1、 MATLAB Excel ： 選項一一加載項一一coMra載項一一轉到一一沒有勾選項 E:MATLABtoolboxexlink 然后，Excel中就出現MATLA工具 注意 Excel 中的數據：） 3. 啟動 matlab 1）點擊 start MATLAB 2）senddata to matlab ，并對變量矩陣變量進行命名（注意：選取變量 為數值，不包括各變量） （data 表中數據進行命名 ） 空間權重進行命名） （3）導入MATLAB的兩個矩陣變量就可以看見 4.將elhorst和jplv7兩個程序文件夾復制到 MATLAB安裝目錄的 toolbox 文件夾 5. 設置路徑： 2

2、. MATLAB 安裝目錄中尋找 toolbox exlink 點擊 , 啟用宏 6. 輸入程序，得出結果 T=30; N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); xconstant=ones(N*T,1); nobs K=size(x); results=ols(y,xconstant x); vnames=strvcat( logcit , intercept , logp , logy ); prt_reg(results,vnames,1); sige=*(nobs-K)/nobs); loglikols=-nobs/2*log(2*pi*sige

3、)-1/(2*sige)* % The (robust)LM tests developed by Elhorst LMsarsem_panel(results,W,y,xconstant x); %(Robust) LMtests 解釋 每一行分別表示： 該面板數據的時期數為 30 （T=30）, 該面板數據有30個地區（N=30）, 將空間權重矩陣標準化（W=normw（w1）, 將名為A （以矩陣形式出現在 MATLABA中）的變量的第3列數據定義為被解釋變量 將名為A的變量的第4、5、6列數據定義為解釋變量矩陣 x， 定義一個有 N*T行，1列的全1矩陣，該矩陣名為：xconstant

4、 ，（ ones即為全1矩陣） 說明解釋變量矩陣 x的大小：有nobs行，K列。（size為描述矩陣的大小）。 附錄: 靜態面板空間計量經濟學 、OLS靜態面板編程 1、普通面板編程 T=30; N=46; W二no rmw(W1); y=A(:,3); x=A(:,4,6); xcon sta nt=on es(N*T,1); n obs K=size(x); results=ols(y,xc on sta nt x);y, vnames=strvcat( logcit , intercept , logp , logy ); prt_reg(results,vnames,1); sige=

5、*(nobs-K)/nobs); loglikols=-nobs/2*log(2*pi*sige)-1/(2*sige)* % The (robust)LM tests developed by Elhorst LMsarsem_panel(results,W,y,xconstant x); % (Robust) LM tests 2、空間固定 OLS (spatial-fixed effects T=30; N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); xconstant=ones(N*T,1); nobs K=size(x); model=1; ywit

6、h,xwith,meanny,meannx,meanty,meantx=demean(y,x,N,T,model); results=ols(ywith,xwith); vnames=strvcat(logcit,logp,logy); % should be changed if x is changed prt_reg(results,vnames); sfe=meanny-meannx*; % including the constant term yme = y - mean(y); et=ones(T,1); error=y-kron(et,sfe)-x*; rsqr1 = erro

7、r*error; rsqr2 = yme*yme; FE_rsqr2 = - rsqr1/rsqr2 % r-squared including fixed effects sige=*(nobs-K)/nobs); logliksfe=-nobs/2*log(2*pi*sige)-1/(2*sige)* LMsarsem_panel(results,W,ywith,xwith); % (Robust) LM tests 3、時期固定 OLS( time-period fixed effects T=30; N=46; W=normw(W1);y=A(:,3); x=A(:,4,6); xco

8、nstant=ones(N*T,1); nobs K=size(x); model=2; ywith,xwith,meanny,meannx,meanty,meantx=demean(y,x,N,T,model); results=ols(ywith,xwith); vnames=strvcat(logcit,logp,logy); % should be changed if x is changed prt_reg(results,vnames); tfe=meanty-meantx*; % including the constant term yme = y - mean(y); en

9、=ones(N,1); error=y-kron(tfe,en)-x*; rsqr1 = error*error; rsqr2 = yme*yme; FE_rsqr2 = - rsqr1/rsqr2 % r-squared including fixed effectssige=*(nobs-K)/nobs); logliktfe=-nobs/2*log(2*pi*sige)-1/(2*sige)* LMsarsem_panel(results,W,ywith,xwith); % (Robust) LM tests 4、空間與時間雙固定模型 T=30; N=46; W=normw(W1); y

