No abstract

Classification and regression tree analysis is a powerful statistical technique which helps to determine the most important variables in a particular dataset and helps to create a model. The study was conducted to identify linear body measurement traits (beak length, body length, keel length, chest circumference, toe length, body girth, shank length, back length, shank circumference and wing length) which could be employed in developing an effective prediction equation for body weight of Potchefstroom Koekoek laying hens. Eighty Potchefstroom Koekoek laying hens at twenty two weeks old were used. Pearson's correlation together with classification and regression tree (CRT) methods were used for analysis. Descriptive statistics indicated that mean of body weight was 1.50 kg. Correlation findings revealed that body weight was positively significantly correlated (P < 0.05) with beak length (r = 0.23) and toe length (r = 0.21), respectively. CRT results demonstrated that beak length, wing length and back length play an important role in the body weight of Potchefstroom Koekoek laying hen chickens. This study suggests that body weight of laying hens could be estimated by some linear body measurement traits. The models established in the current study might be employed by chicken farmers when making selection during breeding to improve body weight. However, further studies need to be done to validate the use of classification and regression tree analysis in prediction of body weight from linear body measurement traits of chickens.

No abstract

| Multivariate Adaptive Regression Splines (MARS) data mining algorithm is a non-parametric regression method employed to obtain the prediction of live weight by using body measurements. The study was conducted to investigate the relationship between body weight, linear body measurement traits and the effect of linear body measurement traits on body weight of Hy-Line silver brown commercial layer. A total of one hundred (n= 100) Hy-Line silver brown commercial layers aged 22 weeks were used for body measurements viz; body weight (BW) in kilograms, Beak Length (BK), Body Length (BL), Body Girth (BG), Shank Length (SL) and Wing Length (WL) in centimetres. Furthermore, Pearson correlation and MARS methods were used for data analysis. Correlation results revealed that BW had a negative statistically high significant correlation with WL (r=-0.48**) and BL (r=-0.61**). MARS results developed a non-parametric regression model with coefficient of determination (R 2) = 1, adjusted coefficient of determination (R 2 adj.)= 1, standard deviation ration (SD ratio) = 0.006, root mean square error (RMSE) = 0.001 and Pearson correlation (r) = 1 between predicted and actual values (P < 0.01) of body weight. MARS model revealed that WL and BL had an effect on BW of Hy-Line silver brown commercial layer. The findings suggest that WL and BL had an effect on BW, therefore chicken layer farmers might use WL and BL for selection during breeding to improve BW. In conclusion, MARS models developed in this study might be used by chicken layer farmers for selection during breeding.

Egg is a reproduction tool for chickens and valuable food source for humans. The objective of this study was to examine the effect of egg weight (EW) on egg quality traits such as egg length (EL), egg diameter (ED), yolk weight (YW), albumen weight (AW), shell weight (SW), shell index (SI), yolk ratio (YR), albumen ratio (AR) and shell ratio (SR). Potchefstroom Koekoek layer genotype eggs (n = 200) were used. Pearson correlation and analysis of variance (ANOVA) were used for analysis. Correlation results indicated that egg weight had a statistical significant correlation (P < 0.05) with egg quality traits. Egg weight displayed a positive significant correlation with EL (0.82), AW (0.67) and SW (0.62), respectively. The findings suggest that EL, AW and SW might be used to improve EW of Potchefstroom Koekoek chicken genotype. ANOVA results showed that egg weight had a statistical significant difference (P < 0.05) with egg quality traits except albumen ratio and yolk ratio (P > 0.05). Moreover, the findings revealed that small eggs weight had a longer egg length, yolk weight, shell weight, shell ratio and albumen weight than medium and large eggs. Large eggs had a higher egg diameter and shell index. Keywords: Albumen weight, egg length, large egg, medium egg, small egg, shell weight