Principal components variable importance reconstruction (PC-VIR): Exploring predictive importance in multicollinear acoustic speech data
This method offers a new way to understand variable importance in multicollinear data, which is a common problem in fields like speech analysis, for researchers and practitioners needing to interpret complex models.
This paper introduces Principal Components Variable Importance Reconstruction (PC-VIR), a method to identify the relative predictive importance of individual variables in multicollinear datasets, categorizing them into strong, moderate, or no importance. When applied to acoustic features for discriminating vocalic nasality, PC-VIR produced more conservative but similar estimates to separate logistic regression models, and achieved comparable data fit and prediction accuracy to partial least squares methods.
This paper presents a method of exploring the relative predictive importance of individual variables in multicollinear data sets at three levels of significance: strong importance, moderate importance, and no importance. Implementation of Bonferroni adjustment to control for Type I error in the method is described, and results with and without the correction are compared. An example of the method in binary logistic modeling is demonstrated by using a set of 20 acoustic features to discriminate vocalic nasality in the speech of six speakers of the Mixean variety of Low Navarrese Basque. Validation of the method is presented by comparing the direction of significant effects to those observed in separate logistic mixed effects models, as well as goodness of fit and prediction accuracy compared to partial least squares logistic regression. The results show that the proposed method yields: (1) similar, but more conservative estimates in comparison to separate logistic regression models, (2) models that fit data as well as partial least squares methods, and (3) predictions for new data that are as accurate as partial least squares methods.