A new algorithm for latent root regression analysis

New properties of latent root regression are shown aiding insight into the determination of a prediction model. Moreover, a procedure for the determination of a prediction model is discussed. It has similarities to partial least squares and differ from the latter method only in the way components used as predictors are formed. This procedure is extended to the case where the problem at hand concerns the prediction of more than one variable. The method is illustrated using real data sets.

[1]  M. Stone.  Continuum regression: Cross-validated sequentially constructed prediction embracing ordinary least s , 1990 .

[2]  E. Vigneau,et al.  New approach in biased regression , 1997 .

[3]  Douglas M. Hawkins,et al.  On the Investigation of Alternative Regressions by Principal Component Analysis , 1973 .

[4]  R. Gunst,et al.  Latent Root Regression: Large Sample Analysis , 1979 .

[5]  Evelyne Vigneau,et al.  Application of latent root regression for calibration in near-infrared spectroscopy. Comparison with principal component regression and partial least squares , 1996 .

[6]  J. T. Webster,et al.  Latent Root Regression Analysis , 1974 .

[7]  I. Jolliffe.  Principal Component Analysis , 2002 .

[8]  Robert L. Mason,et al.  A Comparison of Least Squares and Latent Root Regression Estimators , 1976 .

[9]  Arthur E. Hoerl,et al.  Ridge Regression: Biased Estimation for Nonorthogonal Problems , 2000, Technometrics.

[10]  Robert L. Mason,et al.  Biased Estimation in Regression: An Evaluation Using Mean Squared Error , 1977 .

[11]  Charles R. Johnson,et al.  Matrix analysis , 1985, Statistical Inference for Engineers and Data Scientists.

[12]  Norman R. Draper,et al.  Ridge Regression and James-Stein Estimation: Review and Comments , 1979 .

[13]  P. Garthwaite.  An Interpretation of Partial Least Squares , 1994 .

[14]  N. Wermuth,et al.  A Simulation Study of Alternatives to Ordinary Least Squares , 1977 .

[15]  N. Draper,et al.  Applied Regression Analysis , 1966 .