Araştırma Makalesi
BibTex RIS Kaynak Göster

ZEYTİNYAĞININ YAĞ ASİDİ VE TRİGLİSERİD PROFİLLERİNİ KULLANARAK PCA'DA ÇOKLU DOĞRUSAL BAĞLANTI VE DOĞRUSAL BAĞIMLILIK YÖNETİMİ

Yıl 2026, Cilt: 51 Sayı: 2 , 409 - 422 , 31.03.2026
https://doi.org/10.15237/gida.GD26019
https://izlik.org/JA43AU96CG

Öz

Bu çalışmada, Kahramanmaraş’dan (Türkiye) 2023/2024 hasat sezonunda elde edilen ekstra sızma zeytinyağlarının (n=40) yağ asidi ve trigliserid (TAG) profillerine, çoklu doğrusal bağlantı ve doğrusal bağımlılıktan kaynaklanan matris dengesizliklerini teşhis etmek ve ele almak amacıyla temel bileşen analizi (PCA) uygulanmıştır. Veri boyutunu azaltmak ve örnek varyabilitesini belirlemek için toplam 34 değişken (23 deneysel ve 11 türetilmiş) kullanılmıştır. Standartlaştırılmış değişkenlerle yapılan ilk PCA denemesi zayıf faktörlenebilirlik göstermiş (Kaiser-Meyer-Olkin ölçüsü, KMO=0.13 ve örneklem yeterlilik ölçüsü, MSA<0.40) ve Bartlett küresellik testi, korelasyon matrisi pozitif tanımlı olmadığından hesaplanamamıştır. Çoklu doğrusal bağlantı ve doğrusal bağımlılık, Pearson korelasyonları ve regresyon tabanlı tanı araçları (varyans şişirme faktörü, VIF; tolerans indeksi, TI; koşul indeksi, CI; ve varyans ayrışım oranları, VDP) kullanılarak değerlendirilmiştir. Yüksek korelasyon ve gereksiz bilgi gösteren çoğu türetilmiş değişkenin veri setinden çıkarılarak değişken sayısı 23’e indirilmiş ve tekrar edilen PCA’da, Bartlett küresellik testi anlamlı hale gelmiş (P<0.001), ancak KMO=0.49 değeri modelin henüz yeterli faktörlenebilirliğe sahip olmadığını göstermiştir. MSA (<0.40) ve çoklu doğrusal bağlantı tanı ölçütleri (VIF>10; TI<0.10) temelinde kademeli bir eleme ile 17 değişkenli optimize bir model elde edilmiştir. Nihai model, toplam varyansın %74’ünü açıklayan 5 ana bileşen (PC) üretmiş ve kabul edilebilir bir örnekleme yeterliliği seviyesine ulaşmıştır (KMO=0.70). Promax rotasyonunda, değişkenler çoğunlukla desen matrisinde ilgili PC’lere benzersiz ve güçlü bir şekilde atanırken, yapı matrisinde ikincil yüklemeler sınırlı ölçüde gerçekleşmiştir. Skor analizinde, çoğu örnek PC1-PC2 düzleminde bir ayrım göstermiştir. Ek olarak, yalnızca 10 örnek (%25) standartlaştırılmış z-skor eşiğini aşmıştır (|z|>2). Genel olarak, sonuçlar, zeytinyağı verilerinin güvenilir ve yorumlanabilir PCA modellemesi için faktörlenebilirliğin ve çoklu bağlantı sorunlarının açık bir şekilde yönetilmesi ve korelasyon matrisi yapısı ile skor dağılımlarının dikkatlice incelenmesi gerektiğini göstermiştir.

Etik Beyan

Etik kurul raporu gerekmemektedir.

