| Abstract: | The influence of somatotype on the validity of anthropometric prediction of body density (Db) in young women (N = 92) was investigated. Three groups of predominantly endomorph (N = 27), mesomorph (N = 35), and ectomorph (N = 30) women were identified by the Heath-Carter and Sheldon somatotyping methods. Discriminant analysis revealed a 100% accuracy in somatotype group determination. Thirteen diameters, 26 girths, and 8 skinfolds were measured and used in a STEPWISE regression analysis to derive somatotype-specific regression equations to predict body density. Combining all the measures provided very good prediction accuracy in all three groups with multiple correlation coefficients (R) of 0.98, 0.90, and 0.90, and the standard error of estimate (SEE) of 0.003, 0.005, and 0.005 for Db (gm X cc-1) in the endomorphs, mesomorphs, and ectomorphs, respectively. A cross-validation study confirmed the accuracy of the somatotype-specific regression equations and demonstrated an inherent weakness in using some generalized equations on specific somatotypes. The use of non-somatotype-specific equations resulted in mean Db prediction errors ranging from -0.018 to +0.023 gm X cc-1 (8.5 to -10.7% Fat). Although all equations tested demonstrated specific weaknesses in one or more of the somatotype groups when predicting Db, the Jackson et al. (1980) equation performed better than most of the non-somatotype-specific prediction equations. These findings suggest that the anthropometric estimation of Db may not be sample specific in the same manner as had been previously thought and that greater accuracy may be achieved by using regression equations which have been generated on a previously somatotyped population sample. |
