On the Adoption of Partial Least Squares in Psychological Research: Caveat Emptor

The partial least squares technique (PLS) has been touted as a viable alternative to latent variable structural equation modeling (SEM) for evaluating theoretical models in the differential psychology domain. We bring some balance to the discussion by reviewing the broader methodological literature to highlight: (1) the misleading characterization of PLS as an SEM method; (2) limitations of PLS for global model testing; (3) problems in testing the significance of path coefficients; (4) extremely high false positive rates when using empirical confidence intervals in conjunction with a new "sign change correction" for path coefficients; (5) misconceptions surrounding the supposedly superior ability of PLS to handle small sample sizes and non-normality; and (6) conceptual and statistical problems with formative measurement and the application of PLS to such models. Additionally, we also reanalyze the dataset provided by Willaby et al. (2015; doi:10.1016/j.paid.2014.09.008) to highlight the limitations of PLS. Our broader review and analysis of the available evidence makes it clear that PLS is not useful for statistical estimation and testing.

Aplicação de alguns modelos quimiométricos à espectroscopia de fluorescência de raios-X de energia dispersiva

The objective of this work was to accomplish the simultaneous determination of some chemical elements by Energy Dispersive X-ray Fluorescence (EDXRF) Spectroscopy through multivariate calibration in several sample types. The multivariate calibration models were: Back Propagation neural network, Levemberg-Marquardt neural network and Radial Basis Function neural network, fuzzy modeling and Partial Least Squares Regression. The samples were soil standards, plant standards, and mixtures of lead and sulfur salts diluted in silica. The smallest Root Mean Square errors (RMS) were obtained with Back Propagation neural networks, which solved main EDXRF problems in a better way.

Quantitative structure-retention relationships analysis of retention index of essential oils

Genetic algorithm and multiple linear regression (GA-MLR), partial least square (GA-PLS), kernel PLS (GA-KPLS) and Levenberg-Marquardt artificial neural network (L-M ANN) techniques were used to investigate the correlation between retention index (RI) and descriptors for 116 diverse compounds in essential oils of six Stachys species. The correlation coefficient LGO-CV (Q²) between experimental and predicted RI for test set by GA-MLR, GA-PLS, GA-KPLS and L-M ANN was 0.886, 0.912, 0.937 and 0.964, respectively. This is the first research on the QSRR of the essential oil compounds against the RI using the GA-KPLS and L-M ANN.

Espectroscopia no infravermelho médio e análise sensorial aplicada à detecção de adulteração de café torrado por adição de cascas de café

Mid-infrared spectroscopy and chemometrics were used to identify adulteration in roasted and ground coffee by addition of coffee husks. Consumers' sensory perception of the adulteration was evaluated by a triangular test of the coffee beverages. Samples containing above 0.5% of coffee husks from pure coffees were discriminated by principal component analysis of the infrared spectra. A partial least-squares regression estimated the husk content in samples and presented a root-mean-square error for prediction of 2.0%. The triangular test indicated that were than 10% of coffee husks are required to cause alterations in consumer perception about adulterated beverages.

Least squares regression with errors in both variables: case studies

Analytical curves are normally obtained from discrete data by least squares regression. The least squares regression of data involving significant error in both x and y values should not be implemented by ordinary least squares (OLS). In this work, the use of orthogonal distance regression (ODR) is discussed as an alternative approach in order to take into account the error in the x variable. Four examples are presented to illustrate deviation between the results from both regression methods. The examples studied show that, in some situations, ODR coefficients must substitute for those of OLS, and, in other situations, the difference is not significant.

Novel Regression Methods For Spectral Data

Singular Value Decomposition (SVD), Principal Component Analysis (PCA) and Multiple Linear Regression (MLR) are some of the mathematical pre- liminaries that are discussed prior to explaining PLS and PCR models. Both PLS and PCR are applied to real spectral data and their di erences and similarities are discussed in this thesis. The challenge lies in establishing the optimum number of components to be included in either of the models but this has been overcome by using various diagnostic tools suggested in this thesis. Correspondence analysis (CA) and PLS were applied to ecological data. The idea of CA was to correlate the macrophytes species and lakes. The di erences between PLS model for ecological data and PLS for spectral data are noted and explained in this thesis. i

Classification of brain tumor extracts by high resolution ¹H MRS using partial least squares discriminant analysis

High resolution proton nuclear magnetic resonance spectroscopy (¹H MRS) can be used to detect biochemical changes in vitro caused by distinct pathologies. It can reveal distinct metabolic profiles of brain tumors although the accurate analysis and classification of different spectra remains a challenge. In this study, the pattern recognition method partial least squares discriminant analysis (PLS-DA) was used to classify 11.7 T ¹H MRS spectra of brain tissue extracts from patients with brain tumors into four classes (high-grade neuroglial, low-grade neuroglial, non-neuroglial, and metastasis) and a group of control brain tissue. PLS-DA revealed 9 metabolites as the most important in group differentiation: γ-aminobutyric acid, acetoacetate, alanine, creatine, glutamate/glutamine, glycine, myo-inositol, N-acetylaspartate, and choline compounds. Leave-one-out cross-validation showed that PLS-DA was efficient in group characterization. The metabolic patterns detected can be explained on the basis of previous multimodal studies of tumor metabolism and are consistent with neoplastic cell abnormalities possibly related to high turnover, resistance to apoptosis, osmotic stress and tumor tendency to use alternative energetic pathways such as glycolysis and ketogenesis.