10、=A(:,3); x=A(:,4,6); xconstant=ones(N*T,1); nobs K=size(x); model=3; ywith,xwith,meanny,meannx,meanty,meantx=demean(y,x,N,T,model); results=ols(ywith,xwith); vnames=strvcat(logcit,logp,logy); % should be changed if x is changed prt_reg(results,vnames)en=on es(N,1); et=on es(T,1); in terce pt二mea n(y

11、)-mea n( x)*; sfe=mea nn y-mea nn x*(e n,i nterce pt); tfe=mea nty-mea ntx*(et,i nterce pt); yme = y - mea n( y); en t=o nes(N*T,1); error二y-kro n( tfe,e n)-kro n(et,sfe)-x*(e nt,i nterce pt); rsqrl = error*error; rsqr2 = yme*yme; FE_rsqr2 = - rsqr1/rsqr2 % r-squared in cludi ng fixed effects sige=*

12、( nobs-K)/nobs); loglikstfe=-nobs/2*log(2* pi *sige)-1/(2*sige)* LMsarsem_pa nel(results,W,ywith,xwith); % (Robust) LM tests 二、靜態面板SAR模型 1、無固定效應(No fixed effects ) T=30; N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); for t=1:T t1=(t-1)*N+1;t2=t*N; wx(t1:t2,:)=W*x(t1:t2,:); end xconstant=ones(N*T,1); nobs

13、K=size(x); =0; =0; =0; results=sar_panel_FE(y,xconstant x,W,T,info); vnames=strvcat( logcit , intercept , logp , logy ); prt_spnew(results,vnames,1) % Print out effects estimates spat_model=0; direct_indirect_effects_estimates(results,W,spat_model); panel_effects_sar(results,vnames,W); 2、空間固定效應( Spa

14、tial fixed effects T=30; N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); for t=1:T t1=(t-1)*N+1;t2=t*N; wx(t1:t2,:)=W*x(t1:t2,:); end xconstant=ones(N*T,1); nobs K=size(x); =0; =1; =0; results=sar_panel_FE(y,x,W,T,info); vnames=strvcat( logcit , logp , logy ); prt_spnew(results,vnames,1) % Print out effect

15、s estimates spat_model=0; direct_indirect_effects_estimates(results,W,spat_model); panel_effects_sar(results,vnames,W); 3、時點固定效應( Time period fixed effects T=30; N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); for t=1:T t1=(t-1)*N+1;t2=t*N; wx(t1:t2,:)=W*x(t1:t2,:); end xconstant=ones(N*T,1); nobs K=size(x

16、); =0; % required for exact results =2; =0; % Do not print intercept and fixed effects; use =1 to turn on results=sar_panel_FE(y,x,W,T,info); vnames=strvcat( logcit , logp , logy ); prt_spnew(results,vnames,1) % Print out effects estimates spat_model=0; direct_indirect_effects_estimates(results,W,sp

17、at_model); panel_effects_sar(results,vnames,W); 4、雙固定效應( Spatial and time period fixed effects T=30; N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); for t=1:T t1=(t-1)*N+1;t2=t*N; wx(t1:t2,:)=W*x(t1:t2,:); end xconstant=ones(N*T,1); nobs K=size(x);=0; =0; % required for exact results =3; =0; % Do not print

18、 intercept and fixed effects; use =1 to turn on results=sar_panel_FE(y,x,W,T,info); vnames=strvcat( logcit , logp , logy ); prt_spnew(results,vnames,1) % Print out effects estimates spat_model=0; direct_indirect_effects_estimates(results,W,spat_model); panel_effects_sar(results,vnames,W); 三、靜態面板SDM模

19、型 1、無固定效應( No fixed effects ) T=30; N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); for t=1:T t1=(t-1)*N+1;t2=t*N; wx(t1:t2,:)=W*x(t1:t2,:); end xconstant=ones(N*T,1); nobs K=size(x);=1; =0; =0; results=sar_panel_FE(y,xconstant x wx,W,T,info); vnames=strvcat( logcit , intercept , logp , logy , W*logp , W*l

20、ogy ); prt_spnew(results,vnames,1) % Print out effects estimates spat_model=1; direct_indirect_effects_estimates(results,W,spat_model); panel_effects_sdm(results,vnames,W); 2、空間固定效應( Spatial fixed effects T=30; N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); for t=1:T t1=(t-1)*N+1;t2=t*N; wx(t1:t2,:)=W*x(t

21、1:t2,:); end xconstant=ones(N*T,1); nobs K=size(x); =0; % required for exact results =0; % Do not print intercept and fixed effects; use =1 to turn on results=sar_panel_FE(y,x wx,W,T,info);% Print out coefficient estimates vnames=strvcat( logcit , logp , logy , W*logp , W*logy ); prt_spnew(results,v

