Out-of-sample R^2

[mj1313]

Hello everybody!

Standard predictive regression model for the equity premium is
rt+1 = a +bxi,t +et+1, (1)
where rt+1 is the return on a stock market index in excess of the risk-free interest rate, xi,t is a variable whose predictive ability is of interest, and et+1 is a disturbance term. I generate out-of-sample forecasts of the equity premium using a recursive (expanding) estimation window. More specifically, we first divide the total sample of T observations for rt and xi,t into an in-sample portion composed of the first R observations and an out-of-sample portion composed of the last P observations. The initial out-of-sample forecast of the equity premium based on the predictor xi,t is given by rˆi,R+1 = aˆR+bˆRxi,R, where aˆR and bˆR are the OLS estimates of a and b, respectively, in (1) generated by regressing {rt} on a constant and {xi . The
next out-of-sample forecast is given by rˆi,R+2 = aˆR+1+bˆR+1xi,R+1, where aˆR+1 and bˆR+1 are generated by regressing {rt}R+1 t=2 on a constant and {xi,t}Rt=1. Proceeding in this manner through the end of the out-of-sample period, we generate a series of P out-of-sample forecasts of the equity premium based on xi,t ({ˆri,t+1}T−1 t=R ). This out-of-sample forecast exercise mimics the situation of a forecaster in real time.

I´m trying to replicate this forecast exercise in "Out-of-Sample Equity Premium Prediction: Consistently Beating the Historical Average"

Do you know if E-Views is able to give the out-of-sample R2 statistic and the MSPE? If yes, how?