Comparison of Principal Component Solutions in Two Populations

Methodology ◽  
2016 ◽  
Vol 12 (1) ◽  
pp. 11-20 ◽  
Author(s):  
Gregor Sočan
Keyword(s):  
Simulation Study ◽  
Principal Components ◽  
Common Factor ◽  
Principal Component ◽  
Component Model ◽  
Bootstrap Procedure ◽  
Factor Loadings ◽  
Component Loadings ◽  
Principal Component Model ◽  
Two Populations

Abstract. When principal component solutions are compared across two groups, a question arises whether the extracted components have the same interpretation in both populations. The problem can be approached by testing null hypotheses stating that the congruence coefficients between pairs of vectors of component loadings are equal to 1. Chan, Leung, Chan, Ho, and Yung (1999) proposed a bootstrap procedure for testing the hypothesis of perfect congruence between vectors of common factor loadings. We demonstrate that the procedure by Chan et al. is both theoretically and empirically inadequate for the application on principal components. We propose a modification of their procedure, which constructs the resampling space according to the characteristics of the principal component model. The results of a simulation study show satisfactory empirical properties of the modified procedure.

scholarly journals Principal component model in macroseismicity

2020 ◽  
Vol 42 (5) ◽  
pp. 172-182
Author(s):  
R.Z. Burtiev ◽  
V.Yu. Cardanets
Keyword(s):  
Principal Component ◽  
Component Model ◽  
Principal Component Model

scholarly journals Morphological evaluation of common bean diversity in Bosnia and Herzegovina using the discriminant analysis of principal components (DAPC) multivariate method

Genetika ◽  
2013 ◽  
Vol 45 (3) ◽  
pp. 963-977 ◽  
Author(s):  
Jasmin Grahic ◽  
Fuad Gasi ◽  
Mirsad Kurtovic ◽  
Lutvija Karic ◽  
Mirha Djikic ◽  
...  
Keyword(s):  
Discriminant Analysis ◽  
Common Bean ◽  
Bosnia And Herzegovina ◽  
Principal Components ◽  
Morphological Characteristics ◽  
Principal Component ◽  
Discriminant Functions ◽  
Factor Loadings ◽  
Geographical Regions ◽  
High Level

In order to analyze morphological characteristics of locally cultivated common bean landraces from Bosnia and Herzegovina (B&H), thirteen quantitative and qualitative traits of 40 P. vulgaris accessions, collected from four geographical regions (Northwest B&H, Northeast B&H, Central B&H and Sarajevo) and maintained at the Gene bank of the Faculty of Agriculture and Food Sciences in Sarajevo, were examined. Principal component analysis (PCA) showed that the proportion of variance retained in the first two principal components was 54.35%. The first principal component had high contributing factor loadings from seed width, seed height and seed weight, whilst the second principal component had high contributing factor loadings from the analyzed traits seed per pod and pod length. PCA plot, based on the first two principal components, displayed a high level of variability among the analyzed material. The discriminant analysis of principal components (DAPC) created 3 discriminant functions (DF), whereby the first two discriminant functions accounted for 90.4% of the variance retained. Based on the retained DFs, DAPC provided group membership probabilities which showed that 70% of the accessions examined were correctly classified between the geographically defined groups. Based on the taxonomic distance, 40 common bean accessions analyzed in this study formed two major clusters, whereas two accessions Acc304 and Acc307 didn?t group in any of those. Acc360 and Acc362, as well as Acc324 and Acc371 displayed a high level of similarity and are probably the same landrace. The present diversity of Bosnia and Herzegovina?s common been landraces could be useful in future breeding programs.

