|
into account. Furthermore, one can use the treatment group as well as the control group to
<br />estimate the neighborhood tenure parameters and the variable moving cost parameters. All
<br />of these additional equations are detailed in the appendix. The model is then estimated via
<br />GMM.
<br />Finally, it remains to estimate the permanent component of amenities wj.l° We do so
<br />after estimating the full GMM system detailed above. We once again consider two mature
<br />households of equal tenure T,,,, living in neighborhoods j and j' respectively and suppose
<br />that both households move to some neighborhood j* after one year. We thus have, At -1 =
<br />(j, Tom, 0, M) , Ot_r = (j', T,,,, 0, M) , and x = x' = S. These choices yield the equation:
<br />Ytj',j* _ �j — ��' + wjt — wj,t + �t �� , 01
<br />—r) — C (x, Bt—r) + Xj,j',j*
<br />Y = In
<br />Pt (SIj'O,T.In ) Pt (j* J,0,T.) Pt+1 (j*Ij,0, T.)
<br />,, ..
<br />RJ ,9
<br />(Pt (Slj',O,Ta)� (Pt U*Y'0!T.) Pt+1(j*Y,0,7.,)
<br />- (B - 1) toj,M (dj,j* - dj, j,) - ym [Rt (j, 0) - Rt (j', 0)]
<br />Identification comes from the fact that, averaging over time, we average out the per -period
<br />neighborhood amenity shocks and expectational error shocks. Moreover, note that we do
<br />not have an endogeneity problem since we have already estimated -ym and can therefore
<br />move the utility impact of the rent difference to the left hand side of the equation. We
<br />also account for the differential moving costs related to distance on the left hand side of the
<br />equation. Finally, note that we can only identify fixed amenity value differences between
<br />neighborhoods. We therefore choose a normalization, letting zipcode 94110, representing the
<br />Mission District and Bernal Heights, be our baseline zipcode. We set its amenity value fixed
<br />effect to zero.
<br />"We cannot identify amenities of the outside options, i.e. the rest of the Bay Area and the rest of the
<br />country, as no one in our 1994 cohorts started off living in those locations.
<br />32
<br />
|