[Análise de modelagem linear usado para determinar os fatores que afetam o rendimento leiteiro de 305 dias]

Animal Science and Technology and Inspection of Animal Products • Arq. Bras. Med. Vet. Zootec. 73 (04) • Jul-Aug 2021 • https://doi.org/10.1590/1678-4162-12346 copiar

[Análise de modelagem linear usado para determinar os fatores que afetam o rendimento leiteiro de 305 dias]

Autoria SCIMAGO INSTITUTIONS RANKINGS

RESUMO

O objetivo deste estudo foi modelar os fatores que afetam a produção de leite das vacas leiteiras em 305 dias, utilizando a Técnica de Modelagem Linear Automática (ALM). O conjunto de dados deste estudo consistia em oito raças diferentes de vacas cultivadas em oito províncias da Turquia. Os resultados da ALM mostraram que a precisão do modelo era de 64,2% significa que 64,2% da variação na produção de leite de 305 dias poderia ser explicada pelo modelo construído. O modelo criado consistia de quatro fatores: Raça, Comprimento da Lactação, Paridade e Província. Portanto, esses fatores selecionados foram mais eficientes do que os outros na previsão da produção de leite de 305 dias.

Palavras-chave:
305 dias de produção de leite; modelagem linear automática; previsão; vacas leiteiras

Autoria

S. Genç

Kirsehir Ahi Evran University ˗ Faculty of Agriculture ˗ Kirsehir, TurkeyKirsehir Ahi Evran UniversityTurkeyKirsehir, TurkeyKirsehir Ahi Evran University ˗ Faculty of Agriculture ˗ Kirsehir, Turkey

https://orcid.org/0000-0002-1512-9072

M. Mendeş

Canakkale Onsekiz Mart University ˗ Faculty of Agriculture ˗ Canakkale, TurkeyCanakkale Onsekiz Mart UniversityTurkeyCanakkale, TurkeyCanakkale Onsekiz Mart University ˗ Faculty of Agriculture ˗ Canakkale, Turkey

https://orcid.org/0000-0003-0109-9914

E-mail: serdargenc1983@gmail.com

SCIMAGO INSTITUTIONS RANKINGS

Figuras

Figuras (4)

Thumbnail

Figure 1
Accuracy Level of the Model. Importance levels of the predictors have been presented in Figure 2.

Thumbnail

Figure 2
Importance Levels of the Variables or Predictors. After the most important factors or variables are determined (Figure 2), the Automatic Linear Modeling is re-run using just importance variables namely Breed, Lactation Length, Parity, and Province. The final results of Automatic Linear Modeling are presented in Figure 3 and 4.

Thumbnail

Figure 3
Diagram for showing statistical significance of variables or factors. This diagram is corresponding to the ANOVA table after multiple linear regression analysis. The predictors are ordered from top to bottom in order of importance levels, and the thickness of each line shows the statistical significance (P-values) of the relevant effect. As it is seen from the diagram in Figure 3, the Breed is the most important predictor or the factor affect the 305-day milk yield estimates, and it is followed by lactation length, parity, and province based on importance levels of them. The effect of all four predictors were statistically significant (P=0.000).

Thumbnail

Figure 4
Diagram for showing the effect of significant factors. Especially in recent years, regression-based methods which can present the results graphically have become very popular (Berry et al., 2007BERRY, D.P.; BUCKLEY, F.; DILLON, P. Body condition score and live-weight effects on milk production in Irish Holstein-Friesian dairy cows. Animal, v.1, p.1351-1359, 2007.; Mendes and Akkartal, 2009MENDES, M.; AKKARTAL, E. Regression tree analysis for predicting slaughter weight in broilers. Ital. J. Anim. Sci., v.8, p.615-624, 2009.). Although the Automatic Linear Modeling is not commonly used regression-based method, we think that this method will become increasingly use for investigating relations between a dependent and many independent variables and determining the factors affecting interested variable. As a result of the ALM, the four most important factors were determined as breed, lactation length, parity, and province. Therefore, these factors should be included to the model in predicting the 305-day milk yield. With this model, 64.2% of the variation in the 305-day milk yield could be explained (Mendes and Akkartal, 2009; Topal et al., 2010TOPAL, M.; AKSAKAL, V.; BAYRAM, B. et al. An analysis of the factors affecting birth weight and actual milk yield in swedish red cattle using regression tree analysis. J. Anim. Plant Sci., v.20, p.63-69, 2010.).

Figure 1 Accuracy Level of the Model. Importance levels of the predictors have been presented in Figure 2.

Figure 2 Importance Levels of the Variables or Predictors. After the most important factors or variables are determined (Figure 2), the Automatic Linear Modeling is re-run using just importance variables namely Breed, Lactation Length, Parity, and Province. The final results of Automatic Linear Modeling are presented in Figure 3 and 4.

Figure 3 Diagram for showing statistical significance of variables or factors. This diagram is corresponding to the ANOVA table after multiple linear regression analysis. The predictors are ordered from top to bottom in order of importance levels, and the thickness of each line shows the statistical significance (P-values) of the relevant effect. As it is seen from the diagram in Figure 3, the Breed is the most important predictor or the factor affect the 305-day milk yield estimates, and it is followed by lactation length, parity, and province based on importance levels of them. The effect of all four predictors were statistically significant (P=0.000).

Figure 4 Diagram for showing the effect of significant factors. Especially in recent years, regression-based methods which can present the results graphically have become very popular (**Berry et al., 2007BERRY, D.P.; BUCKLEY, F.; DILLON, P. Body condition score and live-weight effects on milk production in Irish Holstein-Friesian dairy cows. Animal, v.1, p.1351-1359, 2007.; Mendes and Akkartal, 2009MENDES, M.; AKKARTAL, E. Regression tree analysis for predicting slaughter weight in broilers. Ital. J. Anim. Sci., v.8, p.615-624, 2009.). Although the Automatic Linear Modeling is not commonly used regression-based method, we think that this method will become increasingly use for investigating relations between a dependent and many independent variables and determining the factors affecting interested variable. As a result of the ALM, the four most important factors were determined as breed, lactation length, parity, and province. Therefore, these factors should be included to the model in predicting the 305-day milk yield. With this model, 64.2% of the variation in the 305-day milk yield could be explained (Mendes and Akkartal, 2009; Topal et al., 2010**TOPAL, M.; AKSAKAL, V.; BAYRAM, B. et al. An analysis of the factors affecting birth weight and actual milk yield in swedish red cattle using regression tree analysis. J. Anim. Plant Sci., v.20, p.63-69, 2010.).

Como citar

copiar

Universidade Federal de Minas Gerais, Escola de Veterinária Caixa Postal 567, 30123-970 Belo Horizonte MG - Brazil, Tel.: (55 31) 3409-2041, Tel.: (55 31) 3409-2042 - Belo Horizonte - MG - Brazil
E-mail: abmvz.artigo@gmail.com

Acompanhe os números deste periódico no seu leitor de RSS

Versão para download de PDF

PDF

Inglês

Versões e tradução automática

Versão original do texto

English

Tradução automática

Google Translator
Microsoft Translator

Como citar

RIS

BIBTEX

Outros formatos de citação e exportação:

SciELO - Scientific Electronic Library Online
Rua Dr. Diogo de Faria, 1087 – 9º andar – Vila Clementino 04037-003 São Paulo/SP - Brasil
E-mail: scielo@scielo.org

Leia a Declaração de Acesso Aberto

Métricas

[Análise de modelagem linear usado para determinar os fatores que afetam o rendimento leiteiro de 305 dias]

PlumX

Mensagem

[1] E-mail: serdargenc1983@gmail.com