Introduction: Novel manipulations of the well-known classical least squares multivariate calibration model were explained in detail as a comparative analytical study in this research work. In addition to the application of plain classical least squares model, two preprocessing steps were tried, where prior to modeling with classical least squares, first derivatization and orthogonal projection to latent structures were applied to produce two novel manipulations of the classical least square-based model. Moreover, spectral residual augmented classical least squares model is included in the present comparative study.

Quantitative determination of pyridostigmine bromide in the presence of its two related substances; impurity A and impurity B was considered as a case study to construct the comparison.

Method: 3 factor 4 level design was implemented constructing a training set of 16 mixtures with different concentrations of the studied components. To investigate the predictive ability of the studied models; a test set consisting of 9 mixtures was constructed.

Results: The key performance indicator of this comparative study was the root mean square error of prediction for the independent test set mixtures, where it was found 1.367 when classical least squares applied with no preprocessing method, 1.352 when first derivative data was implemented, 0.2100 when orthogonal projection to latent structures preprocessing method was applied and 0.2747 when spectral residual augmented classical least squares was performed.

Conclusion: Coupling of classical least squares model with orthogonal projection to latent structures preprocessing method produced significant improvement of the predictive ability of it.

简介：作为这项研究工作中的一项比较分析研究，详细解释了著名的经典最小二乘多元校准模型的新颖处理。除了应用普通古典最小二乘法模型外，还尝试了两个预处理步骤，其中在使用古典最小二乘法进行建模之前，先对潜在结构进行首次衍生化和正交投影，以产生两种基于古典最小二乘模型的新颖操作。此外，光谱残差增强古典最小二乘法模型包括在本比较研究中。

在存在两种相关物质的情况下定量测定溴化吡啶斯的明；杂质A和杂质B被认为是构建比较的案例研究。

方法：实施3因子4级设计，构建了包含不同浓度的研究组分的16种混合物的训练集。调查研究模型的预测能力；构建了由9种混合物组成的测试仪。

结果：这项比较研究的关键性能指标是独立测试集混合物的预测均方根误差，在未采用预处理方法的情况下，应用经典最小二乘时发现为1.367，在实施一阶导数数据时发现为1.352，在使用一阶导数数据时为0.2100。将正交投影应用于潜在结构的预处理方法，并在进行光谱残差增强经典最小二乘法的情况下进行0.2747的投影。

结论：将经典最小二乘模型与正交投影耦合到潜在结构的预处理方法可以大大提高其预测能力。