search

Natsiopoulos / ARDL

ARDL, ECM and Bounds-Test for Cointegration
GNU General Public License v3.0
17 stars 9 forks source link

Suggested changes to the JOSS article #7

Closed jessie-dotson closed 2 years ago

jessie-dotson commented 2 years ago

A few typos and edits to consider for JOSS manuscript:

Natsiopoulos commented 2 years ago

Hi @jessie-dotson Thank you for reviewing our submission. Here are our answers for your suggestions.

"equations would be clearer if variables were defined"

Answer: Most of the equations have been removed as suggested by the other reviewer. Theses are general equation forms, and not a modeling application, so there are not much to define. Unless you mean to refer to the constant and linear trend and the error, which we consider redundant to be mentioned for such a simple case. Do you think we should mention these?

"lines 50 - 54: Would be clearer if there were a clear explanation of what determined a "Case"

Answer: In the first version of the software paper the cases where explicitly defined by the detailed equations. In this version, after the other reviewers suggestion about removing the detailed equations, we added the information that the case is about the restriction in the constant and the linear trend. See in the software paper for "...the case for potential restriction in the deterministic parameters (constant and linear trend)..."

"equations 4-8: ECT is not defined"

Answer: These equations do not longer exist.

"line 95: include link to API documentation when discussing the API"

Answer: Thank you for the suggestion. We added the link as needed.

jessie-dotson commented 2 years ago

Perhaps this is a difference in background -- as I warned when I agreed to review this submission, I don't use ARDL -- but I still believe the equations would be more useful if there were some pointers as to what the variables are that are used in equations 1 and 2. Nonetheless, I'm not going ot pursue the point.