scholarly journals MODELOS DE REGRESSÃO ALEATÓRIA ATRAVÉS DO PESO CORPORAL EM CURVAS DE CRESCIMENTO DE AVES

2017 ◽  
Vol 13 (Especial 2) ◽  
pp. 339-347
Author(s):  
Milena Vieira Lima ◽  
jeferson Corrêa Ribeiro ◽  
Lorrayne Gomes ◽  
Andreia Santos Cezário ◽  
Eliandra Maria Bianchini Oliveira ◽  
...  
Keyword(s):  
Regression Models ◽  
Random Effect ◽  
Interval Estimation ◽  
Regression Coefficients ◽  
Random Regression ◽  
Covariance Component ◽  
Independent Variable ◽  
Fixed Curve ◽  
Genetic Value ◽  
Genetic Evaluations

In modern genetic evaluations, random regression models have been used as a custom tool in order to analyze longitudinal traits such as the ones involved in animal growth. Such traits as body weight have an easy mensuration and an excellent response to selection, which is a suitable and important feature for animal breeding programs. The purpose of this review is to discuss about different random regression models that are involved in farm bird growth. The random regression models are recommended as an alternative to genetic evaluation of traits that are regularly measured during the animal life. These models allow the prediction of regression coefficients that represent the behavior of the additive genetic value for each animal in the specific evaluated trait in relation to time (age). Thus, interminable values for the independent variable are considered 340 Colloquium Agrariae, vol. 13, n. Especial, Jan–Jun, 2017, p. 321-347 ISSN: 1809-8215. DOI: 10.5747/ca.2017.v13.nesp.000238 within a defined interval, through deviations of each animal in relation to an estimated and fixed curve. The covariance component estimates assigned to random regression coefficients allow the covariance estimation between any values of the independent variable for a modeled random effect, which is accomplished by the covariance function. Therefore, random regression models improve the use of the weight information, when covariance structures between the studied ages are taken into account during the evaluation. They also allow the description of the estimated variance components that are involved in growth, besides granting presumptions for others in the curve inside the interval estimation.

scholarly journals Reliability of breeding values between random regression and 305-day lactation models

2016 ◽  
Vol 51 (11) ◽  
pp. 1848-1856
Author(s):  
Alessandro Haiduck Padilha ◽  
◽  
Jaime Araujo Cobuci ◽  
Darlene dos Santos Daltro ◽  
José Braccini Neto
Keyword(s):  
Legendre Polynomials ◽  
Regression Models ◽  
Protein Yield ◽  
Random Regression ◽  
Holstein Cattle ◽  
Average Increase ◽  
Data Set ◽  
Breeding Values ◽  
Estimated Breeding Values ◽  
Genetic Evaluations

Abstract The objective of this work was to verify the gain in reliability of estimated breeding values (EBVs), when random regression models are applied instead of conventional 305-day lactation models, using fat and protein yield records of Brazilian Holstein cattle for future genetic evaluations. Data set contained 262,426 test-day fat and protein yield records, and 30,228 fat and protein lactation records at 305 days from first lactation. Single trait random regression models using Legendre polynomials and single trait lactation models were applied. Heritability for 305-day yield from lactation models was 0.24 (fat) and 0.17 (protein), and from random regression models was 0.20 (fat) and 0.21 (protein). Spearman correlations of EBVs, between lactation models and random regression models, for 305-day yield, ranged from 0.86 to 0.97 and 0.86 to 0.98 (bulls), and from 0.80 to 0.89 and 0.81 to 0.86 (cows), for fat and protein, respectively. Average increase in reliability of EBVs for 305-day yield of bulls ranged from 2 to 16% (fat) and from 4 to 26% (protein), and average reliability of cows ranged from 24 to 38% (fat and protein), which is higher than in the lactation models. Random regression models using Legendre polynomials will improve genetic evaluations of Brazilian Holstein cattle due to the reliability increase of EBVs, in comparison with 305-day lactation models.

PSXV-1 Genetic evaluation of longevity of cows culled due to fertility-related problems using random regression models and censored data

2021 ◽  
Vol 99 (Supplement_3) ◽  
pp. 261-261
Author(s):  
Hinayah R Oliveira ◽  
Stephen P Miller ◽  
Luiz F Brito ◽  
Flavio S Schenkel
Keyword(s):  
Censored Data ◽  
Regression Models ◽  
Genetic Evaluation ◽  
Random Regression ◽  
Breeding Values ◽  
Structural Problems ◽  
Time Period ◽  
And Performance ◽  
Genetic Evaluations ◽  
The Impact

