步学会用MATLAB做空间计量回归详细步骤docx.docx

1、步学会用MATLAB做空间计量回归详细步骤docx与MATLAB链接：Excel ：选项加载项 COM 加载项转到没有勾选项2.MATLAB安装目录中寻找 toolbox exlink 点击 , 启用宏E:MATLABtoolboxexlink然后， Excel 中就出现 MATLAB 工具（注意 Excel 中的数据：）3. 启动 matlab（1 ） 点击 start MATLAB（2 ） senddata to matlab ，并对变量矩阵变量进行命名 （注意： 选取变量为数值， 不包括各变量）(data 表中数据进行命名 )（空间权重进行命名）（3 ） 导入 MATLAB 中的两个矩阵

2、变量就可以看见4.将 elhorst 和 jplv7 两个程序文件夹复制到 MATLAB 安装目录的 toolbox 文件夹5.设置路径：6.输入程序，得出结果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*

3、pi*sige)-1/(2*sige)*% The (robust)LM tests developed by ElhorstLMsarsem_panel(results,W,y,xconstant x); % (Robust) LM tests解释每一行分别表示：该面板数据的时期数为 30（ T=30 ），该面板数据有 30 个地区（ N=30 ），将空间权重矩阵标准化（ W=normw(w1) ），将名为 A（以矩阵形式出现在 MATLABA 中）的变量的第3 列数据定义为被解释变量y,将名为 A 的变量的第 4、 5、 6 列数据定义为解释变量矩阵 x，定义一个有 N*T 行， 1 列的

4、全 1 矩阵，该矩阵名为： xconstant ，（ ones 即为全说明解释变量矩阵 x 的大小：有 nobs 行， K 列。（ size 为描述矩阵的大小） 。1 矩阵）附录：静态面板空间计量经济学一、 OLS 静态面板编程1、普通面板编程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

5、);sige=*(nobs-K)/nobs);loglikols=-nobs/2*log(2*pi*sige)-1/(2*sige)*% The (robust)LM tests developed by ElhorstLMsarsem_panel(results,W,y,xconstant x); % (Robust) LM tests2、空间固定 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;ywith,xw

6、ith,meanny,meannx,meanty,meantx=demean(y,x,N,T,model);results=ols(ywith,xwith);vnames=strvcat(logcit,logp,logy); % should be changed if x ischangedprt_reg(results,vnames);sfe=meanny-meannx*; % including the constant termyme = y - mean(y);et=ones(T,1);error=y-kron(et,sfe)-x*;rsqr1 = error*error;rsqr2

7、 = yme*yme;FE_rsqr2 = - rsqr1/rsqr2 % r-squared including fixed effectssige=*(nobs-K)/nobs);logliksfe=-nobs/2*log(2*pi*sige)-1/(2*sige)*LMsarsem_panel(results,W,ywith,xwith); % (Robust) LM tests3、时期固定 OLS（time-period fixed effects ）T=30;N=46;W=normw(W1);y=A(:,3);x=A(:,4,6);xconstant=ones(N*T,1);nobs

8、 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 changedprt_reg(results,vnames);tfe=meanty-meantx*; % including the constant termyme = y - mean(y);en=ones(N,1);error=y-kron(tfe,en)-

9、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 tests4、空间与时间双固定模型T=30;N=46;W=normw(W1);y=A(:,3);x=A(:,4,6);xconstant=ones(N*T,1);no

10、bs 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 changedprt_reg(results,vnames)en=ones(N,1);et=ones(T,1);intercept=mean(y)-mean(x)*;sfe=meanny-meannx*(en,intercept);tfe=meanty-mea

11、ntx*(et,intercept);yme = y - mean(y);ent=ones(N*T,1);error=y-kron(tfe,en)-kron(et,sfe)-x*(ent,intercept);rsqr1 = error*error;rsqr2 = yme*yme;FE_rsqr2 = - rsqr1/rsqr2 % r-squared including fixed effectssige=*(nobs-K)/nobs);loglikstfe=-nobs/2*log(2*pi*sige)-1/(2*sige)*LMsarsem_panel(results,W,ywith,xw