Kaynakça

  • Abdi, H., Williams, L.J. (2010). Principal component analysis. WIREs Computational Statistics, 2, 433-459. https://doi.org/10.1002/wics.101
  • Agozzino, P., Avellone, G., Bongiorno, D., Ceraulo, L., Indelicato, S., Indelicato, S., Vèkey, K. (2010). Determination of the cultivar and aging of Sicilian olive oils using HPLC‐MS and linear discriminant analysis. Journal of Mass Spectrometry, 45, 989-995. https://doi.org/10.1002/jms.1791
  • Amaral, J.S., Mafra, I., Oliveira, M.B.P. (2010). Characterization of three Portuguese varietal olive oils based on fatty acids, triacylglycerols, phytosterols and vitamin E profiles: application of chemometrics. In: Olives and Olive Oil in Health and Disease Prevention, Preedy, V.R., Watson, R.R. (Eds.). Elsevier, Oxford, UK, pp. 581-589.
  • AOCS, 2009. Preparation of Methyl Esters of Fatty Acids (Ce 2-66). Official Methods and Recommended Practices of the American Oil Chemists' Society, The Association, IL, USA.
  • Bosque-Sendra, J.M., Cuadros-Rodríguez, L., Ruiz-Samblás, C., de la Mata, A.P. (2012). Combining chromatography and chemometrics for the characterization and authentication of fats and oils from triacylglycerol compositional data—A review. Analytica Chimica Acta, 724, 1-11. https://doi.org/10.1016/j. aca.2012.02.041
  • Brown, J.D. (2009). Principal components analysis and exploratory factor analysis - Definitions, differences, and choices. Shiken: JALT Testing & Evaluation SIG Newsletter, 13, 26-30.
  • Dıraman, H. (2010). Characterization by chemometry of the most important domestic and foreign olive cultivars from the National Olive Collection Orchard of Turkey. Grasasy Aceites, 61, 341-351.
  • Ergin, M., Can, A.S., Koşkan, Ö. (2023). Factor rotation methods in factor analysis: An application on agricultural data. Ziraat Fakültesi Dergisi, 18, 134-142. https://doi.org/10.54975/isubuzfd.1370165
  • Field, A. (2009). Discovering Statistics Using IBM SPSS Statistics, 3rd ed. SAGE Publications, London, UK, 821p. Hair, J.F., Black, W.C., Babin, B.J., Anderson, R.E. (2019). Multivariate Data Analysis, 8th ed. Cengage Learning, England, 813p.
  • IOC. (2017). Determination of the Difference between Actual and Theoretical Content of Triacylglycerols with ECN 42 (COI/T.20/Doc. No. 20 /Rev. 4). International Olive Council, Spain.
  • IOC. (2024). Trade standard applying to olive oils and olive-pomace oils (COI T.15 NC No 3 Rev. 20). International Olive Council, Spain.
  • IOC. (2026). Olive sector statistics - December 2025 and forecasts. February 2026, https://www.internationaloliveoil.org/olive-sector-statistics-december-2025-and-forecasts/.
  • Johnson, R.A., Wichern, D.W. (2007). Applied Multivariate Statistical Analysis, 6th ed. Pearson Prentice Hall, NJ, USA, 773p.
  • Jolliffe, I.T. (2002). Principal Component Analysis, 2nd ed. Springer, New York, NY, USA, 487p.
  • Kim, J.H. (2019). Multicollinearity and misleading statistical results. Korean J Anesthesiol, 72, 558-569. https://doi.org/10.4097/kja.19087
  • Kline, P. (1994). An Easy Guide to Factor Analysis. Routledge, New York, NY, USA, 208p.
  • O’Brien, R.M. (2007). A caution regarding rules of thumb for variance inflation factors. Quality & Quantity, 41, 673-690. https://doi.org/10.1007/s11135-006-9018-6
  • Salvatore, E., Bevilacqua, M., Bro, R., Marini, F., Cocchi, M. (2013). Classification methods of multiway arrays as a basic tool for food PDO authentication. In: Comprehensive Analytical Chemistry, de la Guardia, M., Gonzálvez, A. (Eds.). Elsevier pp. 339-382. https://doi.org/10.1016/B978-0-444-59562-1.00014-1
  • Tabachnick, B.G., Fidell, L.S. (2013). Using Multivariate Statistics. Pearson Education, New York, NY, USA, 983p.
  • UZZK. (2023). 2023-2024 Üretim Sezonu Sofralık Zeytin ve Zeytinyağı Rekoltesi Ulusal Resmi Tespit Heyeti Raporu. Date Accessed: 16.07.2024, https://www. antalyaborsa.org.tr/_fm/211-2023101009234.pdf.
  • Yorulmaz, A. (2009). Determination of Phenolic, Sterol and Triglyceride Structures of Turkish Olive Oils (in Turkish). Ph.D. Thesis. Ankara University, Graduate School of Natural and Applied Sciences, Ankara, Türkiye, 148p.
  • Yorulmaz, A., Yavuz, H., Tekin, A. (2014). Characterization of Turkish olive oils by triacylglycerol structures and sterol profiles. Journal of the American Oil Chemists' Society, 91, 2077-2090. https://doi.org/10.1007/s11746-014-2554-7

