/* x = average index of central bank independence (1 = little independence 4 = very independent) y = average Inflation 1955 - 1988 Source: Alesina and Summers (1993) Jo. of Money, Credit, and Banking */ data in; input x y; cards; 1.5 8.5 1 7.6 2 6.4 1.75 7.3 2 6.7 2 6.1 2.5 6.5 2 4.1 2 6.1 2 6.1 2.5 4.5 2.5 4.2 2.5 4.9 3.5 4.1 4 3 4 3.2 ; proc means data=in; var x y; run; proc reg data = in; model y = x / r clm cli; run; /* Here we use the transformed model to obtain the point prediction when x = 1.50 (it is the estimate of the intercept in the transformed model) and the ingredients for the construction of the standard error of the prediction error. We use the Standard Error of the Transformed Regression (RMSE in SAS) or the Mean Square of the Error in the ANOVA table) to construct the standard error of the prediction error. se(prediction error) = sqrt(RMSE^2 + se(intercept)^2)= sqrt(mean square error + se(intercept)^2). */ data in; set in; xstar = x - 1.50; proc reg data=in; model y = xstar; run;