Abstract A recent study showed that longevity based on different culling reasons should be considered as different traits in genetic evaluations. However, it is still necessary to create a pipeline that avoid including/excluding animals culled for different reasons in every genetic evaluation run. This study aimed to: 1) perform a genetic evaluation of the longevity of cows culled due to fertility-related problems including records of animals culled for other reasons (i.e., age, structural problems, disease, and performance) as censored records; and, 2) identify the impact of censored data in the genetic parameters and breeding values estimated. Two longevity indicators were evaluated: traditional (TL; time from first calving to culling) and functional (FL; time period in which the cow was alive and also calving after its first calving) longevity. Both TL and FL were evaluated from 2 to 15 years-old, and codified as binary traits for each age (0 = culled and 1 = alive/calved). Both trait definitions were analyzed using a Bayesian random regression linear model. Animals culled for reasons other than fertility were either excluded from the data (standard) or had their records censored after the culling date reported in the dataset (censored). After the quality control, 154,419 and 450,124 animals had uncensored and censored records, respectively. Heritabilities estimated for TL over the ages ranged from 0.02 to 0.13 for standard, and from 0.01 to 0.12 for censored datasets. Heritabilities estimated for FL ranged from 0.01 to 0.14 (standard), and from 0.01 to 0.13 (censored). Average (SD) correlation of breeding values predicted over all ages, using the standard and censored datasets, was 0.77 (0.16) for TL, and 0.83 (0.11) for FL. Our findings suggest that including censored data in the analyses might impact the genomic evaluations and further work is need to determine the optimal predictive approach.

scholarly journals Konstruktion von Indizes mit Restriktionen in Random Regression Modellen zur Veränderung der Wachstumskurve

2007 ◽  
Vol 50 (6) ◽  
pp. 619-627
Author(s):  
N. Mielenz ◽  
L. Schüler
Keyword(s):  
Body Weight ◽  
Growth Curve ◽  
Regression Models ◽  
Test Period ◽  
Regression Coefficients ◽  
Random Regression ◽  
Breeding Value ◽  
Time Interval ◽  
Final Body Weight ◽  
Index Construction

Abstract. Title of the paper: Index construction with restrictions in random regression models to change the pattern of the growth curve Random regression models provide estimated breeding values (EBV) for the complete growth curve for any target age. The animal-specific curves can be described as the weighted sum of continuous covariates with random regression coefficients. By using the covariance matrix K of the additive genetic regression coefficients the response to index selection can be calculated for any age or time of the test period. In this study selection indexes with equality restrictions based on the eigenvectors of matrix K were used to modify the growth curve of the population. In order to demonstrate the index construction a matrix K was used, estimated from repeated measurements for body weight of bulls by using Legendre polynomials as covariates. Indexes for high and low growth rate until age at the reflection point were derived subject to the restriction of zero gain for initial and final body weight. Selection strategies for improving body weight at the end of the test period while holding the daily gain in a certain time interval on a desired level were compared. By using so-called "restrictive economic values", an aggregate breeding value for body weight was derived from EBV for individual growth curve.

scholarly journals APPLICATION OF RANDOM REGRESSION MODELS FOR GROWTH TRAITS OF NELLORE CATTLE IN BRAZIL

2016 ◽  
Vol 8 (2) ◽  
pp. 45-54
Author(s):  
Wéverton José Lima Fonseca ◽  
Amauri Felipe Evangelista ◽  
Laylson Da Silva Borges ◽  
Gleissa Mayone Silva Vogado ◽  
Carlos Syllas Monteiro Luz ◽  
...  
Keyword(s):  
Longitudinal Data ◽  
Beef Cattle ◽  
Regression Models ◽  
Growth Traits ◽  
Standard Procedure ◽  
Random Regression ◽  
Nellore Cattle ◽  
Cattle Breeders ◽  
Estimate Variance ◽  
Genetic Evaluations

The purpose of this review is to show the increase in number of researches on covariance components and genetic evaluation using random regression models (RRM) for growth traits of Nellore cattle. Random regression models, also known as infinite-dimension models have been used to estimate variance components and genetic parameters for weight of beef cattle. In addition, those models are a standard alternative for genetic analyses of longitudinal data, however, the availibility of computational resources for performing genetic evaluations widely is an obstacle. Traits related to animal growth are adopted as selection criteria in beef cattle breeding programs, because the remuneration of cattle breeders is made based on the weight of carcasses. In recent years, RRM have been adopted as standard procedure in relation to the analysis of longitudinal data in animal breeding.

