Suppose that each setting xi of the independent variables in a simple least squares prob...

Suppose that each setting x_i of the independent variables in a simple least squares problem is duplicated, yielding two independent observations Y_i1 , Y_i2. Is it true that the least squares estimates of the intercept and slope can be found by doing a regression of the mean responses of each pair of duplicates, on the x_i? Why or why not?