MANAGING MULTICOLLINEARITY AND LINEAR DEPENDENCE IN PCA OF OLIVE OIL USING FATTY ACID AND TRIGLYCERIDE PROFILES

Yıl 2026, Cilt: 51 Sayı: 2 , 409 - 422 , 31.03.2026
https://doi.org/10.15237/gida.GD26019
https://izlik.org/JA43AU96CG

Öz

In this study, principal component analysis (PCA) was applied to fatty acid and triglyceride (TAG) profiles of extra virgin olive oils (n=40) obtained from Kahramanmaraş (Türkiye) during the 2023/2024 harvest season to diagnose and address matrix instabilities caused by multicollinearity and linear dependence. A total of 34 variables (23 experimental and 11 derived) were used to reduce data dimensionality and determine sample variability. The initial PCA attempt with standardized variables showed poor factorability (Kaiser-Meyer-Olkin measure, KMO=0.13; measure of sampling adequacy, MSA<0.40), and Bartlett’s test of sphericity could not be calculated because the correlation matrix was not positive definite. Multicollinearity and linear dependence were assessed using Pearson correlations and regression-based diagnostics (variance inflation factor, V IF; t olerance i ndex, T I; condition index, CI; and variance decomposition proportions, VDP). Most derived variables showing high correlations and redundant information were removed from the dataset, reducing the number of variables to 23, and in the repeated PCA, Bartlett’s test of sphericity became significant (P<0.001), but the KMO value of 0.49 indicated that the model still had insufficient factorability. An optimized 17-variable model was obtained through a stepwise screening based on MSA (<0.40) and multicollinearity criteria (VIF>10; TI<0.10). The final m odel p roduced 5 principal c omponents ( PCs) t hat e xplained 7 4% of t he t otal variance and reached an acceptable level of sampling adequacy (KMO=0.70). After Promax rotation, variables were mostly loaded uniquely and strongly on the relevant PCs in the pattern matrix, while secondary loadings were limited in the structure matrix. In the score analysis, most samples showed separation on the PC1-PC2 plane. Additionally, only 10 samples (25%) exceeded the standardized z-score threshold (|z|>2). Overall, the results indicated that for reliable and interpretable PCA modelling of the olive oil data, it is necessary to clearly manage factorability and multicollinearity issues and to carefully examine the correlation matrix structures and the score distributions.

