INTERNATİONAL JOURNAL OF AGRİCULTURE & BİOLOGY ISSN Print: 1560–8530; ISSN Online: 1814–9596 12–059/ZIP/2012/14–4–590–594 http://www.fspublishers.org Full Length Article To cite this paper: Tariq, M.M., E. Eyduran, M.A. Bajwa, A. Waheed, F. Iqbal and Y. Javed, 2012. Prediction of body weight from testicular and morphological characteristics in indigenous Mengali sheep of Pakistan: using factor analysis scores in multiple linear regression analysis. Int. J. Agric. Biol., 14: 590–594 Prediction of Body Weight from Testicular and Morphological Characteristics in Indigenous Mengali Sheep of Pakistan using Factor Analysis Scores in Multiple Linear Regression Analysis MOHAMMAD MASOOD TARIQ, ECEVIT EYDURAN 1 †, MASROOR AHMAD BAJWA, ABDUL WAHEED‡, FARHAT IQBAL¶ AND YASIR JAVED Center for Advanced Studies in Vaccinology and Biotechnology (CASVAB), University of Balochistan, Quetta, Balochistan, Pakistan †Biometry Genetics Unit, Department of Animal Science, Faculty of Agriculture, Iğdır University, 76000, Iğdır, Turkiye †Faculty of Veterinary Science, Bahauddin Zakariya University, Multan, Pakistan ¶Department of Statistics, University of Balochistan, Quetta, Pakistan 1 Corresponding author’s e-mail: ecevit.eyduran@gmail.com ABSTRACT The objective of the investigation was to predict body weight (BW) from testicular and morphological characteristics of the indigenous Mengali Sheep in Balochistan, Pakistan. The characteristics recorded were: body weight (BW), testicular length (TL), scrotal length (SL), scrotal circumference (SC), body length (BL), withers height (WH) and heart girth (HG) of 107 indigenous Mengali sheep in age range of 12 to 48 months. Only multiple linear regression analysis fitting to the available data showed tendency to multicollinearity problem with VIF >10 and didn’t present optimal solutions. With the purpose of removing the multicollinearity problem and especially making more correct interpretation biologically, the data were exposed to a combination of Factor and Multiple Linear Regression analyses. The appropriateness of factor analysis for the current data was determined by using criteria such as Kaiser-Meyer Olkin (KMO) measure of sampling adequacy and Bartlett’s test of spherity. These criteria showed that the data were appropriate for the factor analysis, one of the multivariate statistical analysis techniques. Thereafter, the factor analysis was applied to explanatory variables in order to derive new-uncorrelated latent explanatory variables from the variables. In the factor analysis, three new latent variables whose eigenvalues were greater than one were considered as explanatory variable for multiple linear regression analysis. Results obviously illustrated that 79.1% of variation in body weight was effectively explained by these new latent explanatory variables. Consequently, if confirmed at genetic level, the testicular and body traits might provide a significant contribution in the genetic improvement of the body weight of the indigenous Mengali for sheep breeding. © 2012 Friends Science Publishers Key Words: Factor analysis; Multiple linear regression analysis; Indigenous mengali sheep; Multicollinearity; Varimax rotation INTRODUCTION An assessment of indigenous sheep breeds is significant in terms of germplasm conservation of a country. In the indigenous sheep breeding, the identification of multivariate relationships among age, body weight, testicular characteristics and body measurements is necessary for selecting better animals with the aim of gaining more genetic progress on reproductive yield. Among, testicular characteristics, scrotal circumference and length, and testicular length and diameter, which are influenced by age, body weight and seasonal changes were considered to be indirect selection criteria for more genetic progress in fertility (Karakus et al., 2010; Khan et al., 2010). There is a clear evidence that highly significant relationships between pairs of these more heritable testicular traits were reported in some studies (Bilgin et al., 2004) and especially in a previous report, the existence of strong relationships between sperm quality and testicular traits was particularly pointed out in the literature (Blockey, 1980). Karakus et al. (2010) determined that, the best non-linear functions describing relationship between each testicular trait-time in Norduz lambs at young age were Logistic (with 3 parameters) and Richards’s models. Confirming these studies, Salhab et al. (2001) and Karakus et al. (2010) also underlined the significant effects of age and body weight on testicular traits with the multiple linear regression analysis, which is used to identify the relationship of body weight with some body measurements, prone to multicollinearity problem. One of the most effective methods to remove the problem is to use factor analysis scores for multiple regression analysis in different species as reported by many