st: XTFRONTIER: How to interpret Total Efficiency Measures

[Victor Waters <vvwaters@gmail.com>]

Dear StataListers,

I am a little confused about the magnitude of the total efficiency
measure. My XTFRONTIER with time varying decay model,
runs well, almost all of the coefficients are as expected.,

My total efficiency measures (for all units) are very low - between .1
and .25. What importance should I attach to this?
Does it mean all of the units are very inefficient? Can it only be
interpreted as the order of efficiency among the units?

For exactly the same specification if I run time invariant model, the
efficiency measures a lot more reasonable: in the range
.4 to .8. Are these two sets of measures comparable? I understand that
if eta = 0, both ti and tvd option results are the same.
If eta is not 0, can I compare ti and tvd efficiency measures?

I looked at all the sources I have for answers to the above questions,
but could not get answers.

I appreciate pointing me to the right direction.

Best regards,

Victor
*
*   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/