Etik Beyan

An ethics committee report is not required

Kaynakça

  • Abdi, H., Williams, L.J. (2010). Principal component analysis. WIREs Computational Statistics, 2, 433-459. https://doi.org/10.1002/wics.101
  • Agozzino, P., Avellone, G., Bongiorno, D., Ceraulo, L., Indelicato, S., Indelicato, S., Vèkey, K. (2010). Determination of the cultivar and aging of Sicilian olive oils using HPLC‐MS and linear discriminant analysis. Journal of Mass Spectrometry, 45, 989-995. https://doi.org/10.1002/jms.1791
  • Amaral, J.S., Mafra, I., Oliveira, M.B.P. (2010). Characterization of three Portuguese varietal olive oils based on fatty acids, triacylglycerols, phytosterols and vitamin E profiles: application of chemometrics. In: Olives and Olive Oil in Health and Disease Prevention, Preedy, V.R., Watson, R.R. (Eds.). Elsevier, Oxford, UK, pp. 581-589.
  • AOCS, 2009. Preparation of Methyl Esters of Fatty Acids (Ce 2-66). Official Methods and Recommended Practices of the American Oil Chemists' Society, The Association, IL, USA.
  • Bosque-Sendra, J.M., Cuadros-Rodríguez, L., Ruiz-Samblás, C., de la Mata, A.P. (2012). Combining chromatography and chemometrics for the characterization and authentication of fats and oils from triacylglycerol compositional data—A review. Analytica Chimica Acta, 724, 1-11. https://doi.org/10.1016/j. aca.2012.02.041
  • Brown, J.D. (2009). Principal components analysis and exploratory factor analysis - Definitions, differences, and choices. Shiken: JALT Testing & Evaluation SIG Newsletter, 13, 26-30.
  • Dıraman, H. (2010). Characterization by chemometry of the most important domestic and foreign olive cultivars from the National Olive Collection Orchard of Turkey. Grasasy Aceites, 61, 341-351.
  • Ergin, M., Can, A.S., Koşkan, Ö. (2023). Factor rotation methods in factor analysis: An application on agricultural data. Ziraat Fakültesi Dergisi, 18, 134-142. https://doi.org/10.54975/isubuzfd.1370165
  • Field, A. (2009). Discovering Statistics Using IBM SPSS Statistics, 3rd ed. SAGE Publications, London, UK, 821p. Hair, J.F., Black, W.C., Babin, B.J., Anderson, R.E. (2019). Multivariate Data Analysis, 8th ed. Cengage Learning, England, 813p.
  • IOC. (2017). Determination of the Difference between Actual and Theoretical Content of Triacylglycerols with ECN 42 (COI/T.20/Doc. No. 20 /Rev. 4). International Olive Council, Spain.
  • IOC. (2024). Trade standard applying to olive oils and olive-pomace oils (COI T.15 NC No 3 Rev. 20). International Olive Council, Spain.
  • IOC. (2026). Olive sector statistics - December 2025 and forecasts. February 2026, https://www.internationaloliveoil.org/olive-sector-statistics-december-2025-and-forecasts/.
  • Johnson, R.A., Wichern, D.W. (2007). Applied Multivariate Statistical Analysis, 6th ed. Pearson Prentice Hall, NJ, USA, 773p.
  • Jolliffe, I.T. (2002). Principal Component Analysis, 2nd ed. Springer, New York, NY, USA, 487p.
  • Kim, J.H. (2019). Multicollinearity and misleading statistical results. Korean J Anesthesiol, 72, 558-569. https://doi.org/10.4097/kja.19087
  • Kline, P. (1994). An Easy Guide to Factor Analysis. Routledge, New York, NY, USA, 208p.
  • O’Brien, R.M. (2007). A caution regarding rules of thumb for variance inflation factors. Quality & Quantity, 41, 673-690. https://doi.org/10.1007/s11135-006-9018-6
  • Salvatore, E., Bevilacqua, M., Bro, R., Marini, F., Cocchi, M. (2013). Classification methods of multiway arrays as a basic tool for food PDO authentication. In: Comprehensive Analytical Chemistry, de la Guardia, M., Gonzálvez, A. (Eds.). Elsevier pp. 339-382. https://doi.org/10.1016/B978-0-444-59562-1.00014-1
  • Tabachnick, B.G., Fidell, L.S. (2013). Using Multivariate Statistics. Pearson Education, New York, NY, USA, 983p.
  • UZZK. (2023). 2023-2024 Üretim Sezonu Sofralık Zeytin ve Zeytinyağı Rekoltesi Ulusal Resmi Tespit Heyeti Raporu. Date Accessed: 16.07.2024, https://www. antalyaborsa.org.tr/_fm/211-2023101009234.pdf.
  • Yorulmaz, A. (2009). Determination of Phenolic, Sterol and Triglyceride Structures of Turkish Olive Oils (in Turkish). Ph.D. Thesis. Ankara University, Graduate School of Natural and Applied Sciences, Ankara, Türkiye, 148p.
  • Yorulmaz, A., Yavuz, H., Tekin, A. (2014). Characterization of Turkish olive oils by triacylglycerol structures and sterol profiles. Journal of the American Oil Chemists' Society, 91, 2077-2090. https://doi.org/10.1007/s11746-014-2554-7
Toplam 22 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Gıda Mühendisliği
Bölüm Araştırma Makalesi
Yazarlar

