Skip to main content
Cross Validated

Return to Question

added 23 characters in body; edited tags; edited title
Source Link
Richard Hardy
Richard Hardy
  • 69.5k
  • 13
  • 126
  • 278

Is the lag Lag selection in aand Granger causality test: is the predictivemaximum lag the causal lag?

When setting up the Granger causality (Wald) test, I determine the optimum lag using information criterioncriteria AIC, BIC, FPE to test for causality.

  1. What does the lag selection really mean?
  2. IfDoes the selected lag describesdescribe the delay of the Granger cause effect? That is, if I select lag=6$\text{lag}=6$, does that mean that X$X$ Granger causes Y,-causes $Y$ with a delay of 6 time units (say, weeks)?

Is the lag selection in a Granger causality test the predictive lag?

When setting up the Granger causality (Wald) test, I determine the optimum information criterion AIC, BIC, FPE to test for causality.

  1. What does the lag selection really mean?
  2. If the selected lag describes the delay of the Granger cause effect? That is, if I select lag=6, does that mean that X Granger causes Y, with a delay of 6 time units (say, weeks)?

Lag selection and Granger causality: is the maximum lag the causal lag?

When setting up the Granger causality (Wald) test, I determine the optimum lag using information criteria AIC, BIC, FPE to test for causality.

  1. What does the lag selection really mean?
  2. Does the selected lag describe the delay of the Granger cause effect? That is, if I select $\text{lag}=6$, does that mean that $X$ Granger-causes $Y$ with a delay of 6 time units (say, weeks)?
clarified question in title; formatted; removed extra comments
Source Link
gung - Reinstate Monica
gung - Reinstate Monica
  • 147.5k
  • 89
  • 406
  • 717

Granger Causality - Is the lag selection =in a Granger causality test the predictive lag?

I have a short question related to Granger Causality and I wondered if I might find an answer here, though the method is not widely popular.

When setting up the Granger causality (waldWald) test, I determine the optimum information criterion AIC,BIC BIC, FPE to test thefor causality. I wonder what

a) the lag selection really means and b) if the selected lag describes the delay of the Granger cause effect. I.e. if I select lag=6, if that then means that X Granger causes Y, with a delay of 6 time units, i.e. weeks.

  1. What does the lag selection really mean?
  2. If the selected lag describes the delay of the Granger cause effect? That is, if I select lag=6, does that mean that X Granger causes Y, with a delay of 6 time units (say, weeks)?

Granger Causality - lag selection = predictive lag?

I have a short question related to Granger Causality and I wondered if I might find an answer here, though the method is not widely popular.

When setting up the Granger (wald) test, I determine the optimum information criterion AIC,BIC, FPE to test the causality. I wonder what

a) the lag selection really means and b) if the selected lag describes the delay of the Granger cause effect. I.e. if I select lag=6, if that then means that X Granger causes Y, with a delay of 6 time units, i.e. weeks.

Is the lag selection in a Granger causality test the predictive lag?

When setting up the Granger causality (Wald) test, I determine the optimum information criterion AIC, BIC, FPE to test for causality.

  1. What does the lag selection really mean?
  2. If the selected lag describes the delay of the Granger cause effect? That is, if I select lag=6, does that mean that X Granger causes Y, with a delay of 6 time units (say, weeks)?
Source Link
MasterPValue
MasterPValue
  • 33
  • 3

Granger Causality - lag selection = predictive lag?

I have a short question related to Granger Causality and I wondered if I might find an answer here, though the method is not widely popular.

When setting up the Granger (wald) test, I determine the optimum information criterion AIC,BIC, FPE to test the causality. I wonder what

a) the lag selection really means and b) if the selected lag describes the delay of the Granger cause effect. I.e. if I select lag=6, if that then means that X Granger causes Y, with a delay of 6 time units, i.e. weeks.