12、ith); % (Robust) LM tests二、静态面板 SAR 模型1、无固定效应（ No fixed effects ）T=30;N=46;W=normw(W1);y=A(:,3);x=A(:,4,6);for t=1:Tt1=(t-1)*N+1;t2=t*N;wx(t1:t2,:)=W*x(t1:t2,:);endxconstant=ones(N*T,1);nobs K=size(x);=0;=0;=0;results=sar_panel_FE(y,xconstant x,W,T,info);vnames=strvcat( logcit , intercept, logp, log

13、y);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、空间固定效应（ Spatial fixed effects ）T=30;N=46;W=normw(W1);y=A(:,3);x=A(:,4,6);for t=1:Tt1=(t-1)*N+1;t2=t*N;wx(t1:t2,:)=W*x(t1:t2,:);endxcon

14、stant=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 effects estimates spat_model=0;direct_indirect_effects_estimates(results,W,spat_model); panel_effects_sar(results,vnames,W);3、时点固定效应（ Time period

15、fixed effects ）T=30;N=46;W=normw(W1);y=A(:,3);x=A(:,4,6);for t=1:Tt1=(t-1)*N+1;t2=t*N;wx(t1:t2,:)=W*x(t1:t2,:);endxconstant=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 onresults=sar_panel_FE(y,x,W,T,info);vnames=strvcat

16、( 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、双固定效应（ Spatial and time period fixed effects ）T=30;N=46;W=normw(W1);y=A(:,3);x=A(:,4,6);for t=1:Tt1=(t-1)*N+1;t

17、2=t*N;wx(t1:t2,:)=W*x(t1:t2,:);endxconstant=ones(N*T,1);nobs K=size(x);=0; % required for exact results=3;=0; % Do not print intercept and fixed effects; use =1 to turn onresults=sar_panel_FE(y,x,W,T,info);vnames=strvcat( logcit , logp , logy );prt_spnew(results,vnames,1)%Print out effects estimates

18、 spat_model=0;direct_indirect_effects_estimates(results,W,spat_model); panel_effects_sar(results,vnames,W);三、静态面板 SDM 模型1、无固定效应（ No fixed effects ）T=30;N=46;W=normw(W1);y=A(:,3);x=A(:,4,6);for t=1:Tt1=(t-1)*N+1;t2=t*N;wx(t1:t2,:)=W*x(t1:t2,:);endxconstant=ones(N*T,1);nobs K=size(x);=0;=0;=0;results=

19、sar_panel_FE(y,xconstant 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、空间固定效应（ Spatial fixed effec

20、ts ）T=30;N=46;W=normw(W1);y=A(:,3);x=A(:,4,6);for t=1:Tt1=(t-1)*N+1;t2=t*N;wx(t1:t2,:)=W*x(t1:t2,:);endxconstant=ones(N*T,1);nobs K=size(x);=0; % required for exact results=1;=0; % Do not print intercept and fixed effects; use =1 to turn onresults=sar_panel_FE(y,x wx,W,T,info);vnames=strvcat( logcit

21、 , 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);3、时点固定效应（ Time period fixed effects ）T=30;N=46;W=normw(W1);y=A(:,3);x=A(:,4,6);for t=1:Tt1=(t-1)*N+1;t2

22、=t*N;wx(t1:t2,:)=W*x(t1:t2,:);endxconstant=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 ,

23、 W*logy );%Print out coefficient estimates 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)4、双固定效应（ Spatial and time period fixed effects ）T=30;N=46;W=normw(W1);y=A(:,3);x=A(:,4,6);for t=

24、1:Tt1=(t-1)*N+1;t2=t*N;wx(t1:t2,:)=W*x(t1:t2,:);endxconstant=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 onresults=sar_panel_FE(y,x wx,W,T,info);vnames=strvcat( logcit , logp , logy , W*logp, W*logy);prt_spnew(result

25、s,vnames,1)%Print out effects estimates spat_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:KRafg(k,K+k)=1; % R(1,3)=0 an

26、d R(2,4)=0;endWald_spatial_lag=(Rafg*btemp)*inv(Rafg*varcov*Rafg)*Rafg*btempprob_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:KR(k)=btemp(2*K+1)*btemp(k)+btemp(K+k); % k changed in 1,7/12/2010% R(1

27、)=btemp(5)*btemp(1)+btemp(3);% R(2)=btemp(5)*btemp(2)+btemp(4);endRafg=zeros(K,2*K+2);for k=1:KRafg(k,k) =btemp(2*K+1); % k changed in 1, 7/12/2010Rafg(k,K+k) =1;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);endWald_spatial_error=R*inv(Raf