你为什么自己都不看help或者手册呢？这些问题，最应该问stata公司的编程的人。
为什么要用residual呢

  
Menu

    Statistics > Postestimation > Predictions, residuals, etc.


Options for predict

        +------+
    ----+ Main +------------------------------------------------------------------------------------

    xb calculates the linear prediction, that is, a + bx_it.  This is the default for all except the
        population-averaged model.

    stdp calculates the standard error of the linear prediction.  For the fixed-effects model, this
        excludes the variance due to uncertainty about the estimate of u_i.

    mu and rate both calculate the predicted probability of depvar.  mu takes into account the
        offset(), and rate ignores those adjustments.  mu and rate are equivalent if you did not
        specify offset().  mu is the default for the population-averaged model.

    ue calculates the prediction of u_it + e_it.

    xbu calculates the prediction of a + bx_it + u_i, the prediction including the fixed or random
        component.

    u calculates the prediction of u_i, the estimated fixed or random effect.

    e calculates the prediction of e_it.

    score calculates the equation-level score.

    nooffset is relevant only if you specified offset(varname) for xtreg.  It modifies the
        calculations made by predict so that they ignore the offset variable; the linear prediction
        is treated as xb rather than xb + offset.

thanks.