摘要:

AbstractInformation theory makes it possible to judge and evaluate methods and results in chemical analysis. The obtained information can be expressed in different ways. One way is to define information as the decrease of uncertainity after analysis. Conditional probabilities are therefore considered when evaluating the information provided by qualitative analyses. However, the use of other information measures, such as the information gain, is often preferable. In multicomponent analysis the translation of information from signals to the amounts of the analytes has been investigated along with the relevance of individual components. Information theory can also be applied to find the optimum experimental conditions. The evaluation of the properties of analytical methods by information theory has been proposed.

ISSN:0886-9383    

DOI:10.1002/cem.1180040303

出版商:John Wiley&Sons, Ltd.    

年代:1990

数据来源: WILEY

摘要:

AbstractCross‐validatory estimation of the bilinear model based on principal components is reviewed and Krzanowski's modification of Wold's procedure is described. Two different types of residuals useful for checking model adequacy are defined and indices measuring the influence of each observed unit on the estimates of the parameters are discussed. A method for the selection of variables derived from Procrustes analysis is described. Results arising from the study of two sets of enological data are give

ISSN:0886-9383    

DOI:10.1002/cem.1180040304

出版商:John Wiley&Sons, Ltd.    

年代:1990

数据来源: WILEY

摘要:

AbstractDedicated principal properties (DPPs) are presented. The DPP approach is an iterative process based on PLS wherein principal properties are calibrated on QSARs with improved predictive capabilities as a consequence. The DPP approach is illustrated by two examples. In the first example thez‐scales developed for structural description in peptide QSARs are optimized according to the DPP approach. In the second example DDPs based on simulated pentapeptide‐like sequences are calculated and evaluated.A comparison is made of the predictive power of peptide QSAR models based on structural description of the peptides with (a) 29 physico‐chemical variables with (b) three principal properties (z‐scales) and (c) three sets of DPPs. The results show that models based on all 29 variables give better predictions than models based on principal properties. Modelling based on DPPs improves the predictive power to the same level as models based on all 29 va

ISSN:0886-9383    

DOI:10.1002/cem.1180040305

出版商:John Wiley&Sons, Ltd.    

年代:1990

数据来源: WILEY

摘要:

AbstractThe results of unsupervised pattern recognition methods are critically dependent on the measure of similarity used for clustering objects. There is littlea prioriinformation available on the relative utility of various similarity measures. We introduce here an alternative similarity measure based on the metric tensor measure (MTM). Two standard clustering strategies are tested with the proposed similarity measure: hierarchical clustering and theK‐median method. As data we use the ARCH obsidian data, a data set on Hungarian coal, and trace element data on Hungarian paprika. Differences from the Mahalanobis distance measure are described for intraclass relation

ISSN:0886-9383    

DOI:10.1002/cem.1180040306

出版商:John Wiley&Sons, Ltd.    

年代:1990

数据来源: WILEY

ISSN:0886-9383    

DOI:10.1002/cem.1180040307

出版商:John Wiley&Sons, Ltd.    

年代:1990

数据来源: WILEY

ISSN:0886-9383    

DOI:10.1002/cem.1180040308

出版商:John Wiley&Sons, Ltd.    

年代:1990

数据来源: WILEY

ISSN:0886-9383    

DOI:10.1002/cem.1180040302

出版商:John Wiley&Sons, Ltd.    

年代:1990

数据来源: WILEY