Evaluation of the effect of morphological traits on fish growth by comparison using ridge and ordinary least squares regression
DOI:
https://doi.org/10.61326/jofbs.v4i1.03Keywords:
Fish morphometry, Multicollinearity, Variance influence factor, Capoeta damascinaAbstract
Growth in fish is characterized by length and weight and studies that encompassing relationships among the fish length and weigh with some morphometric traits provide crucial information in the field of fish biology. High correlations (or multicollinearity) among the morphometric traits in fish morphology studies is a well-known phenomenon. If the relationship between growth and morphometry is modeled using the ordinary least squares estimator (OLS), the parameter estimates are likely to be too large in absolute value and possibly have the wrong sign due to the problem of multicollinearity. The ridge regression (RR) estimator has been proposed to avoid the adverse effects of multicollinearity among the regressors. In this study, therefore, multiple linear RR was used to model relationship fish length and fish weight to some predictive metric traits. Predictive traits were predorsal length, head length, post dorsal length, head height, and eye diameter. Data were derived from a total of 126 Capoeta damascina individuals sampled from the Euphrates, Türkiye. The ridge optimal k-parameter, producing acceptable variance influence factor (VIF<10), was determined as 0.021 for both of growth indices considering a combination of ridge trace and VIF trace plots and MSE and VIF values produced from an array of k values (0.0≤ k≤1.00). Although, small decreases were observed in the adjusted R-square values (ARS) obtained by RR compared to the ARS values obtained by OLS, a significant decrease in VIF values outweighs this drawback, indicating that the models are more stable. The methodological approach and findings in this study may contribute to filling a gap in the literature regarding the relationships between fish growth and morphology. Additionally, it could enhance better growth predictions for different fish species, aiding sustainable fisheries management and the selective cultivation of desired fish traits in aquaculture by improving the understanding of morphometric features.
References
Adeboye, N. O., Fagoyinbo, I. S., & Olatayo, T. O. (2014). Estimation of the Effect of Multicollinearity on the Standard Error for Regression Coefficients. Journal of Mathematics, 10(4), 16-20. https://doi.org/10.9790/5728-10411620
Albayrak, A. S. (2005). Çoklu doğrusal bağlanti halinde enküçük kareler tekniğinin alternatifi yanlı tahmin teknikleri ve bir uygulama. Uluslararası Yönetim İktisat ve İşletme Dergisi, 1(1), 105-126. (in Turkish)
Alp, A., Akyüz, A., Kara, C., & Güneş, H. (2013). Assessment of movements of Capoeta capoeta in Bulam Stream, Euphrates River, and efficiency of the fish passage [Oral presentation]. International Symposium on Fisheries and Aquatic Sciences, Erzurum, Turkey.
Alp, A., Kara, C., Büyükçapar, H. M., & Bülbül, O. (2005). Age, Growth and Condition of Capoeta capoeta angorae Hanko 1924 from the Upper Water Systems of the River Ceyhan, Turkey. Turkish Journal of Veterinary & Animal Sciences, 29(3), 665-676.
Arechavala-Lopez, P., Sanchez-Jerez, P., Bayle-Sempere, J. T., Sfakianakis, D. G., & Somarakis, S. (2012). Morphological Differences between Wild and Farmed Mediterranean Fish. Hydrobiologia, 679, 217-231.
Asadollah S., Soofiani, N.M., Keivany, Y., & Hatami, R. (2017). Age and Growth of the Mesopotamian barb, Capoeta damascina, in Central Iran. Iranian Journal of Fisheries Sciences, 16(2), 511-521. https://doi.org/10.22092/ijfs.2018.114675
Büyükuysal, M. Ç., & Öz, İ. İ. (2016). Çoklu Doğrusal Bağıntı Varlığında En Küçük Karelere Alternatif Yaklaşım: Ridge Regresyon. Düzce Üniversitesi Sağlık Bilimleri Enstitüsü Dergisi, 6(2), 110-114. (in Turkish)
Clabaut, C., Bunje, P. M., Salzburger, W., & Meyer, A. (2007). Geometric Morphometric Analyses Provide Evidence for the Adaptive Character of the Tanganyikan Cichlid Fish Radiations. Evolution, 61(3), 560-578. https://doi.org/10.1111/j.1558-5646.2007.00045.x
Daoud, J. I. (2017). Multicollinearity and Regression Analysis. Journal of Physics: Conference Series, 949, 012009. https://doi.org/10.1088/1742-6596/949/1/012009
Forrester, J. B., & Kalivas, J. H. (2004). Ridge Regression Optimization Using a Harmonious Approach. Journal of Chemometrics, 18(7‐8), 372-384. https://doi.org/10.1002/cem.883
Gao, Y., Fu, Z., Yang, J., Yu, M., & Wang, W. (2024). Spatial–temporal Differentiation and Influencing Factors of Marine Fishery Carbon Emission Efficiency in China. Environment, Development and Sustainability, 26(1), 453-478. https://doi.org/10.1007/s10668-022-02716-6
Golub, G. H., Heath, M., & Wahba, G. (1979). Generalized Cross-Validation as a Method for Choosing a Good Ridge Parameter. Technometrics, 21(2), 215-223. https://doi.org/10.1080/00401706.1979.10489751
Karakaş, S. (2008). Çoklu doğrusal bağlantı problemi ve yanlı regresyon tahmincileri [Master's thesis, İstanbul Universty]. (in Turkish)
Katz, M. H. (2006). Multivariable analysis, A practical guide for clinicians (2nd ed.). Cambridge University Press.