Application of the european customer satisfaction index to postal services. Structural equation models versus partial least squars

Customer satisfaction and retention are key issues for organizations in today’s competitive market place. As such, much research and revenue has been invested in developing accurate ways of assessing consumer satisfaction at both the macro (national) and micro (organizational) level, facilitating comparisons in performance both within and between industries. Since the instigation of the national customer satisfaction indices (CSI), partial least squares (PLS) has been used to estimate the CSI models in preference to structural equation models (SEM) because they do not rely on strict assumptions about the data. However, this choice was based upon some misconceptions about the use of SEM’s and does not take into consideration more recent advances in SEM, including estimation methods that are robust to non-normality and missing data. In this paper, both SEM and PLS approaches were compared by evaluating perceptions of the Isle of Man Post Office Products and Customer service using a CSI format. The new robust SEM procedures were found to be advantageous over PLS. Product quality was found to be the only driver of customer satisfaction, while image and satisfaction were the only predictors of loyalty, thus arguing for the specificity of postal services

Fully complex-valued radial basis function networks for orthogonal least squares regression

We consider a fully complex-valued radial basis function (RBF) network for regression application. The locally regularised orthogonal least squares (LROLS) algorithm with the D-optimality experimental design, originally derived for constructing parsimonious real-valued RBF network models, is extended to the fully complex-valued RBF network. Like its real-valued counterpart, the proposed algorithm aims to achieve maximised model robustness and sparsity by combining two effective and complementary approaches. The LROLS algorithm alone is capable of producing a very parsimonious model with excellent generalisation performance while the D-optimality design criterion further enhances the model efficiency and robustness. By specifying an appropriate weighting for the D-optimality cost in the combined model selecting criterion, the entire model construction procedure becomes automatic. An example of identifying a complex-valued nonlinear channel is used to illustrate the regression application of the proposed fully complex-valued RBF network.

Sparse multioutput radial basis function network construction using combined locally regularised orthogonal least square and D-optimality experimental design

A construction algorithm for multioutput radial basis function (RBF) network modelling is introduced by combining a locally regularised orthogonal least squares (LROLS) model selection with a D-optimality experimental design. The proposed algorithm aims to achieve maximised model robustness and sparsity via two effective and complementary approaches. The LROLS method alone is capable of producing a very parsimonious RBF network model with excellent generalisation performance. The D-optimality design criterion enhances the model efficiency and robustness. A further advantage of the combined approach is that the user only needs to specify a weighting for the D-optimality cost in the combined RBF model selecting criterion and the entire model construction procedure becomes automatic. The value of this weighting does not influence the model selection procedure critically and it can be chosen with ease from a wide range of values.

Fully complex-valued radial basis function networks: orthogonal least squares regression and classification

We consider a fully complex-valued radial basis function (RBF) network for regression and classification applications. For regression problems, the locally regularised orthogonal least squares (LROLS) algorithm aided with the D-optimality experimental design, originally derived for constructing parsimonious real-valued RBF models, is extended to the fully complex-valued RBF (CVRBF) network. Like its real-valued counterpart, the proposed algorithm aims to achieve maximised model robustness and sparsity by combining two effective and complementary approaches. The LROLS algorithm alone is capable of producing a very parsimonious model with excellent generalisation performance while the D-optimality design criterion further enhances the model efficiency and robustness. By specifying an appropriate weighting for the D-optimality cost in the combined model selecting criterion, the entire model construction procedure becomes automatic. An example of identifying a complex-valued nonlinear channel is used to illustrate the regression application of the proposed fully CVRBF network. The proposed fully CVRBF network is also applied to four-class classification problems that are typically encountered in communication systems. A complex-valued orthogonal forward selection algorithm based on the multi-class Fisher ratio of class separability measure is derived for constructing sparse CVRBF classifiers that generalise well. The effectiveness of the proposed algorithm is demonstrated using the example of nonlinear beamforming for multiple-antenna aided communication systems that employ complex-valued quadrature phase shift keying modulation scheme. (C) 2007 Elsevier B.V. All rights reserved.

Orthogonal-least-squares regression: A unified approach for data modelling

A unified approach is proposed for data modelling that includes supervised regression and classification applications as well as unsupervised probability density function estimation. The orthogonal-least-squares regression based on the leave-one-out test criteria is formulated within this unified data-modelling framework to construct sparse kernel models that generalise well. Examples from regression, classification and density estimation applications are used to illustrate the effectiveness of this generic data-modelling approach for constructing parsimonious kernel models with excellent generalisation capability. (C) 2008 Elsevier B.V. All rights reserved.

