(i) Obtain the fitted values loˆgyi from the regression of logy on x.(ii) For each observation i, create mˆi exp(loˆgyi1).(iii) Now regress y on the single variable mˆwithout an intercept; that is, perform a,…,xsimple regression through the origin. The coefficient on mˆ, the only coefficientthere is, is the estimate of .Onceˆ0 0is obtained, it can be used along with predictions of logy to predict y. Thesteps are as follows:(i) For given values of x1, x2,…,x(ii) Obtain the prediction yˆ from (6.42).k, obtain loˆgy from (6.39).k
đang được dịch, vui lòng đợi..
