Which Dickey-Fuller test should I apply to this time series?

AI Thread Summary
The discussion centers on the appropriate application of the Dickey-Fuller test for a time series of climate data suspected to be non-stationary. The user is testing for unit roots while considering an underlying model with an intercept and a positive linear time trend. They express uncertainty about whether to use the Dickey-Fuller test that includes both an intercept and a trend, or just an intercept, given that the first difference appears to only have an intercept. Clarification is sought on the implications of using a trend term in the test, particularly regarding its relationship to quadratic trends. The conversation highlights the complexity of determining the correct test based on the characteristics of the time series data.
pythonscript
Messages
6
Reaction score
0
I have a time series of climate data that I'm testing for stationarity. Based on previous research, I expect the model underlying the data to have an intercept term, a positive linear time trend, and some normally distributed error term. In other words, I expect the underlying model to look something like this:

yt = a0 + a1t + β yt-1 + ut $

where ut is normally distributed. Since I'm assuming the underlying model has both an intercept and a linear time trend, I tested for a unit root with equation #3 of the simple Dickey-Fuller test, as shown:

∇yt = α01t+δ yt-1+ut

This test returns a critical value that would lead me to reject the null hypothesis and conclude that the underlying model is non-stationary. However, I question if I'm applying this correctly, since even though the underlying model is assumed to have an intercept and a time trend, this does not imply that the first difference ∇yt will as well. Quite the opposite, in fact, if my math is correct.

Calculating the first difference based on the equation of the assumed underlying model gives:
∇yt = yt - yt-1 = [a0 + a1 + β yt-1 + ut] - [a0 + a1(t-1) + β yt-2 + ut-1]

∇yt = [a0 - a0] + [a1t - a1(t-1)] + β[yt-1 - yt-2] + [ut - ut-1]

∇yt = a1 + β * ∇yt-1 + ut - ut-1$

Therefore, the first difference ∇yt appears to only have an intercept, not a time trend.

Because the underlying model has an intercept and a time trend, should I use the Dickey-Fuller test that includes an intercept and time trend when it tests for a unit root, or should I use the Dickey-Fuller test that only includes an intercept because the first difference of the original time series only has an intercept?
 
Mathematics news on Phys.org
You are correct that the difference operation a linear trend term (k)(t) produces a constant, not another linear trend term.

It's interesting to try to read that Wikipedia article you linked. It's about some hypothesis tests, but it never manages to state the null hypotheses and the test statistics. Apparently you understand the test statistics - which is more than I know.

However, I did find this page: http://stats.stackexchange.com/questions/18133/selecting-regression-type-for-dickey-fuller-test where the reply mentions that using the test with term of the form (k)(t) implies we are investigating a model with a quadratic trend. So my guess is that you don't use that form to test your null hypothesis.
 
As far as I know, the null hypothesis is that a unit root exists and that the process is therefore stationary. I had found that thread you linked, and I'm the user who started the short but ongoing discussion in the comments. The linked post (listed in the right-hand column) is also mine, and is quite similar to my post here.

http://stats.stackexchange.com/q/44647

I don't understand why using a test with a trend term a1t would be used with a quadratic term, however. Can you shed any light on that?
 
The only light I can shed is that if f(t) = kt^2 then
\triangle f(t) = f(t+1) - f(t) = k(t+1)^2 - kt^2 = k( t^2 + 2t + 1) - kt^2 = 2kt + k
So the \triangle of a model with a t^2 term has a term linear in t.
 
Suppose ,instead of the usual x,y coordinate system with an I basis vector along the x -axis and a corresponding j basis vector along the y-axis we instead have a different pair of basis vectors ,call them e and f along their respective axes. I have seen that this is an important subject in maths My question is what physical applications does such a model apply to? I am asking here because I have devoted quite a lot of time in the past to understanding convectors and the dual...
Insights auto threads is broken atm, so I'm manually creating these for new Insight articles. In Dirac’s Principles of Quantum Mechanics published in 1930 he introduced a “convenient notation” he referred to as a “delta function” which he treated as a continuum analog to the discrete Kronecker delta. The Kronecker delta is simply the indexed components of the identity operator in matrix algebra Source: https://www.physicsforums.com/insights/what-exactly-is-diracs-delta-function/ by...

Similar threads

Replies
4
Views
2K
Replies
8
Views
3K
Replies
8
Views
2K
Replies
3
Views
2K
Replies
4
Views
5K
Replies
2
Views
2K
Replies
5
Views
2K
Replies
5
Views
3K
Back
Top