Causes of autocorrelation 1. Omitting relevant regressors Suppose the true model is Y =Bo+BXI+B2x2t+a But the model is mis-specified as Y=Bo+BXI+v That is v,=B2X2+8 If Xo is correlated with Xi1, v, is also correlated with VA-1. This is particularly serious if X2t represents a lagged dependent variable Slide 21Slide 21 Causes of Autocorrelation 1. Omitting relevant regressors Suppose the true model is But the model is mis-specified as That is, If X2t is correlated with X2,t-1 , νt is also correlated with νt-1 . This is particularly serious if X2t represents a lagged dependent variable. Yt X t X t t =  +  +  + 0 1 1 2 2 Yt = 0 + 1 X1t + t  t = 2 X2t + t