In static designs, you can select from four signal-to-noise (S/N) ratios, depending on the goal of your design. You should use your engineering knowledge, understanding of the process, and experience to choose the appropriate S/N ratio [2].
Choose... |
S/N ratio formulas |
Use when the goal is to... |
And your data are... |
Larger is better |
S/N = -10*log(S(1/Y2)/n) |
Maximize the response |
Positive |
Nominal is best |
S/N = -10*log(s2) |
Target the response and you want to base the S/N ratio on standard deviations only |
Positive, zero, or negative |
Nominal is best (default) |
S/N = 10*log((Y2) / s2) The adjusted formula is: S/N = 10*log((Y2 - s2 / n )/ s2) |
Target the response and you want to base the S/N ratio on means and standard deviations |
Non-negative with an "absolute zero" in which the standard deviation is zero when the mean is zero |
Smaller is better |
S/N = -10*log(S(Y2)/n)) |
Minimize the response |
Non-negative with a target value of zero |
Note |
The Nominal is Best (default) S/N ratio is useful for analyzing or identifying scaling factors, which are factors in which the mean and standard deviation vary proportionally. Scaling factors can be used to adjust the mean on target without affecting S/N ratios. |