(c) Suppose yt = But + et where et has zero mean, constant variance and is not serially correlated. If we define yt = yt + yt-1, at = at + t-1 and et = Et + Et-1 show that least squares regression of y on at will give unbiased estimates of B. Also show that the error term has a constant variance but E(**_) # 0. What will be the properties of the least squares estimates