Part 6

Question 1

Nonstationarity + what its graph like

Answer 1

Nonstationarity, especially in the context of stochastic trends, refers to a characteristic of a time series where its statistical properties, such as mean, variance, and autocorrelation, change over time. In simpler terms, a nonstationary series does not have a consistent pattern that remains constant through time

Question 2

deterministic trend + whats its graph like

Answer 2

A deterministic trend in a time series refers to a consistent and predictable pattern of growth or decline that can be described by a mathematical function, without being influenced by random variations

Question 3

Unit roots meaning

Answer 3

Unit roots refers to where the value of one observation is highly dependent on the previous one. This can lead to unpredictable. Detecting roots pivotal as one may assume data is stationary

Question 4

problems that may occur if non-stationary data are used in their levels form (2)

Answer 4

Spurious Regression: When non-stationary variables are used in regression analyses, it can result in a spurious regression. This means the statistical tests might suggest a strong relationship between variables when, in reality, there isn’t one. It occurs because non-stationary data can trend together by chance, making it appear as though there is a meaningful connection between them.

Invalid Test Statistics: Many statistical tests assume the data are stationary. If this assumption is violated, the test statistics (like t-statistics and F-statistics in regression analysis) may not follow their usual distributions, leading to incorrect conclusions about the significance of variables.

Question 5

How do we test for a unit root?

Answer 5

DF - Dickey Fuller

Question 6

For Dickey-Fuller test, if if stat < critical value then …

Answer 6

The null hypothesis of a unit root is rejected in favour of the
stationary alternative if stat < critical value

Question 7

Unit root tests do not perform well if there are ….

Answer 7

Unit root tests do not perform well if there are structural breaks. The tests have low power in such circumstances and are oversized.

Question 8

Augmented dicker fuller and PP give same conclusions as DF?

Answer 8

Yes