THE DOCUMENT PRESENTS AN ANALYSIS OF THE STOCHASTIC NATURE OF THE GROSS DOMESTIC PRODUCT OF MEXICO FOR THE PERIOD 1900-2001. SEVERAL SPECIFICATIONS TO TEST FOR THE EXISTENCE OF UNIT ROOTS ARE PRESENTED. THE CONVENTIONAL TESTS, DICKEY FULLER, AUGMENTED DICKEY FULLER AND PHILLIPS PERRON, INDICATE THAT THE SERIES IS NON-STATIONARY AND INTEGRATED OF ORDER 1. THIS RESULT IS ROBUST TO THE INCLUSION OF EXOGENOUSLY AND ENDOGENOUSLY DETERMINED STRUCTURAL BREAKS. INTERESTINGLY, WHEN STRUCTURAL BREAKS ARE DETERMINED ENDOGENOUSLY, A STRUCTURAL BREAK IN 1907 IS IDENTIFIED. WE INTERPRET THIS RESULTS AS SUGGESTING THAT SETTING THE DATE OF A STRUCTURAL BREAK EX-ANTE MIGHT NOT BE THE MOST EFFICIENT PROCEDURE WHEN TESTING FOR UNIT ROOTS.THE DOCUMENT PRESENTS AN ANALYSIS OF THE STOCHASTIC NATURE OF THE GROSS DOMESTIC PRODUCT OF MEXICO FOR THE PERIOD 1900-2001. SEVERAL SPECIFICATIONS TO TEST FOR THE EXISTENCE OF UNIT ROOTS ARE PRESENTED. THE CONVENTIONAL TESTS, DICKEY FULLER, AUGMENTED DICKEY FULLER AND PHILLIPS PERRON, INDICATE THAT THE SERIES IS NON-STATIONARY AND INTEGRATED OF ORDER 1. THIS RESULT IS ROBUST TO THE INCLUSION OF EXOGENOUSLY AND ENDOGENOUSLY DETERMINED STRUCTURAL BREAKS. INTERESTINGLY, WHEN STRUCTURAL BREAKS ARE DETERMINED ENDOGENOUSLY, A STRUCTURAL BREAK IN 1907 IS IDENTIFIED. WE INTERPRET THIS RESULTS AS SUGGESTING THAT SETTING THE DATE OF A STRUCTURAL BREAK EX-ANTE MIGHT NOT BE THE MOST EFFICIENT PROCEDURE WHEN TESTING FOR UNIT ROOTS.