A MONTE-CARLO STUDY OF THE EFFECT OF NOISE ON WAVELENGTH SELECTION DURING COMPUTERIZED WAVELENGTH SEARCHES

The process of selecting wavelengths for performing quantitative analysis in the near-infrared is notorious for its instability. A Monte Carlo technique was used to investigate the sensitivity of the wavelength selection process to the noise content of the spectra. The random nature of the noise causes the wavelengths to be selected at random; this seems to be sufficient to explain the instability of the selection process. The statistics of the selection process are insensitive to error in the dependent variable, and, within limits, also insensitive to the amount of noise in the spectral data. The statistics are sensitive to the number of samples in the data set and to the nature of the distribution of the noise.