A colleague of mine is using a VAR for quarterly data (deseasonalized). Typically it is customary to use lag of 4 or 5. However, they used two lags based on a single test result, the SC criteria. Of course, there may be a degrees of freedom problem if they decide to go with the longer 4-quarter lag. What is the best way to explain their rationale to them?


closed as unclear what you're asking by kjetil b halvorsen, Michael Chernick, mdewey, Jeremy Miles, Peter Flom Aug 13 at 11:58

Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • 8
    $\begingroup$ Why would you explain "their rationale to them"? Surely they know what their own rationale is. $\endgroup$ – gung Aug 19 '15 at 16:15

If it's an economic forecasting, then their rationale is simpler than that: they don't have enough data to go beyond 2 lags. Look at the number of parameters to estimate, including covariance of errors.

In economic forecasting we always struggle with limited sample sizes.

  • 2
    $\begingroup$ This user is not telling us, how much data he has and you argument with lack of data. You can also have macroeconomic data such as inflation for the last 70 years in Germany or France. If you have 70 years you can certainly use 4 lags. $\endgroup$ – Ferdi Jan 13 '17 at 7:54

Not the answer you're looking for? Browse other questions tagged or ask your own question.