Dimensional Analyses of Taxonic Data

2007 ◽  
Vol 101 (2) ◽  
pp. 617-635 ◽  
Author(s):  
William M. Grove
Keyword(s):  
Principal Component Analysis ◽  
Factor Analysis ◽  
Data Structures ◽  
Principal Components ◽  
Common Factor ◽  
Principal Component ◽  
Mixed Population ◽  
Single Population ◽  
Factor Analytic ◽  
Mixed Populations

Principal component analysis (PCA) and common factor analysis are often used to model latent data structures. Typically, such analyses assume a single population whose correlation or covariance matrix is modelled. However, data may sometimes be unwittingly sampled from mixed populations containing a taxon (nonarbitrary subpopulation) and its complement class. One derives relations between values of PCA parameters within subpopulations and their values in the mixed population. These results are then extended to factor analysis in mixed populations. As relationships between subpopulation and mixed-population principal components and factors sensitively depend on within-subpopulation structures and between-subpopulation differences, naive interpretation of PCA or factor analytic findings can potentially mislead. Several analyses, better suited to the dimensional analysis of admixture data structures, are presented and compared.

Testing Analog Circuits by PCA of Power Supply Current

2012 ◽  
Vol 157-158 ◽  
pp. 641-645 ◽  
Author(s):  
Guo He ◽  
Chao Jie Zhang ◽  
Guang Hui Chang ◽  
Shu Hai Liang
Keyword(s):  
Fault Detection ◽  
Power Supply ◽  
Analog Circuits ◽  
Principal Component ◽  
General Rule ◽  
Component Model ◽  
Level Sensor ◽  
Supply Current ◽  
Principal Component Model ◽  
Liquid Level Sensor

A method using principal component analysis (PCA) of dynamic power supply current was proposed for testing of analog circuits in this paper. The basic model of the proposed method and the general rule for analog fault detection were described in detail. At first, the principal component model of fault-free circuits was constructed. Then the circuits-under-test was compared with the principal component model to calculate the statistic for fault detection. The features of power supply current in both time and frequency domain were combined by PCA, and it could overcome the difficulty to determine threshold by empirical knowledge. The proposed method was applied to detect faults of the signal filtering and amplifying circuit, which is used in the ultrasonic liquid-level sensor. The results show that the power supply current contains information about the circuit’s faults, and can be used for fault detection of analog circuits by analyzing this signal.

Estimating and Forecasting the Term Structure of Korea Markets Using the Nelson-Siegel Model

2004 ◽  
Vol 12 (2) ◽  
pp. 101-126
Author(s):  
Joon Haeng Lee
Keyword(s):  
Term Structure ◽  
Yield Curve ◽  
Principal Component ◽  
Component Model ◽  
Structure Model ◽  
Sample Period ◽  
Term Structure Model ◽  
Long Run ◽  
Out Of Sample ◽  
Principal Component Model

This paper estimates and forecasts yield curve of korea bond market using a three factor term structure model based on the Nelson-Siegel model. The Nelson-Siegel model is in-terpreted as a model of level, slope and curvature and has the flexibility required to match the changing shape of the yield curve. To estimate this model, we use the two-step estima-tion procedure as in Diebold and Li. Estimation results show our model is Quite flexible and gives a very good fit to data. To see the forecasting ability of our model, we compare the RMSEs (root mean square error) of our model to random walk (RW) model and principal component model for out-of sample period as well as in-sample period. we find that our model has better forecasting performances over principal component model but shows slight edge over RW model especially for long run forecasting period. Considering that it is difficult for any model to show better forecasting ability over the RW model in out-of-sample period, results suggest that our model is useful for practitioners to forecast yields curve dynamics.

Use of a (MSPCA) and (SVM) Method for Diagnosis of Motor Faults

2013 ◽  
Vol 321-324 ◽  
pp. 114-117
Author(s):  
Wen Ying Chen ◽  
Ya Nan Wang ◽  
Xue Fei Wu ◽  
Yu Xiang Qu
Keyword(s):  
Principal Component Analysis ◽  
Fault Detection ◽  
Principal Component ◽  
Component Analysis ◽  
Component Model ◽  
Practical Significance ◽  
Support Vector ◽  
Multi Scale ◽  
Principal Component Model ◽  
Q Statistic

This paper uses the combination between support vector machine and multi-scale principal component analysis. For motor fault detection, the principal component model can be established in various scales. Through T2 and Q statistic judgment whether motor can run normally. The experimental results show that the method of combination vector machine and multi-scale principal component analysis is supported to diagnose motor fault. This offers a new method and idea to diagnose motor. This method improves the accuracy of motor fault detection and practical significance.

Sign in / Sign up

Export Citation Format

Share Document