A new strategy to prevent over-fitting in partial least squares models based on model population analysis

作者：Deng, Bai-Chuan; Yun, Yong-Huan; Liang, Yi-Zeng^*; Cao, Dong-Sheng; Xu, Qing-Song; Yi, Lun-Zhao; Huang, Xin

来源：Analytica Chimica Acta, 2015, 880: 32-41.

DOI：10.1016/j.aca.2015.04.045

• Partial least squares
• Over-fitting
• Model population analysis
• Model selection
• Model stability
• Cross-validation

Partial least squares (PLS) is one of the most widely used methods for chemical modeling. However, like many other parameter tunable methods, it has strong tendency of over-fitting. Thus, a crucial step in PLS model building is to select the optimal number of latent variables (nLVs). Cross-validation (CV) is the most popular method for PLS model selection because it selects a model from the perspective of prediction ability. However, a clear minimum of prediction errors may not be obtained in CV which makes the model selection difficult. To solve the problem, we proposed a new strategy for PLS model selection which combines the cross-validated coefficient of determination (Q(cv)(2)) and model stability (S). S is defined as the stability of PLS regression vectors which is obtained using model population analysis (MPA). The results show that, when a clear maximum of Q(cv)(2) is not obtained, S can provide additional information of over-fitting and it helps in finding the optimal nLVs. Compared with other regression vector based indictors such as the Euclidean 2-norm (B2), the Durbin Watson statistic (DW) and the jaggedness (J), S is more sensitive to over-fitting. The model selected by our method has both good prediction ability and stability.

• 出版日期2015-6-23
• 单位昆明理工大学; 中南大学