Sampling Error Profile Analysis for calibration transfer in multivariate calibration

Abstract

A new strategy named Sampling Error Profile Analysis (SEPA) is proposed in the optimization for some parameters in piecewise direct standardization (PDS), such as the number of principal components and window size, and the evaluation for the calibration transfer. Partial least squares (PLS) with mean-centering is used in PDS for calibration transfer. Random re-sampling is carried out in SEPA to obtain a series of subsets and build same number sub-models that produce corresponding number root mean square errors (RMSE), of which the mean value and standard deviation are calculated. To take both accuracy and stability into account, the sum of the mean value and standard deviation are used for parameter optimization and model evaluation. The performance of the proposed strategy has been tested on two data sets: a ternary mixture dataset and a corn dataset. Compared with PDS, SEPA-PDS obtained lower prediction errors, indicating that the transfer model would be more robust and effective when using the parameters optimized by SEPA. Compared with other two commonly used calibration transfer methods of slope and bias correction (SBC) and spectral space transformation (SST), SEPA-PDS acquired more satisfactory results.