[Limdep Nlogit List] Stochastic Frontiers (errors in estimation)

[Pavlos C. Symeou]

Dear Limdep-listers,

I have been trying to estimate a Battese and Coelli - time varying 
inefficiency model with a number of Z variables that affect the 
efficiency scores. I use Limdep 9 to estimate a multi-input multi-output 
translog model based on panel data for 15 years and 113 countries. Below 
I provide the commands I use and output they produce after estimation. I 
need help to understand what I am doing wrong. I can't estimate any 
efficiency scores and Limdep produces various errors in different stages 
of the procedure.

Your help is valuable.

Thanks and Happy New Year,

Pavlos



--> Frontier     ; Lhs = LNY1
        ; Rhs = one, XS
        ; Pds = 15
        ; Model = BC
        ; Rh2 = ZS
        ; Eff = u $
  Error   315: Stoch. Frontier: OLS residuals have wrong skew. OLS is MLE.
WARNING! OLS residuals have the wrong skewness for SFM
Other forms of the model models may also behave poorly.
In this case, one MLE for the half normal model is OLS
for beta and sigma and zero for the inefficiency term.
Maximum iterations reached. Exit iterations with status=1.

+---------------------------------------------+
| Limited Dependent Variable Model - FRONTIER |
| Maximum Likelihood Estimates                |
| Model estimated: Jan 03, 2008 at 01:50:40AM.|
| Dependent variable                 LNY1     |
| Weighting variable                 None     |
| Number of observations             1695     |
| Iterations completed                 51     |
| Log likelihood function       -10551.84     |
| Number of parameters                 33     |
| Info. Criterion: AIC =         12.48948     |
|   Finite Sample: AIC =         12.49028     |
| Info. Criterion: BIC =         12.59531     |
| Info. Criterion:HQIC =         12.52867     |
| Variances: Sigma-squared(v)=   8938.70603   |
|            Sigma-squared(u)=  19638.21994   |
|            Sigma(v)        =     94.54473   |
|            Sigma(u)        =    140.13643   |
| Sigma = Sqr[(s^2(u)+s^2(v)]=    169.04711   |
| Stochastic Production Frontier, e=v-u.      |
+---------------------------------------------+
+--------+--------------+----------------+--------+--------+----------+
|Variable| Coefficient  | Standard Error |b/St.Er.|P[|Z|>z]| Mean of X|
+--------+--------------+----------------+--------+--------+----------+
---------+Primary Index Equation for Model
 Constant|    456.106984      88.7387504     5.140   .0000
 LX1     |    6.27502814      4.76532848     1.317   .1879  -371.095961
 LX1LX2  |     .02396850       .03951832      .607   .5442  -319.443283
 LX1LY2S |    -.10777281       .03622185    -2.975   .0029  -602.643722
 LX1LY3S |    -.15111436       .03368515    -4.486   .0000  -494.200121
 LX1SQ   |   -6.59483200      4.73005698    -1.394   .1632  -360.862718
 LX2     |    6.87990642      5.55754410     1.238   .2157  -190.194638
 LX2LY2S |    -.11656331       .02951213    -3.950   .0001  -463.059328
 LX2LY3S |    -.21631294       .02880244    -7.510   .0000  -331.716066
 LX2SQ   |   -9.26394732      5.64020525    -1.642   .1005  -184.714940
 LY2S    |   -18.4730978      7.24680407    -2.549   .0108  -364.111357
 LY2SLY3S|    -.19625337       .02204924    -8.901   .0000  -408.573282
 LY2SSQ  |    20.4140155      8.01362428     2.547   .0109  -365.164307
 LY3S    |   -20.5033915      4.48522105    -4.571   .0000  -213.433041
 LY3SSQ  |    22.8068224      4.90242529     4.652   .0000  -215.867852
 T       |   -41.1559801      3.36539025   -12.229   .0000   8.00000000
 TLX1    |     .53693750       .21018656     2.555   .0106  -310.197719
 TLX2    |    2.51200670       .48826893     5.145   .0000  -156.508794
 TLY2S   |   -1.51091987      1.10324166    -1.370   .1708  -369.363857
 TLY3S   |   -1.76661337      1.00074816    -1.765   .0775  -225.627731
 TSQ     |    -.12864040       .19597293     -.656   .5116   82.6666667
---------+Offset [mean=mu(i)] parameters in one sided error
 DARABLE |    -.05330241       .01429629    -3.728   .0002   179.141006
 DGDP    |     .10359925       .00925142    11.198   .0000   87.2743637
 DPOP    |    -.04922306       .02304654    -2.136   .0327  -83.1663196
 LIBF    |   -2.66762829      5.77408152     -.462   .6441  -171.974041
 LIBI    |   -8.25725876      64.5824664     -.128   .8983  -180.672566
 LIBM    |    10.7048074      63.1794824      .169   .8655  -180.706785
 NRA     |   -214.987303      99.4464844    -2.162   .0306    .20766962
 OPENC   |    -.04088520       .01959387    -2.087   .0369  -195.916048
 POLITY  |     .08440786       .03761648     2.244   .0248  -487.837758
 PRIVAT  |   -31.6025426      19.9452282    -1.584   .1131    .41592920
---------+Variance parameters for compound error
 Lambda  |    1.48222363       .07494866    19.777   .0000
 Sigma   |    169.047112      4.69180560    36.030   .0000

Warning   141: Iterations:current or start estimate of sigma is nonpositiv
Warning   141: Iterations:current or start estimate of sigma is nonpositiv
Warning   141: Iterations:current or start estimate of sigma is nonpositiv
Warning   141: Iterations:current or start estimate of sigma is nonpositiv
Warning   141: Iterations:current or start estimate of sigma is nonpositiv
Initial iterations cannot improve function.Status=3
  Error   805: Initial iterations cannot improve function.Status=3
Function=  .31649671740D+11, at entry,  .19991487733D+06 at exit
  Error   143: Models - estimated variance matrix of estimates is singular

--> Create    ; Score = Exp(-u) $
  Error   768: Have been unable to break down the command segment.
  Error   623: Check for error in -U
  Error   623: Look for: Unknown names, pairs of operators, e.g., */
  Error    61: Compilation error in CREATE. See previous diagnostic.