Modelo sdm 241 as shown i n 242 k i m phi pps and

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: endência espacial com y = α ιmodel con+aX β spatial dep endence in bot h t he dep enden7) var iable and +u (2 3t T his n + ρW1 yédia móvel para os resíduos (SARMA) ao invés.do modelo de leg m t ins t = dist u b ε u he θW2ur+ ances. W1 y + X β2 + espacial: u (2.37) ε ∼ N (0, σ I n ) ε y = ( I n −yρW1 )ι−n1 + ρW1 y ι+ )X β( I+ u ρW1 ) − 1 ( I n − θW2 ) − 1 ε (2.38) = α (X β + α n + n − In) 1) −1 (2.37) u = θW2 u + ε ( X ε ∼ N (0,)σ2 I( I )n − ρW1 ) − 1 ( I n − θW2 ) − 1 ε (2.38) β + αι n + n y = ( I n − ρW1 ) − 1 ( X β + α ι n ) + ( I n − ρW1 ) − 1 ( I n − θW2 ) − 1 ε (2.38) ylor & Francis Group, LLC LLC INTERPRETAÇÃO DOS PARÂMETROS © 2009 by Taylor & Francis Group, LLC 1. Impactos Diretos e Indiretos • • A interpretação dos parâmetros estimados nos modelos espaciais devem levar em consideração não apenas o efeito direto dos mesmos, mas também a contribuição dos vizinhos. Modelo SDM ( 2.41) as shown i n ( 2.42) ( K i m, Phi pps, and A nsel i n, 2003, Mot i vat i ng and I nt er pr et ing Spat i al Economet r i c M odels 35 Sr ( W ) 11 Sr ( W ) 12 . . . Sr ( W ) 1n x 1r k Spr ocM21 vat i(.W and shown i n ( g Spa al Economet r a M A ns ) ot Sr 41 as xP at i ng r ( Wess iin ( 2ng )) 22 I nt er pr et in2.42) t(iK i m,2r hi pps,i c ndodelsel i n, 200335 , (2.42) . c.f. equat.ion(4)). . .. . . . . . . . r = 1 at i ng pr ocess i n ( 2.41) as shown i n ( 2.42) ( K i m, Phi pps, and A nsel i n, 2003, Sr ( W io 1 Sr ( xn r c.f. equat) n n(4)). W ) n 2 . . . Sr ( W ) n n y1 Sr ( W ) 11 Sr ( W ) 12 . . . Sr ( W ) 1n x 1r k Sr ( W ) 21 Sr ( W ) 22 x 2r V ( W ) ι n α + y.2 ( W ) ε V= .x 1r . Sr . W ) 11 Sr . W ) 12 .. . . Sr ( W ) 1n ( ( . y1 . . . . . . . . r=1 k y2 Sr ( W ) 21 Sr ( W ) 22 x Sr W . i 1 S n ) n 4. Sr ( ke n t ) x r 2r n. gl e dependent yvar i abl e obser(vat non ri ( W(.2.2 3.).. maW )s n he r olne. = . . . .. . 1 W ) mor e t r ansp.ar ent .r =We use. Sr ( W ) i . in t his equat ion t o. j α ( V n1...
View Full Document

This note was uploaded on 05/01/2013 for the course ECONOMIA 001 taught by Professor Farinha during the Fall '10 term at Universidade de Lisboa.

Ask a homework question - tutors are online