Prediction of coagulation properties, titratable acidity and pH of bovine milk using mid-infrared spectroscopy

This study investigated the potential application of mid-infrared spectroscopy (MIR 4,000–900 cm−1) for the determination of milk coagulation properties (MCP), titratable acidity (TA), and pH in Brown Swiss milk samples (n = 1,064). Because MCP directly influence the efficiency of the cheese-making process, there is strong industrial interest in developing a rapid method for their assessment. Currently, the determination of MCP involves time-consuming laboratory-based measurements, and it is not feasible to carry out these measurements on the large numbers of milk samples associated with milk recording programs. Mid-infrared spectroscopy is an objective and nondestructive technique providing rapid real-time analysis of food compositional and quality parameters. Analysis of milk rennet coagulation time (RCT, min), curd firmness (a30, mm), TA (SH°/50 mL; SH° = Soxhlet-Henkel degree), and pH was carried out, and MIR data were recorded over the spectral range of 4,000 to 900 cm−1. Models were developed by partial least squares regression using untreated and pretreated spectra. The MCP, TA, and pH prediction models were improved by using the combined spectral ranges of 1,600 to 900 cm−1, 3,040 to 1,700 cm−1, and 4,000 to 3,470 cm−1. The root mean square errors of cross-validation for the developed models were 2.36 min (RCT, range 24.9 min), 6.86 mm (a30, range 58 mm), 0.25 SH°/50 mL (TA, range 3.58 SH°/50 mL), and 0.07 (pH, range 1.15). The most successfully predicted attributes were TA, RCT, and pH. The model for the prediction of TA provided approximate prediction (R2 = 0.66), whereas the predictive models developed for RCT and pH could discriminate between high and low values (R2 = 0.59 to 0.62). It was concluded that, although the models require further development to improve their accuracy before their application in industry, MIR spectroscopy has potential application for the assessment of RCT, TA, and pH during routine milk analysis in the dairy industry. The implementation of such models could be a means of improving MCP through phenotypic-based selection programs and to amend milk payment systems to incorporate MCP into their payment criteria.

Prediction of moisture, calorific value, ash and carbon content of two dedicated bioenergy crops using near-infrared spectroscopy

The potential of near infrared spectroscopy in conjunction with partial least squares regression to predict Miscanthus xgiganteus and short rotation coppice willow quality indices was examined. Moisture, calorific value, ash and carbon content were predicted with a root mean square error of cross validation of 0.90% (R2 = 0.99), 0.13 MJ/kg (R2 = 0.99), 0.42% (R2 = 0.58), and 0.57% (R2 = 0.88), respectively. The moisture and calorific value prediction models had excellent accuracy while the carbon and ash models were fair and poor, respectively. The results indicate that near infrared spectroscopy has the potential to predict quality indices of dedicated energy crops, however the models must be further validated on a wider range of samples prior to implementation. The utilization of such models would assist in the optimal use of the feedstock based on its biomass properties.

Evaluating mid-infrared spectroscopy as a new technique for predicting sensory texture attributes of processed cheese

The objective of this study was to investigate the potential application of mid-infrared spectroscopy for determination of selected sensory attributes in a range of experimentally manufactured processed cheese samples. This study also evaluates mid-infrared spectroscopy against other recently proposed techniques for predicting sensory texture attributes. Processed cheeses (n = 32) of varying compositions were manufactured on a pilot scale. After 2 and 4 wk of storage at 4 degrees C, mid-infrared spectra ( 640 to 4,000 cm(-1)) were recorded and samples were scored on a scale of 0 to 100 for 9 attributes using descriptive sensory analysis. Models were developed by partial least squares regression using raw and pretreated spectra. The mouth-coating and mass-forming models were improved by using a reduced spectral range ( 930 to 1,767 cm(-1)). The remaining attributes were most successfully modeled using a combined range ( 930 to 1,767 cm(-1) and 2,839 to 4,000 cm(-1)). The root mean square errors of cross-validation for the models were 7.4(firmness; range 65.3), 4.6 ( rubbery; range 41.7), 7.1 ( creamy; range 60.9), 5.1(chewy; range 43.3), 5.2(mouth-coating; range 37.4), 5.3 (fragmentable; range 51.0), 7.4 ( melting; range 69.3), and 3.1 (mass-forming; range 23.6). These models had a good practical utility. Model accuracy ranged from approximate quantitative predictions to excellent predictions ( range error ratio = 9.6). In general, the models compared favorably with previously reported instrumental texture models and near-infrared models, although the creamy, chewy, and melting models were slightly weaker than the previously reported near-infrared models. We concluded that mid-infrared spectroscopy could be successfully used for the nondestructive and objective assessment of processed cheese sensory quality..