22、names,1) % Print out effects estimates spat_model=1; direct_indirect_effects_estimates(results,W,spat_model); panel_effects_sdm(results,vnames,W); 3、時點固定效應( Time period fixed effects T=30; N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); for t=1:T t1=(t-1)*N+1;t2=t*N; wx(t1:t2,:)=W*x(t1:t2,:); end xconstant

23、=ones(N*T,1); nobs K=size(x); =0; % required for exact results =2; =0; % Do not print intercept and fixed effects; use =1 to turn on % New routines to calculate effects estimates results=sar_panel_FE(y,x wx,W,T,info); vnames=strvcat( logcit , logp , logy , W*logp , W*logy ); prt_spnew(results,vnames

24、,1) % Print out effects estimates spat_model=1; direct_indirect_effects_estimates(results,W,spat_model); panel_effects_sdm(results,vnames,W) 4、雙固定效應( Spatial and time period fixed effects T=30; prt_spnew(results,vnames,1) % Print out effects estimates N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); for t=1

25、:T t1=(t-1)*N+1;t2=t*N; wx(t1:t2,:)=W*x(t1:t2,:); end xconstant=ones(N*T,1); nobs K=size(x); =0; =0; % required for exact results =3; =0; % Do not print intercept and fixed effects; use =1 to turn on results=sar_panel_FE(y,x wx,W,T,info); vnames=strvcat( logcit , logp , logy , W*logp , W*logy ); spa

26、t_model=1; direct_indirect_effects_estimates(results,W,spat_model); panel_effects_sdm(results,vnames,W) wald test spatial lag % Wald test for spatial Durbin model against spatial lag model btemp=; varcov=; Rafg=zeros(K,2*K+2); for k=1:K end Wald_spatial_lag=(Rafg*btemp)*inv(Rafg*varcov*Rafg)*Rafg*bt

27、emp prob_spatial_lag=1-chis_cdf (Wald_spatial_lag, K) wald test spatial error % Wald test spatial Durbin model against spatial error model R=zeros(K,1); for k=1:K R(k)=btemp(2*K+1)*btemp(k)+btemp(K+k); % R(1)=btemp(5)*btemp(1)+btemp(3); % R(2)=btemp(5)*btemp(2)+btemp(4); end Rafg=zeros(K,2*K+2); for

28、 k=1:K Rafg(k,K+k) =1; Rafg(k,K+k)=1; % R(1,3)=0 and R(2,4)=0; % k changed in 1, 7/12/2010 Rafg(k,k) =btemp(2*K+1); % k changed in 1, 7/12/2010 Rafg(k,2*K+1)=btemp(k); % Rafg(1,1)=btemp(5);Rafg(1,3)=1;Rafg(1,5)=btemp(1); % Rafg(2,2)=btemp(5);Rafg(2,4)=1;Rafg(2,5)=btemp(2); end Wald_spatial_error=R*i

29、nv(Rafg*varcov*Rafg)*R prob_spatial_error=1-chis_cdf (Wald_spatial_error,K) LR test spatial lag resultssar=sar_panel_FE(y,x,W,T,info); LR_spatial_lag=-2* (LR_spatial_lag,K) LR test spatial error resultssem=sem_panel_FE(y,x,W,T,info); LR_spatial_error=-2* (LR_spatial_error,K) 5、空間隨機效應與時點固定效應模型 T=30;

30、N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); for t=1:T t1=(t-1)*N+1;t2=t*N; wx(t1:t2,:)=W*x(t1:t2,:); end xconstant=ones(N*T,1); nobs K=size(x); ywith,xwith,meanny,meannx,meanty,meantx=demean(y,x wx,N,T,2); =1; results=sar_panel_RE(ywith,xwith,W,T,info); prt_spnew(results,vnames,1) spat_model=1; direct_

31、indirect_effects_estimates(results,W,spat_model); panel_effects_sdm(results,vnames,W) wald test spatial lag btemp=(1:2*K+2); varcov=(1:2*K+2,1:2*K+2); Rafg=zeros(K,2*K+2); for k=1:K end Wald_spatial_lag=(Rafg*btemp)*inv(Rafg*varcov*Rafg)*Rafg*btemp prob_spatial_lag= 1-chis_cdf (Wald_spatial_lag, K)

32、wald test spatial error R=zeros(K,1); for k=1:K R(k)=btemp(2*K+1)*btemp(k)+btemp(K+k); % R(1)=btemp(5)*btemp(1)+btemp(3); % R(2)=btemp(5)*btemp(2)+btemp(4); end% 2=time dummies Rafg(k,K+k)=1; % R(1,3)=0 and R(2,4)=0; % k changed in 1, 7/12/2010 Rafg=zeros(K,2*K+2); for k=1:K Rafg(k,K+k) =1; Rafg(k,2