Keppeler, F. W., Montaña, C. G., & Winemiller, K. O. (2020). The Relationship between Trophic Level and Body Size in Fishes Depends on Functional Traits. Ecological Monographs, 90(4), e01415. https://doi.org/10.1002/ecm.1415
Khalaf, G., & Shukur, G. (2005). Choosing Ridge Parameter for Regression Problems. Communications in Statistics - Theory and Methods, 34(5), 1177-1182. https://doi.org/10.1081/STA-200056836
Kyritsi, S., & Moutopoulos, D. K. (2018). Mouth Size and Body Length Relations for Freshwater Fish Species. Turkish Journal of Fisheries and Aquatic Sciences, 18(11), 1331-1332. https://doi.org/10.4194/1303-2712-v18_11_10
Lenhardt, M., Jarić, I., Cvijanović, G., Kolarević, J., Gačić, Z., Smederevac-Lalić, M., & Višnjić-Jeftić, Ž. (2012). Comparison of Morphological Characters between Wild and Cultured Sterlet (Acipenser ruthenus L.). Slovenian Veterinary Research, 49(4), 177-84.
Liyandja, T. L., Armbruster, J. W., Poopola, M. O., & Stiassny, M. L. (2022). Evolutionary Convergence in Body Shape Obscures Taxonomic Diversity in Species of the African Labeo forskalii Group: Case Study of L. parvus Boulenger 1902 and L. ogunensis Boulenger 1910. Journal of Fish Biology, 101(4), 898-913. https://doi.org/10.1111/jfb.15148
Mami, A. M., Abdalla, A., & Bin Ismaeil, E. H. (2021). Selecting the Optimal Value of Penalty Parameter K in Ridge Regression Estimators. International Journal of Sciences: Basic and Applied Research, 60(5), 189-209.
Martins, B. O., Franco‐Belussi, L., Siqueira, M. S., Fernandes, C. E., & Provete, D. B. (2021). The Evolution of Red Blood Cell Shape in Fishes. Journal of Evolutionary Biology, 34(3), 537-548. https://doi.org/10.1111/jeb.13757
McDonald, G. C. (2009). Ridge Regression. Wiley Interdisciplinary Reviews: Computational Statistics, 1(1), 93-100. https://doi.org/10.1002/wics.14
Mojekwu, T. O., & Anumudu, C. I. (2015). Advanced Techniques for Morphometric Analysis in Fish. Journal of Aquaculture Research & Development, 6(8), 1-6. https://doi.org/10.4172/2155-9546.1000354
Nandi S., & Saikia S.K. (2015). Role of Morphometry in Determining the Feeding Success of Small Freshwater Fish Species: Multivariate Analysis of Amblypharyngodon mola, Puntius ticto, and Esomus danricus. Archives of Polish Fisheries, 23, 79-90. https://doi.org/10.1515/aopf-2015-0009
Niu, S. Q., Haake, D. M., & Knouft, J. H. (2019). Gut Content Biomass of Stream Fishes: Associations with Streamflow Velocity, Population Density, and Prey Abundance at Two Spatial Scales. Hydrobiologia, 826(1), 85-97. https://doi.org/10.1007/s10750-018-3719-4
Okamura, H., Yamashita, Y., & Ichinokawa, M. (2017). Ridge Virtual Population Analysis to Reduce the Instability of Fishing Mortalities in the Terminal Year. ICES Journal of Marine Science, 74(9), 2427-2436. https://doi.org/10.1093/icesjms/fsx089
Oke, J., Akinkunmi, W. B., & Etebefia, S. O. (2019). Use of Correlation, Tolerance and Variance Inflation Factor for Multicollinearity Test. GSJ, 7(5), 652-659.
