[Gretl-users] bug in chow test

Hi all, I seem to have encountered a bug in the Chow test implementation. Using Ramanathan's data set 7-2, I wanted to do a Chow test based on the GENDER dummy variable (after regressing WAGE on all the other variables). In the gui, I selected GENDER from the dialog box, but the output says the test is based on a split at observation #25. The command log lists "chow 25". When I tried "chow GENDER -dummy" in the console, I get the message "The model already contains GENDER". Thanks in advance for any help, PS =============================== Dr. Peter Summers Assistant Professor Department of Economics Texas Tech University ===============================