I am trying to write a script that, based on a regression with a lot of variables and lags, drop unsignificant variables and leave only the significant regressors. I am having problems to identify the variable to drop in each iteration because gretl sometimes detects "exact" collinearity (but not perfect collinearity) and removes one regressor, so that the regressors I write in the ols command are not the same as gretl uses in the estimation, so it makes difficult to associate the coefficients in $coeff with my list of regressors. I suppose gretl detects "exact" collinearity when det(X'X)<epsilon being epsilon a very small number. And in general I think it is good that the program removes a variable and run the regression. But I don't find a solution without asking Allin and Jack to change the ols source. I think changing the ols source may be some solutions to resolve this problem. Gretl after the ols estimation could: 1- save the variable with highest t pvalue in a $ variable (for example its ID number in a scalar) 2- save a list with the regressors used in the estimation (or a row matrix with the ID numbers) Do you see any other solution? -- Ignacio Diaz-Emparanza DEPARTAMENTO DE ECONOMÍA APLICADA III (ECONOMETRÍA Y ESTADÍSTICA) UPV/EHU Avda. Lehendakari Aguirre, 83 | 48015 BILBAO T.: +34 946013732 | F.: +34 946013754 www.et.bs.ehu.es

El Wednesday 09 January 2008 16:26:16 Allin Cottrell escribió: That's perfect !! But, what does mean "sequenciallly" here? Estimate the model, omit the variable with the highest p-value, estimate the model without this variable, ... or is this command based on only the first estimation and applying sequential F tests? -- Ignacio Diaz-Emparanza DEPARTAMENTO DE ECONOMÍA APLICADA III (ECONOMETRÍA Y ESTADÍSTICA) UPV/EHU Avda. Lehendakari Aguirre, 83 | 48015 BILBAO T.: +34 946013732 | F.: +34 946013754 www.et.bs.ehu.es