2.50 + 0.012 t + e_t, where t = 1 for the first month and e_t is a stationary, mean-zero error. Which statement best describes this model?
The model is a log-linear trend: regressing the natural log of sales on time implies a constant proportional growth rate, so a slope of 0.012 means roughly 1.2% growth per month, not a 0.012-unit increase in levels.
- AA log-linear trend model in which sales grow at an approximate constant rate of 1.2% per monthCorrect
- BA linear trend model in which sales rise by 0.012 units each month
- CA random walk with drift of 0.012 per month
- DA quadratic trend model in which the growth rate rises over time
Explanation
Regressing the log of a series on time gives a log-linear trend. The slope 0.012 is the approximate constant proportional growth per period, i.e. 1.2% per month. The linear trend option confuses the slope in logs with a unit change in levels. A random walk with drift has stochastic, not deterministic, trend.
Did you get it right without looking?
One question tells you little. A timed set on Nonstationary Time Series shows your real accuracy, how long you take and where you lose marks.
More Nonstationary Time Series questions
- Which statement best describes the effect of ignoring a structural break in the mean of a stationary series when applying a Dickey-Fuller te…
- An analyst fits the regression Y_t = δ·Y_{t-1} + ε_t to a monthly series of a bond spread and wants to test for a unit root using the Dickey…
- In a Dickey-Fuller regression ΔY_t = γY_{t-1} + ε_t, the estimated γ is −0.060 with a standard error of 0.030. The 5% Dickey-Fuller critical…
- An AR(1) model Y_t = 0.2 + phi Y_{t-1} + e_t is estimated. In the Dickey-Fuller regression of the first difference on the lagged level, the …
- A Dickey-Fuller test is applied to a series that follows a stationary AR(1) with coefficient 0.95 in a sample of only 60 observations. Which…
- A risk team analyzes monthly log values of a series that has a stochastic seasonal pattern. Seasonal differences, Y_t - Y_{t-12}, look stati…