ECON 710 Final: ECON 710 UW Madison Final Exam 2001
Document Summary
May 17, 2001 yi = + ei. The null hypothesis is a linear regression yi = xi + ei. The parameter is estimated by ols yielding predicted values (cid:136)yi. Then using a second- stage ls regression yi = x0 i (cid:152) + ((cid:136)yi)2 (cid:152) + (cid:152)ei. The reset test statistic r is the squared t-ratio on (cid:152) . A colleague suggests obtaining the critical value for the test using the bootstrap. Sort the bootstrap statistics r , take number 950 (the. 95% percentile) and use this as the critical value. (d) reject the null hypothesis if r exceeds this critical value, otherwise do not reject. 1: (20 points) let yt be a strictly stationary and ergodic time series which follows the following nonlinear autoregressive model yt = y2 t 1 + et. Let zt = e ( t | it 1) be the expected in(cid:223)ation rate.
