bodyfat {mboost} | R Documentation |
For 71 healthy female subjects, body fat measurements and several anthropometric measurements are available for predictive modelling of body fat.
data("bodyfat")
A data frame with 71 observations on the following 10 variables.
age
DEXfat
waistcirc
hipcirc
elbowbreadth
kneebreadth
anthro3a
anthro3b
anthro3c
anthro4
Garcia et al. (2005) report on the development of predictive regression equations for body fat content by means of common anthropometric measurements which were obtained for 71 healthy German women. In addition, the women's body composition was measured by Dual Energy X-Ray Absorptiometry (DXA). This reference method is very accurate in measuring body fat but finds little applicability in practical environments, mainly because of high costs and the methodological efforts needed. Therefore, a simple regression equation for predicting DXA measurements of body fat is of special interest for the practitioner. Backward-elimination was applied to select important variables from the available anthropometrical measurements, and Garcia (2005) report a final linear model utilizing hip circumference, knee breadth and a compound covariate which is defined as the sum of log chin skinfold, log triceps skinfold and log subscapular skinfold.
Ada L. Garcia, Karen Wagner, Torsten Hothorn, Corinna Koebnick, Hans-Joachim F. Zunft and Ulrike Trippo (2005), Improved prediction of body fat by measuring skinfold thickness, circumferences, and bone breadths. Obesity Research, 13(3), 626–634.
Peter Buhlmann and Torsten Hothorn (2007), Boosting algorithms: regularization, prediction and model fitting. Statistical Science, 22(4), 477–505.
data("bodyfat", package = "mboost") ### final model proposed by Garcia et al. (2005) fmod <- lm(DEXfat ~ hipcirc + anthro3a + kneebreadth, data = bodyfat) coef(fmod) ### plot additive model for same variables amod <- gamboost(DEXfat ~ hipcirc + anthro3a + kneebreadth, data = bodyfat, baselearner = "bbs") layout(matrix(1:3, ncol = 3)) plot(amod[mstop(AIC(amod, "corrected"))], ask = FALSE)