This function calculates the Variable Importance in the Projection statistic for the Partial Least Squares regression. It is used in the PLS function. Executing it in isolation will probably not be useful to most users.
an mvr object, as produced by the pls procedure or a range of other functions
This is required to produce the VIP scores for the PLS procedure.
data frame with as many columns as independent variables are input into the PLS analysis. The number of columns corresponds to the number of latent components selected for the analysis. Values in the data frame are the VIP values corresponding to each variable for the respective component.
Eike Luedeling, but the function was mainly copied from http://mevik.net/work/software/pls.html; the reference given there is listed below
the function is mostly identical to the one provided on http://mevik.net/work/software/pls.html.
Here is the reference given there:
Chong, Il-Gyo & Jun, Chi-Hyuck, 2005, Performance of some variable selection methods when multicollinearity is present, Chemometrics and Intelligent Laboratory Systems 78, 103-112
This reference refers to the chillR package:
Luedeling E, Kunz A and Blanke M, 2013. Identification of chilling and heat requirements of cherry trees - a statistical approach. International Journal of Biometeorology 57,679-689.
1 2 3 4 5 6 7 8 9 10