Two types of single-peaked data: Correspondence analysis as an alternative to principal component analysis

2009 ◽  
Vol 53 (8) ◽  
pp. 3117-3128 ◽  
Author(s):  
Marike Polak ◽  
Willem J. Heiser ◽  
Mark de Rooij
Keyword(s):  
Principal Component Analysis ◽  
Correspondence Analysis ◽  
Principal Component ◽  
Component Analysis

scholarly journals Profil Kawasan Reboisasi Mangrove Kepulauan Seribu Berdasarkan Karakteristik Lingkungan dan Fauna Makrobentik Terkait

2021 ◽  
Vol 5 (3) ◽  
pp. 315
Author(s):  
Febrianti Lestari ◽  
Syahrial Syahrial ◽  
Rika Anggraini ◽  
Yudho Andika ◽  
Cut Meurah Nurul 'Akla ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Correspondence Analysis ◽  
Principal Component ◽  
Component Analysis

Fauna makrobentik sering digunakan sebagai bioindikator kualitas lingkungan dan informasi tentang karakteristik lingkungan maupun keberadaan fauna makrobentik di kawasan reboisasi mangrove masih sangat terbatas. Kajian profil kawasan reboisasi mangrove Kepulauan Seribu berdasarkan karakteristik lingkungan dan fauna makrobentiknya telah dilakukan pada bulan Maret 2014. Kajian ini bertujuan untuk mengetahui kondisi ekologi perairan di sekitar kawasan reboisasi mangrove Kepulauan Seribu. Untuk mengetahui keterkaitan karakteristik lingkungan dan fauna makrobentik dengan stasiun pengamatan dilakukan dengan statistik Correspondence Analysis (CA), sedangkan karakteristik lingkungan penentu fauna makrobentik serta hubungannya dilakukan dengan statistik Principal Component Analysis (PCA) dan regresi linier sederhana. Hasil kajian memperlihatkan bahwa konsentrasi karakteristik lingkungan yang diukur tidak begitu berbeda antar stasiun dan tidak melebihi ambang baku mutu untuk kehidupan biota laut. Selanjutnya fauna makrobentik yang ditemukan terdiri dari 6 spesies dengan kepadatan tertingginya berada di Stasiun 3 (05.00 ind/m2) dan terendahnya di Stasiun 1 (02.00 ind/m2). Pada Stasiun 1 konsentrasi pH dan suhunya sangat tinggi, sedangkan Stasiun 2 dan 3 konsentrasi salinitasnya yang tinggi. Fauna makrobentik Atilia (Columbella) scripta, Metopograpsus latifrons, Littoraria scabra, Saccostrea cucculata dan Cardisoma carnifex dapat berasosiasi dengan mangrove di semua stasiun. Selain itu, karakteristik lingkungan yang menentukan keberadaan fauna makrobentik C. carnifex adalah parameter pH, dimana semakin tinggi konsentrasi pH, maka kepadatan C. carnifex semakin menurun. Selain itu, karakteristik lingkungan yang menentukan keberadaan fauna makrobentik S. cucculata, M. latifrons dan A. scripta ditentukan oleh parameter DO dan salinitas yakni semakin rendah konsentrasi DO dan salinitas, maka kepadatan S. cucculata, M. latifrons maupun A. scripta akan semakin tinggi.

Correspondence Analysis In Heavy Mineral Interpretation

1994 ◽  
Author(s):  
J. Tourenq ◽  
V. Rohrlich
Keyword(s):  
Principal Component Analysis ◽  
Correspondence Analysis ◽  
Principal Component ◽  
Sedimentary Basins ◽  
Component Analysis ◽  
Heavy Mineral ◽  
Heavy Minerals ◽  
Data Sets ◽  
Mineral Data ◽  
Non Parametric

Correspondence analysis, a non-parametric principal component analysis, has been used to analyze heavy mineral data so that variations between both samples and minerals can be studied simultaneously. Four data sets were selected to demonstrate the method. The first example, modern sediments from the River Nile, illustrates how correspondence analysis brings out extra details in heavy mineral associations. The other examples come from the Plio-Quaternary "Bourbonnais Formation" of the French Massif Central. The first data set demonstrates how the principal factor plane (with axes 1 and 2) highlights relationships between geographical position and the predominant heavy mineral association (metamorphic minerals and zircon), suggesting the paleogeographic source. In the second set, the factor plane of axes 1 and 3 indicates a subdivision of the metamorphic mineral assemblage, suggesting two sources of metamorphic minerals. Finally, outcrop samples were projected onto the factor plane and reveal ancient drainage systems important for the accumulation of the Bourbonnais sands. Statistical methods used in interpreting heavy minerals in sediments range from simple and classical methods, such as calculation of means and standard deviations, to the calculation of correspondences and variances. Use of multivariate methods is increasingly frequent (Maurer, 1983; Stattegger, 1986; 1987; Delaune et al., 1989; Mezzadri and Saccani, 1989) since the first studies of Imbrie and vanAndel (1964). Ordination techniques such as principal component analysis (Harman, 1961) synthesize large amounts of data and extract the most important relationships. We have chosen a non-parametric form of principal component analysis called correspondence analysis. This technique has been used in sedimentology by Chenet and Teil (1979) to investigate deep-sea samples, by Cojan and Teil (1982) and Mercier et al. (1987) to define paleoenvironments, and by Cojan and Beaudoin (1986) to show paleoecological control of deposition in French sedimentary basins. Correspondence analysis has been used successfully to interpret heavy mineral data (Tourenq et al, 1978a, 1978b; Bolin et al, 1982; Tourenq, 1986, 1989; Faulp et al, 1988; Ambroise et al, 1987). We provide examples of different situations where the method can be applied. We will not present the mathematical and statistical procedures involved in correspondence analysis, but refer readers to Benzécri et al.

Sign in / Sign up

Export Citation Format

Share Document