## Questions and Answers

Why is testing for non-stationarity important in regression analysis?

Non-stationary variables can lead to spurious regressions with high R2 values, even if the variables are unrelated.

Which model characterizes non-stationarity as a random walk with drift?

$y_t = \mu + y_{t-1} + u_t$

What happens to the standard assumptions for asymptotic analysis if the variables in a regression model are non-stationary?

The standard assumptions for asymptotic analysis will not be valid.

What is the general form of an explosive process in the given context?

Signup and view all the answers

What does a value of $\phi > 1$ indicate in the context of non-stationarity?

Signup and view all the answers

What is required to induce stationarity in the case of deterministic non-stationarity?

Signup and view all the answers

What is the characteristic of an I(2) series?

Signup and view all the answers

What is the basic objective of testing for a unit root in time series?

Signup and view all the answers

What does an I(0) series indicate?

Signup and view all the answers

What does an I(1) series indicate?

Signup and view all the answers

What does an I(2) series indicate?

Signup and view all the answers

What are the characteristics of I(0), I(1), and I(2) series?

Signup and view all the answers

How do we generalize the concept of a non-stationary series?

Signup and view all the answers

Non-stationary series can lead to spurious regressions, where a regression of one variable on another could have a high R2 even if the two are totally unrelated.

Signup and view all the answers

The random walk model with drift is given by the equation $y_t = \mu + y_{t-1} + u_t$ where $u_t$ is an iid process.

Signup and view all the answers

If the variables in a regression model are not stationary, the standard assumptions for asymptotic analysis will not be valid, and the usual t-ratios will not follow a t-distribution.

Signup and view all the answers

There are two models frequently used to characterize non-stationarity: the random walk model with drift and the deterministic trend process.

Signup and view all the answers

An I(2) series contains two unit roots and so would require differencing twice to induce stationarity.

Signup and view all the answers

Detrending a stochastic non-stationary series involves differencing the series to induce stationarity.

Signup and view all the answers

The model $y_t = \mu + \phi y_{t-1} + u_t$ characterizes the non-stationarity as an explosive process when $\phi > 1$.

Signup and view all the answers

A series that is integrated of order $d$ is said to be $I(d)$.

Signup and view all the answers

If a non-stationary series $y_t$ must be differenced $d$ times before it becomes stationary, then it is said to be integrated of order $d$.

Signup and view all the answers

The basic objective of testing for a unit root in time series is to test the null hypothesis that $\phi = 1$ in the model $y_t = \phi y_{t-1} + u_t$.

Signup and view all the answers

An I(0) series is a non-stationary series that contains no unit roots and is already stationary.

Signup and view all the answers

If $\phi > 1$, shocks to the system are not only persistent through time, they are also propagated, leading to an increasingly large influence.

Signup and view all the answers

Consumer prices have been argued to have 2 unit roots, indicating a high degree of non-stationarity.

Signup and view all the answers

The majority of economic and financial series contain a single unit root, making them $I(1)$ series.

Signup and view all the answers

The second case, $yt = \mu + yt-1 + u_t$, is known as deterministic non-stationarity and requires detrending to induce stationarity.

Signup and view all the answers

The first difference operator, $\Delta$, is used to induce stationarity in a non-stationary series.

Signup and view all the answers