Path Coefficients and Path Regressions: Alternative or Complementary Concepts?

摘要: (1) The authors concur with Tukey in treating the standardized and concrete forms of correlational statistics as if they were alternative conceptions between which it is necessary to make a choice. It has always seemed me that these should be looked upon two aspects single theory corresponding different modes interpretation which, taken together, often give deeper understanding situation than either can by itself. (2) E1ven when sole objectives analysis are coefficients, actual path takes simpler more homogeneous form terms ones. application method data usually requires algebraic manipulation coefficients pertaining unmeasured variables on same basis measured As former only dealt form, homogeneity all so course algebra. such simple matter pass from other (in cases standard deviations available all) economy effort using far possible, where objectives, outweighed loss respects. (3) first importance use data. This not done Turner Stevens most their examples. leads naturally