In this article,we study using a.parametric bootstrap(PB)approach to solve the hypothesis test and multiple comparison problem in panel data models.In the paper,the following aspects are interested.1.For a fixed one-way error component regression model(ANCOVA model),we propose simultaneous confidence intervals for all pairwise multiple comparisons in AN-COVA unbalanced design with unequal variances,using a parametric bootstrap approach.simulation results show that Type 1 error of the multiple comparison test is close to the normal level even for small samples.2.For the testing equality problem of regression coefficients in several two-way error component regression models,a parameter bootstrap approach is proposed.At the same time,we has been extended the parameter bootstrap approach the to a multiple compar-ison procedure.Some simulated numerical results indicate that the PB test,regardless of the sample sizes,values of the variance components,number of the models,performs well. |