Re: [Gretl-users] SOMETHING WRONG IN GRETL

May be, this would be helpful There are TWO issues: 1) NUMERIC correctness and 2) ECONOMETRIC correctness 1) (i) ols INF 0 PBI eval mean($uhat) # 4.6556457e-14 # using multiple precision floating-point arithmetic, # with the help of the Gnu Multiple Precision (GMP) library mpols INF 0 PBI eval mean($uhat) # -1.4953213e-14 The order of 10^-14 is a good approximation for zero (I) A lss tested soft : Stata, Eviews, R (cran), R (Microsoft), python give the same results 2) The regression is incorrect in ECONOMETRIC sense as a consequence of at minimum 2 reasons: (i) outliers for hyperinflation period (circa 1990) (ii) PBI is obviously non-stationary In the last case, besides summing up to zero, the residuals could behave as strangely as they prefer to do Oleh 2 березня 2017, 01:17:09, від "HEBERT SUAREZ CAHUANA" <hsuarezc(a)unsa.edu.pe&gt;: