Consider following error correction model, where all variables in levels are assumed to be I(1):

        D.y_it = c_i + a_i1*D.y_it-1 + a_i2*D.y_it-2 + ... +  a_ip*D.y_it-p

                     + b_i0*D.x_it + b_i1*D.x_it-1 + ... + b_ip*D.x_it-p

                     + a_i(y_it-1 - b_i*x_it-1) + u_it

    a_i provides an estimate of the speed of error-correction towards the long run equilibrium y_it = - (b_i/a_i) * x_it for that series i. The Ga and Gt test statistics test H0: a_i = 0
    for all i versus H1: a_i < 0 for at least one i. These statistics start from a weighted average of the individualy estimated a_i's and their t-ratio's respectively. Rejection of H0
    should therefore be taken as evidence of cointegration of at least one of the cross-sectional units.  The Pa and Pt test statistics pool information over all the cross-sectional units
    to test H0: a_i = 0 for all i vs H1:  a_i < 0 for all i. Rejection of H0 should therefore be taken as evidence of cointegration for the panel as a whole.

    The tests are very flexible and allow for an almost completely heterogeneous specification of both the long- and short-run parts of the error correction model, where the latter can be
    determined from the data. The series are allowed to be of unequal length.

    If the cross sectional units are suspected to be correlated, robust critical values can be obtained through bootstrapping.

希望对你有帮助

谢谢您！用的时候才学，很费劲，需要我再好好琢磨一下！非常感谢您！

前两个表示至少存在一组协整关系，后两个表示10组都存在协整关系