Comparison of the variable importance in projection (VIP) and of the selectivity ratio (SR) methods for variable selection and interpretation

Abstract

This study compares the application of two variable selection methods in partial least squares regression (PLSR), the variable importance in projection (VIP) method and the selectivity ratio (SR) method. For this purpose, three different data sets were analysed: (a) physiochemical water quality parameters related to sensorial data, (b) gas chromatography-mass spectrometry (GC-MS) chemical (organic compound) profiles from fossil sea sediment samples related to sea surface temperature (SST) changes, and (c) exposed genes of Daphnia magna female samples related to their total offspring production. Correlation coefficients (r), levels of significance (p-value) and interpretation of the underlying experimental phenomena allowed the discussion about the best approach for variable selection in each case. The comparison of the two variable selection methods in the first water quality data set showed that the SR method is more accurate for sensorial prediction. For the climate data set, when raw total ion current (TIC) GC-MS chromatograms were considered, variables selected using the VIP method were easier to interpret compared with those selected by the SR method. However, when only some chromatographic peak areas (concentrations) were considered, the SR method was more efficient for prediction, and the VIP method selected the most relevant variables for the interpretation of SST changes. Finally, for the transcriptomic data set, the SR method was found again to be more reliable for prediction purposes.

Observation and Estimation of Evapotranspiration from an Irrigated Green Roof in a Rain-Scarce Environment

“…For all three ET a models, their 5-min ET a estimates were summed to daily amounts to be compared with the ET a daily measurements. The variable importance in projection (VIP) scores summarize the influence of individual variables on the PLS model, and give a measure useful to select the independent variables that contribute the most to the dependent variable's variance [73]. It is generally accepted in practice that variables having a VIP > 1.0 are highly influential, values between 0.8 < VIP < 1.0 indicate moderately influential variables, and variables with VIP < 0.8 are less important [73,74].…”

“…The variable importance in projection (VIP) scores summarize the influence of individual variables on the PLS model, and give a measure useful to select the independent variables that contribute the most to the dependent variable's variance [73]. It is generally accepted in practice that variables having a VIP > 1.0 are highly influential, values between 0.8 < VIP < 1.0 indicate moderately influential variables, and variables with VIP < 0.8 are less important [73,74]. The coefficients of determination (R 2 ), the root mean square error (RMSE), the Nash-Sutcliffe efficiency (NSE) [75], and the percent bias (PBIAS) were calculated to evaluate the goodness of fit of the three ET a models.…”

Raman spectra analysis of human blood protein fractions using the projection on latent structures method

“…Spectral informative bands during the regression model construction were determined by the analysis of the variable importance in projection (VIP) [11]. The higher the VIP-score of an individual variable corresponds to the more significant values in the constructed model.…”

Prediction of 2-acetyl-1-pyrroline content in grains of Thai Jasmine rice based on planting condition, plant growth and yield component data using chemometrics

“…In addition to the predictive model, the significance of each of the parameters was evaluated using PLS coefficients and variable influence on projection (VIP) [30]. For a calibration model, different data pre-processing can strongly influence the analysis results and there are no clear-cut guidelines when to use or to avoid certain preprocessing methods.…”