Ölmez, P., & Yağanoğlu, A. M. (2023). Use of Ridge Regression Analysis in the Multicollinearity in Animal Science. Journal of Biometry Studies, 3(2), 32-38. https://doi.org/10.61326/jofbs.v3i2.02
Orbach, D. N., Donovan, M., & Purchase, C. F. (2019). Sexually Selected Traits are Larger and More Variable in Male than Female Beach‐spawning Capelin, Mallotus villosus. Journal of Fish Biology, 95(6), 1385-1390. https://doi.org/10.1111/jfb.14145
Özkale, M. R., & Altuner, H. (2021). Bootstrap Selection of Ridge Regularization Parameter: A Comparative Study via a Simulation Study. Communications in Statistics - Simulation and Computation, 52(8), 3820-3838. https://doi.org/10.1080/03610918.2021.1948574
Pino, M. M., Rivas, D. V., Carrera, C. O., Avila, N. C., Salazar, T. M., Díaz Merino, H., Gastañaduy, C. C., Ysa, R. S., Lozado, J. C., Santos, R. C., Gastañaduy, D. C., & Palacios, L. V. (2021). Lasso Model for Morphological Covariation Patterns between Colossoma macropomum and Piaractus orinoquensis × Colossoma macropomum Hybrid. Journal of Biochemical Technology, 12(1), 45-48. https://doi.org/10.51847/pFILL2lk3G
Revelle, W., & Revelle, M. W. (2015). Package ‘psych’. The comprehensive R archive network, 337(338).
Rikardsen, A. H., & Johansen, M. (2003). A Morphometric Method for Estimation of Total Lipid Level in Live Arctic Charr: A Case Study of Its Application on Wild Fish. Journal of Fish Biology, 62(3), 724-734. https://doi.org/10.1046/j.1095-8649.2003.00062.x
Rivas Villegas, D., Rivero Alzamora, C., Carrera Osorio, C., Calderón Ramírez, L., Rojas Correa, L., Cáceres, N., Sánchez Palacios, J., Del Carpio Franco, C., Vásquez Grados, M., Salinas Cruz, L., Rojas Ponce, K., Figueroa Rodríguez, J. J., & Quipas Bellizza, M. M. (2024). Comparison of Collinearity Indices for Linear Models in Agricultural Trials. OnLine Journal of Biological Sciences, 24(2), 195-207. https://doi.org/10.3844/ojbsci.2024.195.207
Sahin, M., Yavuz, E., & Uckardes, F. (2018). Multicollinearity Problem and Bias Estimates in Japanese Quail. Pakistan Journal of Zoology, 50(2), 757-761. http://dx.doi.org/10.17582/journal.pjz/2018.50.2.757.761
Thompson, C. G., Kim, R. S., Aloe, A. M., & Becker, B. J. (2017). Extracting the Variance Inflation Factor and other Multicollinearity Diagnostics from Typical Regression Results. Basic and Applied Social Psychology, 39(2), 81-90. https://doi.org/10.1080/01973533.2016.1277529
Turan, C. (1999). A Note on the Examination of Morphometric Differentiation among Fish Populations: The Truss System. Turkish Journal of Zoology, 23(3), 259-264.
Ullah, M. I., Aslam, M., & Altaf, S. (2018). lmridge: A Comprehensive R Package for Ridge Regression. The R Journal, 10(2), 326-346.
Williams, G. J. (2011). Data mining with Rattle and R: The art of excavating data for knowledge discovery. Springer.
Winans, G. A. (1987). Using morphometric and meristic characters for identifying stocks of fish [Oral presentation]. The Slock Identification Workshop, Florida, USA.
Yazıcı, R. & Yazıcıoğlu, O. (2020). Some Morphometric Relationships of Wels Catfish (Silurus glanis L., 1758) Inhabiting Sıddıklı Dam Lake (Kırşehir, Turkey). Journal of Anatolian Environmental and Animal Sciences, 5(2), 199-204. https://doi.org/10.35229/jaes.718647
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Mehmet Fatih CAN, Cemil KARA
This work is licensed under a Creative Commons Attribution 4.0 International License.
