Two or more non-stationary variables are cointegrated if there is a linear combination of those variables which is stationary.

learn more… | top users | synonyms

1
vote
0answers
14 views

Johanson test conditions and Breusch-Godfrey LM test

I am a student from Belgium and I am making a thesis about the relationship between credit aggregates and property prices. I examine the Granger causality between the two variables and I also do some ...
0
votes
0answers
16 views

VAR / VEC in levels or difference depending on Cointegration

Thanks in advance. I have four I(1) variables I'm trying to model by VAR/VEC. I know that it is only okay to model non-stationary variables in levels only if they are cointegrated. What I would ...
0
votes
0answers
31 views

Cointegration difficulties using Stata

I am working on a time series analysis with 52 quarterly data concerning a variety of possible determinants of CO$_2$ emissions by transport (CO$_2$ taxes, GDP, load factor, transport volume). This ...
0
votes
0answers
18 views

VECM , VAR or Granger causality

In my study, the variables are cointegrated. Now I want to test causality so should I perform VAR, VECM or the Granger causality test?
0
votes
0answers
14 views

Can co-integration be conducted if one of the variables is not of the same order?

All my independent variables are stationary at their levels except one variable which became stationary after first difference i.e. my dependent variable. Can I still conduct co-integration test ?
0
votes
1answer
43 views

Cointegrated series

My problem is this: I have 2 series $y$ and $x$ that I want to verify are cointegrated. So first I verified them with ADF unit root test and revealed that one variable is integrated at first ...
0
votes
0answers
24 views

Modelling a time series with the “optimal” combination of N proxy series

I have a time series T. I also a universe U of time series such that A, B, C ... Q are time series that belong to the universe U. My problem decomposes into the following sub tasks: Find a subset ...
1
vote
0answers
46 views

Raw Prices vs. Daily Return vs. Price Ratio - ADF unit-root test

As the title suggests, I'd like to ask what the difference between using Raw Prices vs. Daily Return vs. Price Ratio in the Augmented Dickey-Fuller unit-root test. The context is that I am trying to ...
1
vote
1answer
87 views

Regression discontinuity design versus panel cointegration

I have a panel data (21 years) and I am trying to figure out whether I should use regression discontinuity design (RDD) or panel cointegration. I do have a randomness in the assignment variable and so ...
0
votes
0answers
119 views

Dynamic Panel models, GMM, STATA

just joined this forum I really appreciate the coperative spirit between members. I have a silly questions but its quite important for me :s Im wirting a paper about the contribution of foreign banks ...
1
vote
2answers
108 views

About the stationarity of a sine wave

I generated two sine wave time series and want to check the stationarity of them. (1) The first time series is short. kpss.test() thinks it is stationary. ...
2
votes
4answers
2k views

Why use vector error correction model?

I am confused about the Vector Error Correction Model (VECM). Technical background: VECM offers a possibility to apply Vector Autoregressive Model (VAR) to integrated multivariate time series. In the ...
6
votes
3answers
154 views

Does zero correlation between 2 differenced series implies no cointegration between original series?

The question is related to this one. In this question @mpiktas gives an answer on why checking correlation is not enough but the answer doesn't seem completely correct to me for the following reason: ...
1
vote
0answers
103 views

Cointegration but no Granger-Causality found

I have found Cointegration based on Engle/ Granger and Johansen. However, Granger-causality is rejected for both variables. How is that possible? According to theory, if x and y are I(1) and ...
0
votes
2answers
177 views

Non-stationary series keep close to each other but correlation between growth rates is ~0 - how is this possible?

I have 2 (monthly) time-series that look like this: Economical intuition suggests that they are positively related and I can see this on the plot but if I compute correlation between their ...
0
votes
0answers
77 views

Handling stationarity issues in proc ucm/state space time series models

Hope I'm able to find someone who can answer this question. The previous one didn't get answered! Proc ucm is the SAS implementation (using state space concepts) to isolate the unobserved trend, ...
0
votes
0answers
29 views

ADF test in R yielding perfect cointegration. How is this possible?

