Estimation of influential points in any data set from coefficient of determination and its leave-one-out cross-validated counterpart

Tóth, Gergely; Bodai, Zsolt; Héberger, Károly

doi:10.1007/s10822-013-9680-4

Cited by 24 publications

(11 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The highest value of the predictive squared correlation coefficient was found for Amino-P-C10 (Q 2 LOOCV = 0.687) and IAM.PC.DD2 (Q 2 LOOCV = 0.503). Negative Q 2 value (Q 2 LOOCV = −0.01) was noted for Amino-P-C18, indicating predictions no better than the mean [17,38]. We therefore concluded that PLS models provide insufficient predictive ability.…”

Section: Dimensionality Reduction Techniques In Qsrr Study Of Nucleosmentioning

confidence: 84%

“…We also assessed the internal predictive character of the obtained models using a method proposed by Toth et al [38]. For the Amino-P-C10 and IAM.PC.DD2 stationary phases we may conclude, that there is no statistically significant evidence, that models developed on the reduced data sets, obtained by LOOCV, are Table 3 The number of coefficients selected by LASSO along with descriptive and validation parameters for the three stationary phases.…”

Section: Modeling Of Retention Of Nucleosides and Pterins Via Stepwismentioning

confidence: 97%

“…The internal predictive character of the obtained models was assessed by the test proposed by Toth et al [38]. Briefly, the predictive residual sum of squares (PRESS) and the residual sum of squares (RSS) with their corresponding degrees of freedom df PRES and df RSS , were used to calculate the F-statistics, which was compared to the F distribution.…”

Section: Model Evaluationmentioning

confidence: 99%

See 2 more Smart Citations

Least absolute shrinkage and selection operator and dimensionality reduction techniques in quantitative structure retention relationship modeling of retention in hydrophilic interaction liquid chromatography

Daghir-Wojtkowiak

Wiczling

Bocian

et al. 2015

Journal of Chromatography A

View full text Add to dashboard Cite

Section: Dimensionality Reduction Techniques In Qsrr Study Of Nucleosmentioning

confidence: 84%

Section: Modeling Of Retention Of Nucleosides and Pterins Via Stepwismentioning

confidence: 97%

Section: Model Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Least absolute shrinkage and selection operator and dimensionality reduction techniques in quantitative structure retention relationship modeling of retention in hydrophilic interaction liquid chromatography

Daghir-Wojtkowiak

Wiczling

Bocian

et al. 2015

Journal of Chromatography A

View full text Add to dashboard Cite

“…In The fact that outliers are not influential points can occur, as explained by Tóth et al (2013), considering that the concepts are different. An outlier is an extreme value that does not follow the general tendency.…”

Section: Local Influence Analysismentioning

confidence: 99%

Spatial-temporal Analysis of Soybean Productivity Using Geostatistical Methods

Dalposso

Uribe-Opazo

Bastiani

2022

JAS

View full text Add to dashboard Cite

To have information about the soybean productivity over the crop years is essential to define strategies to increase profits and reduce costs and most important to reduce environmental impacts. One form of monitoring is the use of Geostatistical methods, which allow us to obtain maps with more accurate predictions. In this paper, an area of 127.16 ha was studied during six crop years between 2012/2013 and 2017/2018. We found that productivity values vary between crop years, mainly due to uncontrollable climatic factors. The removal of influential points caused changes in the predicted values showed in the maps, and the use of scaled semivariograms allowed us to obtain similar maps to those obtained considering the model without influential points, then there was no need to exclude observations. The use of a model with replicates helped to identify regions where productivity was lower. The use of explanatory variables allowed us to elaborate a more accurate thematic map in the 2017/2018 crop year, which was well evidenced by the prediction standard error map.

show abstract

“…Additional parameters have been also calculated in order to confirm quality of the developed QSPR models, namely: concordance correlation coefficient (CCC) and modified r 2 for whole dataset (r 2 (overall) ) [17]. We also estimated the presence of influential points in the training set by performing F-test proposed by Toth et al, where F value is equal to: (1 -Q 2 CV )/(1 -R 2 ) [18]. Moreover, we calculated other metrics and compared them with criteria proposed by Tropsha and thereby confirmed the good quality of the developed QSPR models [19].…”

Section: Validation Processmentioning

confidence: 99%

Representation of the Structure—A Key Point of Building QSAR/QSPR Models for Ionic Liquids

Rybińska-Fryca

Sosnowska²,

Puzyn

2020

Materials

View full text Add to dashboard Cite

The process of encoding the structure of chemicals by molecular descriptors is a crucial step in quantitative structure-activity/property relationships (QSAR/QSPR) modeling. Since ionic liquids (ILs) are disconnected structures, various ways of representing their structure are used in the QSAR studies: the models can be based on descriptors either derived for particular ions or for the whole ionic pair. We have examined the influence of the type of IL representation (separate ions vs. ionic pairs) on the model’s quality, the process of the automated descriptors selection and reliability of the applicability domain (AD) assessment. The result of the benchmark study showed that a less precise description of ionic liquid, based on the 2D descriptors calculated for ionic pairs, is sufficient to develop a reliable QSAR/QSPR model with the highest accuracy in terms of calibration as well as validation. Moreover, the process of a descriptors’ selection is more effective when the possible number of variables can be decreased at the beginning of model development. Additionally, 2D descriptors usually demand less effort in mechanistic interpretation and are more convenient for virtual screening studies.

show abstract

Estimation of influential points in any data set from coefficient of determination and its leave-one-out cross-validated counterpart

Cited by 24 publications

References 20 publications

Least absolute shrinkage and selection operator and dimensionality reduction techniques in quantitative structure retention relationship modeling of retention in hydrophilic interaction liquid chromatography

Least absolute shrinkage and selection operator and dimensionality reduction techniques in quantitative structure retention relationship modeling of retention in hydrophilic interaction liquid chromatography

Spatial-temporal Analysis of Soybean Productivity Using Geostatistical Methods

Representation of the Structure—A Key Point of Building QSAR/QSPR Models for Ionic Liquids

Contact Info

Product

Resources

About