[Gretl-users] Re: rolling estimation

Hi Theodoros, did you check my RollingStats package? https://gretl.sourceforge.net/current_fnfiles/RollingStats.gfn In the sample script you find examples on how to do this? Best Artur Am 12.11.24 um 19:25 schrieb Theodoros Panagiotidis: > Dear All, > > I am trying to write script for running OLS and then plotting the > coefficients > > # Define your sample and dataset > open capm.gdt  # Replace with your dataset file > > # Define the rolling window size > scalar window_size = 50  # Set the size of the rolling window (e.g., 60 > periods) > > # Define the variable names > series y = ERFORD  # Replace with your dependent variable > series x = ERSANDP  # Replace with your independent variable > > # Initialize series to store rolling estimates > series coef_x = NA  # Stores coefficient for x > series intercept = NA  # Stores intercept (constant term) > > # Run rolling regression > loop i = window_size .. $nobs  # Loop from the end of the initial window > to the last observation >     scalar start = i - window_size + 1  # Calculate the starting point > of the window >     sample start i  # Set the sample range for the current rolling window >     ols y const x  # Run OLS on the defined sample > >     # Store results >     coef_x[i] = $coeff(x)  # Store the coefficient for x >     intercept[i] = $coeff(const)  # Store the intercept (constant term) > endloop > > # Reset the sample to full range after the loop > sample 1 $nobs  # Reset to full sample > > # Plot results or save as desired > gnuplot coef_x intercept --with-lines --time-series >