I am using the famous conintegrated pairs tutorial to just different stocks for cointegration. The adf.test yeilds perfect cointegration, which I feel must be incorrect. Here is why: When I run ...
1
vote
1answer
158 views

Johansen test loading matrix

I'm using the URCA package in R to test for cointegration by Johansen's method. Can anyone tell me what the weights (loading ...
1
vote
1answer
54 views

Linear combination of processes yielding higher order of integrarion

Is it possible to have an integrated random walk process by linearly combining finite number of random walks? Is it possible to have a random walk process by linearly combining I(0) processes? ...
2
votes
1answer
419 views

Relationship between cointegration and causality in a VAR/VECM model

I am asking myself how cointegration and causality are related in a VAR/VECM model. Suppose you have two $I(1)$ variables in your 2 dim VAR process which are cointegrated, so there is one ...
0
votes
0answers
156 views

Plot forecasts through vecm by using calendar years

I'm using the library vars in R to plot fanchart and predictions through the vector of error correction model. I have used this ...
1
vote
1answer
134 views

How to tell if the relationship between time series variables changes over time?

Lets start out by saying that I'm a novice with statistics. I'm looking to analyze the relationship between Return on Sales (ROS) and Asset Turnover (TAT) over time to see how they impact firm ...
2
votes
1answer
191 views

Read cointegration relations R

I want to figure out how to read the cointegration relation between 5 cointegrated variables. I present the results down here with r=number of cointegrated equations is 3. Variables are normalized ...
1
vote
0answers
55 views

How can I perform a familywise error rate correction for Johansen cointegration tests?

I want to test multiple possible cointegration relationships with the Johansen cointegration test. I'm currently using the urca package in R with the ca.jo test. I was going to use the Bonferroni ...
3
votes
0answers
115 views

Cointegration structure

I have two time series that I am investigating, acc and amb, the time frequency is daily data. They are both non stationary, as evidenced by the follows: ...
1
vote
0answers
112 views

PCA of cointegrated variables

In Optimal Hedging Using Cointegration, C. Alexander, 1999 (http://www.icmacentre.ac.uk/pdf/cointegration.pdf), page 3, footnote #2: [...] a PCA of cointegrated variables will yield the common ...
0
votes
1answer
125 views

Cointegration of a VAR(1) process

I am using a Johansen procedure to test for cointegration a vectorial 4-dim vector (timeserie). First I tested for differential stationarity of each individual vector, all of those have a unit root ...
0
votes
0answers
47 views

cointegration - mixing S & NS regressors; how to test for stationarity; so on

I would like to model a non-stationary variables as a function of 2 other non-stationary variables, in addition to two stationary variables and several dummy variables. The NS dependent variable and ...
2
votes
1answer
136 views

Help for Johansen cointegrating vectors test

I used the Johansen cointegrating procedure to see how many cointegrating vectors are available in the long run and obtained ONE cointegrating vector from Maximum Eigenvalue statistic and FOUR ...
1
vote
1answer
400 views

Constructing a VECM with a mix of I(0) and I(1) variables

I've been using the Johansen Procedure to check and correct for cointegration in my model, by estimating a VECM instead of VAR. But now I want to estimate a new model, in which I expect the same ...
0
votes
1answer
192 views

Error correction model (to test for asymmetry) with stationary I(0) variables

I have price series which are all stationary without taking any difference --> I(0). Can I still perform an ECM model to test for asymmetry? For example: Y= constant X; taking the residuals and ...
0
votes
0answers
173 views

How do i interpret Johansen's test? (Matlab)

I found several similar questions with no answer. But I'm gonna give it a shot anyway. I'm trying to find assets (stocks) which are co-integrated, since Engle-Granger's test may give cause to ...
0
votes
0answers
775 views

how do i interpret trace statistic of Johansen's cointegration test?

how do i interpret the results of the Johansen cointegration test if the result from my STATA output fails to accept both null hypotheses of r=0 and r<=1 ? for example: STATA Screenshot can i ...
1
vote
2answers
240 views

Johansen's $\Pi$ is full rank except variables are non-stationary

I have two variables. They're both $I(1)$ even when I fit constant and trend terms into the ADF test. The $p$-values for the stationarity tests are around 0.5 so it's not a marginal case. However, ...
1
vote
2answers
371 views

Johansen cointegration test with stationary variables

Journals and books about the Johansen cointegration test suggest that only I(1) variables should be put into a cointegration test. However many journals modelling economic growth and inflation use two ...
1
vote
0answers
20 views

Is is ok to use credit spreads to account for a drop in time series for vector error correction model?

