R语言程序如下：
jo1=ca.jo(data1,type="trace",ecdet = ('trend'),K=3,spec="longrun",season=NULL)
vecm.ols=cajorls(jo1,r=1)
summary(vecm.ols$rlm)

结果是这样的：
Response b.d :

Call:
lm(formula = b.d ~ ect1 + constant + b.dl1 + a.dl1 + b.dl2 +
    a.dl2 - 1, data = data.mat)

Residuals:
      Min        1Q    Median        3Q       Max
-0.147699 -0.012363  0.001038  0.015584  0.098315

Coefficients:
           Estimate Std. Error t value Pr(>|t|)
ect1      0.0004875  0.0009597   0.508    0.612
constant -0.1299624  0.2585723  -0.503    0.616
b.dl1     0.0844789  0.0649283   1.301    0.194
a.dl1    -0.0039859  0.0236960  -0.168    0.867
b.dl2     0.0618550  0.0648104   0.954    0.341
a.dl2     0.0104587  0.0305578   0.342    0.732

Residual standard error: 0.033 on 236 degrees of freedom
Multiple R-squared:  0.01655,        Adjusted R-squared:  -0.008451
F-statistic: 0.662 on 6 and 236 DF,  p-value: 0.6804


Response a.d :

Call:
lm(formula = a.d ~ ect1 + constant + b.dl1 + a.dl1 + b.dl2 +
    a.dl2 - 1, data = data.mat)

Residuals:
     Min       1Q   Median       3Q      Max
-1.24493 -0.01642  0.00068  0.02846  0.23329

Coefficients:
          Estimate Std. Error t value Pr(>|t|)   
ect1     -0.015848   0.002615  -6.062 5.30e-09 ***
constant  4.280570   0.704459   6.076 4.89e-09 ***
b.dl1    -0.044655   0.176892  -0.252    0.801   
a.dl1    -0.844534   0.064558 -13.082  < 2e-16 ***
b.dl2     0.116768   0.176571   0.661    0.509   
a.dl2    -0.695510   0.083252  -8.354 5.66e-15 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.0899 on 236 degrees of freedom
Multiple R-squared:  0.4225,        Adjusted R-squared:  0.4078
F-statistic: 28.77 on 6 and 236 DF,  p-value: < 2.2e-16



为什么误差修正模型的滞后项只有2阶而不是3阶呢，而且johansen检验的时候我的选的是带有趋势项的，为什么估计出的VECM模型里面是constant项呢