cmp package problem - lcmp.mlib is read only

[Arthur Carvalho Brito]

Hello,

I apologize in advance in case I say something really trivial. I am not a Stata user.

I want to install package cmp

After installing it and ghk2 and trying to run any simple regression with it, here is the error I get:

file c:\ado\plus/l/lcmp,mlib is read-only; cannot be modified or erased
file is read-only; cannot be modified or erased

I am using Stata 14 in a server without admin permissions and with no internet connection. Only a supervisor can install packages and so on.

Can someone help debug this?

The supervisor says that other people did not have any trouble in using other installed packages.

[William Lisowski]

I have duplicated your problem by installing cmp and ghk2 then making lcmp.mlib read-only before the first time I try to use cmp. Stata needs to initialize the contents of lcmp.mlib the first time it is used, and the supervisor did not grant you write permission on that file.

The supervisor should run the following simple example from an admin account that can modify the file. Once that is done, you should be able to use cmp successfully going forward. This program does not need internet connectivity to run.

clear all
cmp setup
sysuse auto
reg mpg weight length
cmp (mpg = weight length),  ind($cmp_cont) quietly

and it produces this output when successful.

. clear all

. cmp setup
$cmp_out      = 0
$cmp_missing  = .
$cmp_cont     = 1
$cmp_left     = 2
$cmp_right    = 3
$cmp_probit   = 4
$cmp_oprobit  = 5
$cmp_mprobit  = 6
$cmp_int      = 7
$cmp_trunc    = 8  (deprecated)
$cmp_roprobit = 9
$cmp_frac     = 10

. sysuse auto
(1978 Automobile Data)

. reg mpg weight length

      Source |       SS           df       MS      Number of obs   =        74
-------------+----------------------------------   F(2, 71)        =     69.34
       Model |  1616.08062         2  808.040312   Prob > F        =    0.0000
    Residual |  827.378835        71   11.653223   R-squared       =    0.6614
-------------+----------------------------------   Adj R-squared   =    0.6519
       Total |  2443.45946        73  33.4720474   Root MSE        =    3.4137

------------------------------------------------------------------------------
         mpg |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
      weight |  -.0038515    .001586    -2.43   0.018    -.0070138   -.0006891
      length |  -.0795935   .0553577    -1.44   0.155    -.1899736    .0307867
       _cons |   47.88487    6.08787     7.87   0.000       35.746    60.02374
------------------------------------------------------------------------------

. cmp (mpg = weight length),  ind($cmp_cont) quietly

Fitting individual models as starting point for full model fit.

Fitting constants-only model for LR test of overall model fit.

Fitting full model.

Mixed-process regression                        Number of obs     =         74
                                                LR chi2(2)        =      80.14
Log likelihood = -194.32676                     Prob > chi2       =     0.0000

------------------------------------------------------------------------------
         mpg |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
mpg          |
      weight |  -.0038515   .0015535    -2.48   0.013    -.0068963   -.0008067
      length |  -.0795935    .054224    -1.47   0.142    -.1858705    .0266836
       _cons |   47.88487    5.96319     8.03   0.000     36.19724    59.57251
-------------+----------------------------------------------------------------
    /lnsig_1 |   1.207099   .0821995    14.68   0.000     1.045991    1.368207
-------------+----------------------------------------------------------------
       sig_1 |   3.343769   .2748561                      2.846217    3.928299
------------------------------------------------------------------------------

.

[Arthur Carvalho Brito]

thank you! It worked