Skip to main content
deleted 2 characters in body
Source Link
Andy
  • 19.3k
  • 20
  • 86
  • 104

Consider G-Causality on two stationary time series vectors (call these variables $X$ and $Y$), each with 100+ observations. It's daily financial market time series data. I have reason to believe that there's reverse causality between these two variables (i.e., $X$ causes $Y$ as well as $Y$ causes $X$).

I want to know the current consensus (or nearing consensus) regarding the best method of selecting lag length I want to know the current consensus (or nearing consensus) regarding the best method of selecting lag length. 

A Google search has only revealed some 1984 and 1985 papers. Scholarpedia's entry on Granger causality says that it's O.K. to minimise AIC or BIC, but no references were provided for this claim so I don't want to code that up until I get confirmation.

  Or is selection based on qualitative reasoning?

Disclaimer: Cross posted on talkstats.com.

Consider G-Causality on two stationary time series vectors (call these variables $X$ and $Y$), each with 100+ observations. It's daily financial market time series data. I have reason to believe that there's reverse causality between these two variables (i.e., $X$ causes $Y$ as well as $Y$ causes $X$).

I want to know the current consensus (or nearing consensus) regarding the best method of selecting lag length. A Google search has only revealed some 1984 and 1985 papers. Scholarpedia's entry on Granger causality says that it's O.K. to minimise AIC or BIC, but no references were provided for this claim so I don't want to code that up until I get confirmation.

  Or is selection based on qualitative reasoning?

Disclaimer: Cross posted on talkstats.com.

Consider G-Causality on two stationary time series vectors (call these variables $X$ and $Y$), each with 100+ observations. It's daily financial market time series data. I have reason to believe that there's reverse causality between these two variables (i.e., $X$ causes $Y$ as well as $Y$ causes $X$).

I want to know the current consensus (or nearing consensus) regarding the best method of selecting lag length. 

A Google search has only revealed some 1984 and 1985 papers. Scholarpedia's entry on Granger causality says that it's O.K. to minimise AIC or BIC, but no references were provided for this claim so I don't want to code that up until I get confirmation. Or is selection based on qualitative reasoning?

Disclaimer: Cross posted on talkstats.com.

Tweeted twitter.com/#!/StackStats/status/234980658680836096
edited title
Link
user88
user88

Granger causality: Lag length selection Granger causality test

added 49 characters in body; edited tags; edited title
Source Link
chl
  • 54.3k
  • 23
  • 227
  • 388

Granger Causalitycausality: Lag length selection

Consider G-Causality on two stationary time series vectors (call these variables X$X$ and Y$Y$), each with 100+ observations. It's daily financial market time series data. I have reason to believe that there's reverse causality between these two variables (i.e., X$X$ causes Y$Y$ as well as Y$Y$ causes X$X$).

I want to know the current consensus (or nearing consensus) regarding the best method of selecting lag length. A Google search has only revealed some 1984 and 1985 papers. Scholarpedia's entry on (http://www.scholarpedia.org/article/Granger_causality#Stationarity)Granger causality says that it's O.K. to minimise AIC or BIC, but no references were provided for this claim so I don't want to code that up until I get confirmation.

Or is selection based on qualitative reasoning?

Disclaimer: Cross posted here:on http://www.talkstats.com/showthread.php/27425-Granger-Causality-Lag-length-selectiontalkstats.com.

Granger Causality: Lag length selection

Consider G-Causality on two stationary time series vectors (call these variables X and Y), each with 100+ observations. It's daily financial market time series data. I have reason to believe that there's reverse causality between these two variables (i.e. X causes Y as well as Y causes X).

I want to know the current consensus (or nearing consensus) regarding the best method of selecting lag length. A Google search has only revealed some 1984 and 1985 papers. Scholarpedia's entry (http://www.scholarpedia.org/article/Granger_causality#Stationarity) says that it's O.K. to minimise AIC or BIC, but no references were provided for this claim so I don't want to code that up until I get confirmation.

Or is selection based on qualitative reasoning?

Cross posted here: http://www.talkstats.com/showthread.php/27425-Granger-Causality-Lag-length-selection.

Granger causality: Lag length selection

Consider G-Causality on two stationary time series vectors (call these variables $X$ and $Y$), each with 100+ observations. It's daily financial market time series data. I have reason to believe that there's reverse causality between these two variables (i.e., $X$ causes $Y$ as well as $Y$ causes $X$).

I want to know the current consensus (or nearing consensus) regarding the best method of selecting lag length. A Google search has only revealed some 1984 and 1985 papers. Scholarpedia's entry on Granger causality says that it's O.K. to minimise AIC or BIC, but no references were provided for this claim so I don't want to code that up until I get confirmation.

Or is selection based on qualitative reasoning?

Disclaimer: Cross posted on talkstats.com.

Source Link
user13253
user13253
Loading