Efficiency of part lactation test day records for genetic evaluations using fixed and random regression models

2002 ◽  
Vol 74 (2) ◽  
pp. 189-197 ◽  
Author(s):  
R. A. Mrode ◽  
G. J. T. Swanson ◽  
C. M. Lindberg
Keyword(s):  
Regression Model ◽  
Milk Yield ◽  
Regression Models ◽  
Rank Correlation ◽  
Random Regression ◽  
Moderate Correlation ◽  
Data Set ◽  
Random Regression Model ◽  
Holstein Friesian ◽  
Genetic Evaluations

AbstractThe efficiency of part lactation test day (TD) records in first parity for the genetic evaluation of bulls and cows using a random regression model (RRM) and a fixed regression model (FRM) was studied, modelling the random and fixed lactation curves by Legendre polynomials. The data set consisted of 9 242 783 TD records for first lactation milk yield of 1 134 042 Holstein Friesian heifers. The efficiency of both models with part lactation TD records was examined by comparing predicted transmitting abilities (PTAs) for 305-day milk yield for 114 bulls and their 4697 daughters, from analyses where the maximum number of TD records of these daughters was restricted to the initial 2, 4 or 6 TDs with those estimated from 10 TDs. The correlations of PTAs estimated from 2, 4 or 6 TDs with those from 10 TDs computed for cows and bulls within each model were very similar. A rank correlation of 0·91 (0·92 FRM) was obtained for cows between PTAs based on 2 TDs and those from 10 TDs. The correlation increased to 0·96 with 4 TDs and 0·98 with 6 TDs. For bulls, correlations between PTAs estimated from 4 or 6 TDs with those estimated from 10 TDs were high at 0·98 and 0·99 respectively. With 2 TDs, the correlation was 0·95. The average under-prediction of PTAs with 2, 4 or 6 TDs relative to 10 TDs was generally higher and more variable with a FRM compared with a RRM for highly persistent cows and bulls. A similar trend was observed for mean over-prediction of PTAs, except for the initial predictions based on 2 TDs when the RRM gave a higher mean over-prediction for bulls and their daughters with low persistency but high initial TD records. The range of over and under-predictions were large (up to 200 kg milk) for some bulls when only 2 TDs were included in both models. A moderate correlation of 0·64 was obtained between persistency evaluations estimated from 10 TDs with those estimated from 2 TDs. The correlation increased to 0·71 with 4 TDs included and 0·85 with 6 TDs. The moderately high correlation between 6 TDs and 10 TDs of 0·85 was unexpected given the high correlation of 0·99 between PTAs for yield estimated from 6TDs with those estimated from 10 TDs.

scholarly journals Persistence in milk, fat and protein production of primiparous Holstein cows by random regression models

2010 ◽  
Vol 39 (12) ◽  
pp. 2617-2624 ◽  
Author(s):  
Igor de Oliveira Biassus ◽  
Jaime Araújo Cobuci ◽  
Claudio Napolis Costa ◽  
Paulo Roberto Nogara Rorato ◽  
José Braccini Neto ◽  
...  
Keyword(s):  
Milk Fat ◽  
Legendre Polynomials ◽  
Regression Models ◽  
Minas Gerais ◽  
Random Regression ◽  
Holstein Cows ◽  
Minas Gerais State ◽  
Genetic Evaluations ◽  
Additive Genetic Effects

Total numbers of 56,508, 35,091 and 8,326 records of milk, fat, and protein test-day yields, respectively, were used to estimate genetic parameters for six persistency measures on milk, fat and protein productions of Holstein cows reared in Minas Gerais state. Covariance components for additive genetic effects and permanent environmental effects were estimated by REML in random regression models using Legendre polynomials from the third to the sixth order. Overall, models with the highest orders of Legendre polynomials showed the best quality of adjustments of these productive records. Heritability estimates obtained by the models for persistence in milk, fat, and protein yields ranged from 0.04 to 0.32, from 0.00 to 0.23, and from 0.00 to 0.27, respectively. Values of genetic correlation estimates between persistence and total 305-day milk, fat, and protein yields ranged from -0.38 to 0.54, from -0.39 to 0.97, and from -0.78 to 0.67, respectively. Persistence measurement proposed by Jakobsen (PS2) is preferential for using in further genetic evaluations for persistence in milk, fat and protein yields of Holstein cows in Minas Gerais state.

scholarly journals Comparison of Breeding Values for Daily Gains of Bulls Estimated with Multi-Trait and Random Regression Models

2007 ◽  
Vol 50 (2) ◽  
pp. 147-154
Author(s):  
H. Krejčová ◽  
N. Mielenz ◽  
J. Přibyl ◽  
L. Schüler
Keyword(s):  
Legendre Polynomials ◽  
Regression Models ◽  
Reference Model ◽  
Average Daily Gain ◽  
Regression Coefficients ◽  
Random Regression ◽  
Breeding Values ◽  
Higher Rank ◽  
Estimated Breeding Values ◽  
Daily Gain

