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

Analytica Chimica Acta

Volumn 880, Issue , 2015, Pages 32-41

  Deng, Bai Chuan ^a,b   Yun, Yong Huan ^b   Liang, Yi Zeng ^b   Cao, Dong Sheng ^b   Xu, Qing Song ^b   Yi, Lun Zhao ^c   Huang, Xin ^b  

^a UNIVERSITY OF BERGEN   (Norway)

^b CENTRAL SOUTH UNIVERSITY   (China)

^c KUNMING UNIVERSITY OF SCIENCE AND TECHNOLOGY   (China)

Author keywords

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

Indexed keywords

CHEMICAL ANALYSIS; FORECASTING; STABILITY;

CROSS VALIDATION; MODEL SELECTION; MODEL STABILITY; OVERFITTING; PARTIAL LEAST SQUARE (PLS); POPULATION ANALYSIS;

LEAST SQUARES APPROXIMATIONS;

ARTICLE; CHEMICAL MODEL; CONTROLLED STUDY; ERROR; INTERMETHOD COMPARISON; MODEL POPULATION ANALYSIS; OVER FITTING; PARTIAL LEAST SQUARES REGRESSION; PREDICTION; PRIORITY JOURNAL; STATISTICAL ANALYSIS; STATISTICAL MODEL; STATISTICAL PARAMETERS; VALIDATION PROCESS; ALGORITHM; CHEMISTRY; COMPUTER PROGRAM; METABOLISM; REGRESSION ANALYSIS; SOYBEAN; ULTRAVIOLET SPECTROPHOTOMETRY;

ALGORITHMS; LEAST-SQUARES ANALYSIS; MODELS, CHEMICAL; SOFTWARE; SOYBEANS; SPECTROPHOTOMETRY, ULTRAVIOLET;

EID: 84931562522     PISSN: 00032670     EISSN: 18734324     Source Type: Journal    
DOI: 10.1016/j.aca.2015.04.045     Document Type: Article

References (54)

