Techniques for identifying coefficients are described. A technique collects sample input values to the filter and identifies desired output values from the filter for the collected sample input values. The technique then generates a power spectrum of the collected sample input values and a power spectrum of the identified desired output values. The technique then calculates the difference between the generated power spectra. Finally, the technique identifies coefficients that yield a filter transfer function that closely approximates the calculated differences. A technique identifies coefficients for a finite impulse response filter. The technique collects sample input values for a function and identifies desired output values for the filter for the collected sample input values. The technique then approximates the output values from the input values using a linear fitting technique. Finally, the technique sets the coefficients to values obtained from the linear-fitting technique.