st: a simple question about xtabond2

[Gary Liam <galiam@live.com>]

Hello all:
 
I am struggling with the strange test result generated by xtabond2. As you can see from the below, the AR(2) test statistic is a dot rather than a value. What does it mean? Any clue would be appreciated.
 
Have a good day, Gary.
 
------------------------------------------------------------------------------
             |               Robust
    lnoutput |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
    lnoutput |
         L1. |    .193328   .0088937    21.74   0.000     .1758968    .2107593
         lnl |   .1429454   .0091662    15.59   0.000       .12498    .1609107
         lnk |   .0734289   .0078575     9.35   0.000     .0580284    .0888294
    lninterm |   .7327368    .014611    50.15   0.000     .7040999    .7613738
      yr2001 |  -.0025063   .0012095    -2.07   0.038    -.0048769   -.0001356
      yr2002 |  -.0006988   .0008106    -0.86   0.389    -.0022875    .0008899
       _cons |  -.4994844   .0663187    -7.53   0.000    -.6294666   -.3695023
------------------------------------------------------------------------------
 
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -17.32  Pr> z =  0.000
Arellano-Bond test for AR(2) in first differences: z =      .  Pr> z =      .
------------------------------------------------------------------------------
_________________________________________________________________
Windows Live™ Groups: Create an online spot for your favorite groups to meet.
http://windowslive.com/online/groups?ocid=TXT_TAGLM_WL_groups_032009
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/