Statistical issues of regression analysis on development of an age-predictive equation.

Several statistical information criteria and other statistical issues such as residual examinations and multi-collinearity in regression analysis were argued to establish the predictive equation of age from physical fitness measurements. These independent variables of physical fitness, body composition, two blood pressures, and bone strength were taken from 31 Japanese males (48 +/- 11.9 years old) living in rural areas. The following equation was selected as the optimal one according to Akaike's information criterion: ŷ = 90.0 -1.294 * SITUP - 0.467 * MAP - 0.094 * BALANCE (R = 0.837). When all ten variables were included in the initial equation, R was 0.864, and the highest R* (R adjusted for d.f.) was observed at the fifth step.