请问大神们如何解决呢?Warning: Matrix is close to singular or badly scaled.
Results may be inaccurate. RCOND = 5.736767e-019.
> In ols at 51
In demoLMsarsem_panel at 30
Ordinary Least-squares Estimates
Dependent Variable = LFDI
R-squared = -251.3651
Rbar-squared = -260.5117
sigma^2 = 922.5813
Durbin-Watson = 0.2789
Nobs, Nvars = 630, 23
Warning: Matrix is close to singular or badly scaled. Results may be inaccurate. RCOND = 1.450489e-018. > In LMsarsem_panel at 37 In demoLMsarsem_panel at 38LM test no spatial lag, probability = 47.3846, 0.000 robust LM test no spatial lag, probability = 2010.5871, 0.000 LM test no spatial error, probability = 736.5092, 0.000 robust LM test no spatial error, probability = 2699.7117, 0.000 Warning: Matrix is close to singular or badly scaled. Results may be inaccurate. RCOND = 1.450489e-018. > In lmlag_panel at 50 In demoLMsarsem_panel at 43LM lag test for omitted spatial lag in panel data
附带程序A=wk1read('cigardemo.wk1',1,0); % data set with T=30W1=wk1read('spat-sym-us1.wk1');% Dataset downloaded from www.wiley.co.uk/baltagi/% Spatial weights matrix constructed by Elhorst%% written by: J.Paul Elhorst summer 2010% University of Groningen% Department of Economics% 9700AV Groningen% the Netherlands% j.p.elhorst@rug.nl%% REFERENCES: % Elhorst JP (2010) Matlab Software for Spatial Panels. Under review.%% Elhorst JP (2010) Spatial Panel Data Models. In Fischer