Ayşe Gizem Gül Bu kişi benim 0009-0006-3439-5751

Abdullah Sinan Çolakoğlu 0000-0002-5928-3581

Gönderilme Tarihi 17 Şubat 2026
Kabul Tarihi 17 Mart 2026
Yayımlanma Tarihi 31 Mart 2026
DOI https://doi.org/10.15237/gida.GD26019
IZ https://izlik.org/JA43AU96CG
Yayımlandığı Sayı Yıl 2026 Cilt: 51 Sayı: 2

Kaynak Göster

APA Gül, A. G., & Çolakoğlu, A. S. (2026). MANAGING MULTICOLLINEARITY AND LINEAR DEPENDENCE IN PCA OF OLIVE OIL USING FATTY ACID AND TRIGLYCERIDE PROFILES. Gıda, 51(2), 409-422. https://doi.org/10.15237/gida.GD26019
AMA 1.Gül AG, Çolakoğlu AS. MANAGING MULTICOLLINEARITY AND LINEAR DEPENDENCE IN PCA OF OLIVE OIL USING FATTY ACID AND TRIGLYCERIDE PROFILES. GIDA. 2026;51(2):409-422. doi:10.15237/gida.GD26019
Chicago Gül, Ayşe Gizem, ve Abdullah Sinan Çolakoğlu. 2026. “MANAGING MULTICOLLINEARITY AND LINEAR DEPENDENCE IN PCA OF OLIVE OIL USING FATTY ACID AND TRIGLYCERIDE PROFILES”. Gıda 51 (2): 409-22. https://doi.org/10.15237/gida.GD26019.
EndNote Gül AG, Çolakoğlu AS (01 Mart 2026) MANAGING MULTICOLLINEARITY AND LINEAR DEPENDENCE IN PCA OF OLIVE OIL USING FATTY ACID AND TRIGLYCERIDE PROFILES. Gıda 51 2 409–422.
IEEE [1]A. G. Gül ve A. S. Çolakoğlu, “MANAGING MULTICOLLINEARITY AND LINEAR DEPENDENCE IN PCA OF OLIVE OIL USING FATTY ACID AND TRIGLYCERIDE PROFILES”, GIDA, c. 51, sy 2, ss. 409–422, Mar. 2026, doi: 10.15237/gida.GD26019.
ISNAD Gül, Ayşe Gizem - Çolakoğlu, Abdullah Sinan. “MANAGING MULTICOLLINEARITY AND LINEAR DEPENDENCE IN PCA OF OLIVE OIL USING FATTY ACID AND TRIGLYCERIDE PROFILES”. Gıda 51/2 (01 Mart 2026): 409-422. https://doi.org/10.15237/gida.GD26019.
JAMA 1.Gül AG, Çolakoğlu AS. MANAGING MULTICOLLINEARITY AND LINEAR DEPENDENCE IN PCA OF OLIVE OIL USING FATTY ACID AND TRIGLYCERIDE PROFILES. GIDA. 2026;51:409–422.
MLA Gül, Ayşe Gizem, ve Abdullah Sinan Çolakoğlu. “MANAGING MULTICOLLINEARITY AND LINEAR DEPENDENCE IN PCA OF OLIVE OIL USING FATTY ACID AND TRIGLYCERIDE PROFILES”. Gıda, c. 51, sy 2, Mart 2026, ss. 409-22, doi:10.15237/gida.GD26019.
Vancouver 1.Ayşe Gizem Gül, Abdullah Sinan Çolakoğlu. MANAGING MULTICOLLINEARITY AND LINEAR DEPENDENCE IN PCA OF OLIVE OIL USING FATTY ACID AND TRIGLYCERIDE PROFILES. GIDA. 01 Mart 2026;51(2):409-22. doi:10.15237/gida.GD26019

by-nc.png       GIDA Dergisi Creative Commons Atıf-Gayri Ticari 4.0 (CC BY-NC 4.0) Uluslararası Lisansı ile lisanslanmıştır.