Most analyses of the infrared emission of Saturn's rings and icy satellites have considered pure water ice as the constituent of regolith and particle surfaces. Visual and near-infrared observations have shown, however, that darkening and reddening contaminants are present at a fraction level of a few percent. In the spectral domain 10-2000 $ cm^ $, water ice becomes transparent in a few windows, which in particular causes the roll-off of emissivity of icy surfaces that is observed below 50 $ cm^ $. Their emissivity there may be affected by these contaminants. We present a quantitative global sensitivity analysis of a hybrid Mie-Hapke model to evaluate the influence of regolith properties and contaminant fraction on the infrared emissivity of icy rings or moons over this spectral range. A hybrid Mie-Hapke model of the hemispherical emissivity $ was made, including various diffraction correction and mixing types with tholins or amorphous carbon grains, or grain size distributions and some anisotropy in emission. A Sobol global sensitivity analysis provided quantitative levels of importance for these factors versus wave number $w_n$. Given the a priori uncertainties, the most important factor acting on $ remains the size distribution of regolith grains and the average anisotropy factor xi . For $w_n$> 50 $ cm^ $, xi , the power-law index $p$ and the minimum $a_ min $ of the size distribution are most influential. In windows of water-ice transparency (10-50, 300-600, and 900-1300 $ cm^ $), the emissivity is also sensitive, but to a lesser extent, to the maximum grain size $a_ max $ and the fraction $f$ of contaminants, if mixed at the molecular level. This model provides a self-consistent tool for interpreting multi-modal observations of the thermal emission from icy surfaces. It also offers interesting insights into recent mid-infrared observations of Saturn's rings and Jupiter's moon Ganymede by the JWST-MIRI instrument.