Abstract. In this study, random regression models with Legendre polynomials of the 2nd, 3rd and 4th degree (RR2, RR3 and RR4) are compared with regard to the estimation of breeding values for the average daily gain of Czech Pied bulls (Simmental type). The data were prepared such that a multi-trait model (MTM) could be used as reference model. For each bull, 8 repeated records or fewer were available for the testing period from the 12th to the 420th day of life. For the modeling of the expected value structure, the fixed regression coefficients of the Legendre polynomials were subordinated hierarchically to the herd-year-season effects (HYS). For the comparison of the random regression models with the reference model, rank correlations between the estimated breeding values of various animal groups were calculated and a variety of top-lists were analyzed. In general, models RR3 and RR4 returned higher rank correlations with MTM in comparison to model RR2. Additionally, the number of common animals in the 1% and 10% top-lists showed that models RR3 and RR4 are to be preferred over RR2 when it comes to the estimation of breeding values.

scholarly journals Genetic parameters for milk production by using random regression models with different alternatives of fixed regression modeling

2011 ◽  
Vol 40 (3) ◽  
pp. 557-567 ◽  
Author(s):  
Jaime Araújo Cobuci ◽  
Claudio Napolis Costa ◽  
José Braccini Neto ◽  
Ary Ferreira de Freitas
Keyword(s):  
Multiple Regression ◽  
Milk Yield ◽  
Regression Models ◽  
Genetic Parameters ◽  
Genetic Correlations ◽  
Information Criterion ◽  
Multiple Regression Model ◽  
Random Regression ◽  
Fixed Curve ◽  
Best Fit

Records of test-day milk yields of the first three lactations of 25,500 Holstein cows were used to estimate genetic parameters for milk yield by using two alternatives of definition of fixed regression of the random regression models (RRM). Legendre polynomials of fourth and fifth orders were used to model regression of fixed curve (defined based on averages of the populations or multiple sub-populations formed by grouping animals which calved at the same age and in the same season of the year) or random lactation curves (additive genetic and permanent enviroment). Akaike information criterion (AIC) and Bayesian information criterion (BIC) indicated that the models which used multiple regression of fixed lactation curves of lactation multiple regression model with fixed lactation curves had the best fit for the first lactation test-day milk yields and the models which used a single regression of fixed curve had the best fit for the second and third lactations. Heritability for milk yield during lactation estimates did not vary among models but ranged from 0.22 to 0.34, from 0.11 to 0.21, and from 0.10 to 0.20, respectively, in the first three lactations. Similarly to heridability estimates of genetic correlations did not vary among models. The use of single or multiple fixed regressions for fixed lactation curves by RRM does not influence the estimates of genetic parameters for test-day milk yield across lactations.

scholarly journals Random Regression Models Are Suitable to Substitute the Traditional 305-Day Lactation Model in Genetic Evaluations of Holstein Cattle in Brazil

2015 ◽  
Vol 29 (6) ◽  
pp. 759-767 ◽  
Author(s):  
Alessandro Haiduck Padilha ◽  
Jaime Araujo Cobuci ◽  
Cláudio Napolis Costa ◽  
José Braccini Neto
Keyword(s):  
Regression Models ◽  
Random Regression ◽  
Holstein Cattle ◽  
Genetic Evaluations

scholarly journals Regression Models in Complex Survey Sampling for Sensitive Quantitative Variables

Mathematics ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 609
Author(s):  
María del Mar Rueda ◽  
Beatriz Cobo ◽  
Antonio Arcos
Keyword(s):  
Regression Analysis ◽  
Regression Models ◽  
Regression Coefficients ◽  
Randomized Response ◽  
Statistical Tool ◽  
Complex Survey ◽  
Complex Sample ◽  
Qualitative Variables ◽  
World Survey ◽  
Sensitive Variable

Randomized response (RR) techniques are widely used in research involving sensitive variables, such as drugs, violence or crime, especially when a population mean or prevalence must be estimated. However, they are not generally applied to examine relationships between a sensitive variable and other characteristics. This type of technique was initially applied to qualitative variables, and studies later showed that a logistic regression may be performed with RR data. Since many of the variables considered in this context are quantitative, RR techniques were extended to these cases to estimate the values required. Regression analysis is a valuable statistical tool for exploring relationships among variables and for establishing associations between responses and covariates. In this article, we propose a design-based regression analysis for complex sample designs based on the unified RR approach. We present estimators of the regression coefficients, study their theoretical properties and consider different ways to estimate their variance. The properties of these estimation techniques were simulated using various quantitative randomized models. The method proposed was also used to analyse the findings from a real-world survey.

Sign in / Sign up

Export Citation Format

Share Document