33、*K+1)=btemp(k); % Rafg(1,1)=btemp(5);Rafg(1,3)=1;Rafg(1,5)=btemp(1); % Rafg(2,2)=btemp(5);Rafg(2,4)=1;Rafg(2,5)=btemp(2); end Wald_spatial_error=R*inv(Rafg*varcov*Rafg)*R prob_spatial_error= 1-chis_cdf (Wald_spatial_error,K) LR test spatial lag resultssar=sar_panel_RE(ywith,xwith(:,1:K),W,T,info); L

34、R_spatial_lag=-2* (LR_spatial_lag,K) LR test spatial error resultssem=sem_panel_RE(ywith,xwith(:,1:K),W,T,info); LR_spatial_error=-2* (LR_spatial_error,K) 四、靜態面板SEM模型 1、無固定效應( No fixed effects ) T=30; N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); for t=1:T Rafg(k,k) =btemp(2*K+1); % k changed in 1, 7/12/

35、2010 t1=(t-1)*N+1;t2=t*N; wx(t1:t2,:)=W*x(t1:t2,:); end xconstant=ones(N*T,1); nobs K=size(x); =0; =0; =0; results=sem_panel_FE(y,xconstant x,W,T,info); vnames=strvcat( logcit , intercept , logp , logy ); prt_spnew(results,vnames,1) % Print out effects estimates spat_model=0; direct_indirect_effects

36、_estimates(results,W,spat_model); panel_effects_sar(results,vnames,W); 2、空間固定效應( Spatial fixed effects T=30; N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); for t=1:T t1=(t-1)*N+1;t2=t*N; wx(t1:t2,:)=W*x(t1:t2,:); end xconstant=ones(N*T,1); nobs K=size(x); =0; =1; =0; results=sem_panel_FE(y,x,W,T,info); vn

37、ames=strvcat( logcit , logp , logy ); prt_spnew(results,vnames,1) % Print out effects estimates spat_model=0; direct_indirect_effects_estimates(results,W,spat_model); panel_effects_sar(results,vnames,W); 3、時點固定效應( Time period fixed effects T=30; N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); for t=1:T t1=

38、(t-1)*N+1;t2=t*N; wx(t1:t2,:)=W*x(t1:t2,:); end xconstant=ones(N*T,1); nobs K=size(x);=3; =0; % Do not print intercept and fixed effects; use =1 to turn on =0; % required for exact results =2; =0; % Do not print intercept and fixed effects; use =1 to turn on results=sem_panel_FE(y,x,W,T,info); vname

39、s=strvcat( logcit , logp , logy ); prt_spnew(results,vnames,1) % Print out effects estimates spat_model=0; direct_indirect_effects_estimates(results,W,spat_model); panel_effects_sar(results,vnames,W); 4、雙固定效應( Spatial and time period fixed effects T=30; N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); for t

40、=1:T t1=(t-1)*N+1;t2=t*N; wx(t1:t2,:)=W*x(t1:t2,:); end xconstant=ones(N*T,1); nobs K=size(x); =0; % required for exact results results=sem_panel_FE(y,x,W,T,info); vnames=strvcat( logcit , logp , logy ); prt_spnew(results,vnames,1) % Print out effects estimates spat_model=0; direct_indirect_effects_

41、estimates(results,W,spat_model); panel_effects_sar(results,vnames,W); 五、靜態面板SDEM模型 1、無固定效應( No fixed effects ) T=30; N=46; W=normw(W1); y=A(:,3); x=A(:,4,6); for t=1:T t1=(t-1)*N+1;t2=t*N; wx(t1:t2,:)=W*x(t1:t2,:); end xconstant=ones(N*T,1); nobs K=size(x); =0; =0; =0; results=sem_panel_FE(y,xconsta

42、nt x wx,W,T,info); vnames=strvcat( logcit , intercept , logp , logy , W*logp , W*logy ); prt_spnew(results,vnames,1) % Print out effects estimates spat_model=1; direct_indirect_effects_estimates(results,W,spat_model); panel_effects_sdm(results,vnames,W); 2、空間固定效應( Spatial fixed effects T=30; N=46; W=normw(W1); y=A(:,3); prt_spnew(results,vnames,1) % Print out effects estimates x=A(:,4,6); for t=1:T t1=(t-1)*N+1;t2=t*N; wx(t1:t2,:)=W*x(t1:t2,:); end xconstant=ones(N*T,1); nobs K=size(x); =0; % required for exact results =1; =0; % Do not print intercept and