Smoothed shocks figure

Dear Johannes,

Could you please help to have a look at the attached smoothed shock figure? Do e_z (std of preference shock ) and h_Me (Measurement error to labor hours) look wired ?

SmoothedShocks1.pdf (16.2 KB)

The measurement error shows too much autocorrelation for my taste, suggesting that it captures model misspecification. But there is probably not much you can do about it.