I am doing a time series analysis on a quarterly basis from 1990 to the third quarter 2012. Some of the time series had a drop in 2008 because of recession then resumed upwards. This drop is rather ...
1
vote
0answers
175 views

Difference between unrestricted VECM and restricted VECM?

What's the difference between an unrestricted and a restricted VECM? I believe a hint lies within the cajorls()[1] function of R language's ...
1
vote
2answers
184 views

Putting stationary variables through Johansen procedure

Is it okay to feed $I(0)$ variables into the Johansen procedure? I've read three sources that seem to state that this is not what you're supposed to do. However, whenever I've done this, I notice that ...
1
vote
1answer
403 views

Vector error correction model

I am working on finding the relationship between equity, gold, crude oil, and currency value. I used the Johanson cointegration test. Trace test indicates 4 cointegrating equations at the 0.05 level. ...
1
vote
1answer
606 views

Cointegration testing with a dummy variable

I have the model: $y_t = \alpha + \beta_1 x_t + \beta_2 D_t x_t + \epsilon_t$ With $y_t$ and $x_t$ as $I(1)$ processes, and $D_t =1$ during a large financial crisis, $D_t = 0$ during non-crisis ...
0
votes
0answers
147 views

Can we use IPS test with Kao test?

I have a question about using panel unit root test and panel co integration test. I used IPS unit root test then I realized my variables are I(1) can I now use kao co-integration test for checking ...
-2
votes
1answer
347 views

How to conduct Johanson's cointegration test with variables stationary at I(0)?

How do you interpret the Johanson's cointegration test if you are doing Granger causality and both variables are stationary at I(0)?
0
votes
0answers
153 views

Cointegration regression - how to solve sensitivity to ordering of variables

I have a few variables, $A$, $B$, $C$, $D$, and $E$. To find their cointegration coefficients, $A$ is regressed against $B$, $C$, $D$, and $E$. $$ A = W_b * B + W_c * C + W_d * D + W_e * E + W0 $$ ...
0
votes
1answer
210 views

Testing threshold cointegration in vector error-correction models

In Hansen and Seo's paper on Testing two regime threshold cointegration in VECM (J. Econometrics, 2002; 110:293), the authors proposed a test based on Lagrange Multiplier for testing treshold in ...
2
votes
0answers
166 views

Computing (lagged) correlations (or similar) between multiple time-series from a VECM or its levels-VARM

Ok, after trying to find a way to get all lagged and non-lagged - correlations from multiple time-series (behavioral series with length around 180) I've confined myself to the following: I have ...
2
votes
0answers
125 views

Is is correct to compare t-statistics of different pairs of cointegrated timeseries?

I am testing for cointegration all the pairs from a set of 100 stocks. I run an Ordinary Least Square Regression on each pair and then I test for the existence of unit roots in the residuals. I am ...
4
votes
3answers
500 views

What does that mean that two time series are colinear?

I am familiar with the concept of cointegration. But I hear sometimes people talking about colinearity (or collinearity) for time series. A set of points is collinear if they are on the same line. ...
0
votes
2answers
204 views

Question about cointegration

I was reading about cointegration (page 5) and it said "If a linear combination of combination of a set of $I(1)$ variables is $I(0)$, then the variables are cointegrated." Does this mean ...
1
vote
0answers
104 views

Non parametric cointegration test in R

I am not very comfortable with the (parametric) assumptions made in cointegration analysis. I have recently found that there is a way to carry out nonparametric conintegration analysis (a google ...
2
votes
2answers
273 views

How to check if a time series is I(1) in R?

I'm testing the cointegration of two time series of stock prices using adfTest from fUnitRoots, but first I need to check if the series are I(1). How can I check if a time series is I(1)?