1. Tauler R., Walczak B., Brown S.D. Comprehensive Chemometrics: Chemical and Biochemical Data Analysis 2009, Elsevier, Amsterdam.
2. Bakeev K.A. Process Analytical Technology: Spectroscopic Tools and Implementation Strategies for the Chemical and Pharmaceutical industries 2010, John Wiley & Sons, New York.
3. Johnstone I.M., Titterington D.M. Statistical challenges of high-dimensional data. Philos. Trans. R. Soc. A 2009, 367:4237-4253.
4. Candes E., Tao T. The Dantzig selector: statistical estimation when p is much larger than n. Ann. Stat. 2007, 35:2313-2351.
5. Wold S., Sjostrom M., Eriksson L. PLS-regression: a basic tool of chemometrics. Chemometr. Intell. Lab. 2001, 58:109-130.
6. Faber N.M., Rajko R. How to avoid over-fitting in multivariate calibration - the conventional validation approach and an alternative. Anal. Chim. Acta 2007, 595:98-106.
7. Li B.B., Morris J., Martin E.B. Model selection for partial least squares regression. Chemometr. Intell. Lab. 2002, 64:79-89.
8. Deng B.C., Yun Y.H., Liang Y.Z., Yi L.Z. A novel variable selection approach that iteratively optimizes variable space using weighted binary matrix sampling. Analyst 2014, 139:4836-4845.
9. Yun Y.H., Wang W.T., Tan M.L., Liang Y.Z., Li H.D., Cao D.S., Lu H.M., Xu Q.S. A strategy that iteratively retains informative variables for selecting optimal variable subset in multivariate calibration. Anal. Chim. Acta 2014, 807:36-43.
10. Deng B.C., Yun Y.H., Ma P., Lin C.C., Ren D.B., Liang Y.Z. A new method for wavelength interval selection that intelligently optimizes the locations, widths and combinations of the intervals. Analyst 2015, 140:1876-1885.
11. Yun Y.H., Wang W.T., Deng B.C., Lai G.B., Liu X.B., Ren D.B., Liang Y.Z., Fan W., Xu Q.S. Using variable combination population analysis for variable selection in multivariate calibration. Anal. Chim. Acta 2015, 862:14-23.
12. p. Technometrics 1973, 15:661-675.
13. Akaike H. A new look at the statistical model identification. IEEE Trans. Autom. Control 1974, 19:716-723.
14. Schwarz G. Estimating the dimension of a model. Ann. Stat. 1978, 6:461-464.
15. Stone M. Cross-validatory choice and assessment of statistical predictions. J. R. Stat. Soc. 1974, 36:111-147.
16. Wold S. Cross-validatory estimation of the number of components in factor and principal components models. Technometrics 1978, 20:397-405.
17. Shao J. Linear model selection by cross-validation. J. Am. Stat. Assoc. 1993, 88:486-494.
18. Box G.E. Science and statistics. J. Am. Stat. Assoc. 1976, 71:791-799.
19. L. Breiman, Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author), (2001) 199-231.
20. Blumer A., Ehrenfeucht A., Haussler D., Warmuth M.K. Occam's razor. Inf. Process. Lett. 1987, 24:377-380.
21. Krzanowski W. Cross-validation in principal component analysis. Biometrics 1987, 43:575-584.
22. Osten D.W. Selection of optimal regression models via cross-validation. J. Chemometr. 1988, 2:39-48.
23. Höskuldsson A. Dimension of linear models. Chemometr. Intell. Lab. 1996, 32:37-55.
24. Van der Voet H. Pseudo-degrees of freedom for complex predictive models: the example of partial least squares. J. Chemometr. 1999, 13:195-208.
25. Tarumi T., Wu Y., Small G.W. Multivariate calibration with basis functions derived from optical filters. Anal. Chem. 2009, 81:2199-2207.
26. Kalivas J.H., Palmer J. Characterizing multivariate calibration tradeoffs (bias, variance, selectivity, and sensitivity) to select model tuning parameters. J. Chemometr. 2014, 28:347-357.
27. Wiklund S., Nilsson D., Eriksson L., Sjostrom M., Wold S., Faber K. A randomization test for PLS component selection. J. Chemometr. 2007, 21:427-439.
28. Gowen A.A., Downey G., Esquerre C., O'Donnell C.P. Preventing over-fitting in PLS calibration models of near-infrared (NIR) spectroscopy data using regression coefficients. J. Chemometr. 2011, 25:375-381.
29. Stout F., Baines M.R., Kalivas J.H. Impartial graphical comparison of multivariate calibration methods and the harmony/parsimony tradeoff. J. Chemometr. 2006, 20:464-475.
30. Rutledge D.N., Barros A.S. Durbin-Watson statistic as a morphological estimator of information content. Anal. Chim. Acta 2002, 454:277-295.
31. Li H.D., Liang Y.Z., Xu Q.S., Cao D.S. Model-population analysis and its applications in chemical and biological modeling. TrAC, Trends Anal. Chem. 2012, 38:154-162.
32. Jolliffe I. Principal Component Analysis 2005, Wiley Online Library, New York.
33. Herzberg A.M., Tsukanov A. A note on modifications of the jackknife criterion for model selection. Utilitas Math. 1986, 29:209-216.
34. Geisser S. The predictive sample reuse method with applications. J. Am. Stat. Assoc. 1975, 70:320-328.
35. Xu Q.S., Liang Y.Z. Monte Carlo cross validation. Chemometr. Intell. Lab. 2001, 56:1-11.
36. Filzmoser P., Liebmann B., Varmuza K. Repeated double cross validation. J. Chemometr. 2009, 23:160-171.
37. Faber K., Kowalski B.R. Propagation of measurement errors for the validation of predictions obtained by principal component regression and partial least squares. J. Chemometr. 1997, 11:181-238.
38. Kalivas J.H. Basis sets for multivariate regression. Anal. Chim. Acta 2001, 428:31-40.
39. Kalivas J.H., Green R.L. Pareto optimal multivariate calibration for spectroscopic data. Appl. Spectrosc. 2001, 55:1645-1652.
40. Faber N.M. A closer look at the bias-variance trade-off in multivariate calibration. J. Chemometr. 1999, 13:185-192.
41. Anzai Y. Pattern Recognition & Machine Learning 1992, Elsevier.
42. Ransohoff D.F. Rules of evidence for cancer molecular-marker discovery and validation. Nat. Rev. Cancer 2004, 4:309-314.
43. Yun Y.H., Liang Y.Z., Xie G.X., Li H.D., Cao D.S., Xu Q.S. A perspective demonstration on the importance of variable selection in inverse calibration for complex analytical systems. Analyst 2013, 138:6412-6421.
44. Dyrby M., Petersen R.V., Larsen J., Rudolf B., Nørgaard L., Engelsen S.B. Towards on-line monitoring of the composition of commercial carrageenan powders. Carbohydr. Polym. 2004, 57:337-348.
45. Forina M., Drava G., Armanino C., Boggia R., Lanteri S., Leardi R., Corti P., Conti P., Giangiacomo R., Galliena C., Bigoni R., Quartari I., Serra C., Ferri D., Leoni O., Lazzeri L. Transfer of calibration function in near-infrared spectroscopy. Chemometr. Intell. Lab. 1995, 27:189-203.
46. Liang Y.-Z., Kvalheim O.M., Manne R. White, grey and black multicomponent systems: a classification of mixture problems and methods for their quantitative analysis. Chemometr. Intell. Lab. 1993, 18:235-250.
47. Lorber A. Error propagation and figures of merit for quantification by solving matrix equations. Anal. Chem. 1986, 58:1167-1172.
48. Lorber A., Faber K., Kowalski B.R. Net analyte signal calculation in multivariate calibration. Anal. Chem. 1997, 69:1620-1626.
49. Li H.-D., Liang Y.-Z., Long X.-X., Yun Y.-H., Xu Q.-S. The continuity of sample complexity and its relationship to multivariate calibration: a general perspective on first-order calibration of spectral data in analytical chemistry. Chemometr. Intell. Lab. 2013, 122:23-30.
50. Brown C.D., Green R.L. Critical factors limiting the interpretation of regression vectors in multivariate calibration. TrAC, Trends Anal. Chem. 2009, 28:506-514.
51. Xu Q.S., Liang Y.Z., Du Y.P. Monte Carlo cross-validation for selecting a model and estimating the prediction error in multivariate calibration. J. Chemometr. 2004, 18:112-120.
52. Centner V., Massart D.L., de Noord O.E., de Jong S., Vandeginste B.M., Sterna C. Elimination of uninformative variables for multivariate calibration. Anal. Chem. 1996, 68:3851-3858.
53. Cao D.S., Liang Y.Z., Xu Q.S., Li H.D., Chen X. A new strategy of outlier detection for QSAR/QSPR. J. Comput. Chem. 2010, 31:592-602.
54. Cao D., Liang Y., Xu Q., Yun Y., Li H. Toward better QSAR/QSPR modeling: simultaneous outlier detection and variable selection using distribution of model features. J. Comput. Aid. Mol. Des. 2011, 25:67-80.