Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Oaxaca command error


From   "Ben Jann" <ben.jann@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Oaxaca command error
Date   Mon, 20 Nov 2006 16:39:13 +0100

The reason for the misbehavior is that Samer's data are -svyset- with
-strata()- set to -area-, but -area- does not exist in the data. If a
specific survey design is set (-svyset-), the -svymean- command is
used by -oaxaca- to compute the sampling variances of the means of the
regressors. However, in Samer's case, -svymean- produces error because
-area- cannot be found. Samer could, for example, type

. svyset, clear

to erase the survey settings. Furthermore, note that computation of
the variances of the means of the regressors is deactivated in
-oaxaca- if the -fixed- or -nose- option is specified.

ben


On 11/18/06, Samer Al-Samarrai <alsamarrai@msbx.net> wrote:
Dear Owour,
Thanks for the suggestion. I am not really sure why the number of dummy
variables should make a difference to the decomposition. However, I removed
all the dummy variables and just left the continuous variables (age and
years of education) and I still have the same problem.
Any ideas?
Cheers
Samer

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of george owuor
Sent: 18 November 2006 16:45
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: Oaxaca command error

Semer

your comand is for a simple OLS, but looking at your exogenours variables
you seem to have so many dummy variables in the midst of afew continours. My
bet is that you should  have as many contionours variables as possible and
reduce the dummies to 2 or 1. Many dummies in OLS may lead to colliniearity
or just a collapse of the estimation
Owuor

----- Original Message ----
From: Samer Al-Samarrai <alsamarrai@msbx.net>
To: statalist@hsphsun2.harvard.edu
Sent: Saturday, November 18, 2006 6:00:36 AM
Subject: st: Oaxaca command error


Dear Ben and all,

Below is my output and commands for the command I am trying to run. Any
ideas why I am getting the error at the end?

Kind regards

Samer



. regress logwage q04_1a agesq nonmuslim unmarried widdiv edyears urban
othact daily public if
>  q02_1a==1

      Source |       SS       df       MS              Number of obs =
6076
-------------+------------------------------           F( 10,  6065) =
291.05
       Model |  841.657382    10  84.1657382           Prob > F      =
0.0000
    Residual |  1753.89694  6065  .289183337           R-squared     =
0.3243
-------------+------------------------------           Adj R-squared =
0.3232
       Total |  2595.55432  6075   .42725174           Root MSE      =
.53776

----------------------------------------------------------------------------
--
     logwage |      Coef.   Std. Err.      t    P>|t|     [95% Conf.
Interval]
-------------+--------------------------------------------------------------
--
      q04_1a |   .0531162   .0033754    15.74   0.000     .0464993
.0597332
       agesq |   -.000566   .0000395   -14.34   0.000    -.0006434
-.0004887
   nonmuslim |  -.0547489   .0205557    -2.66   0.008    -.0950455
-.0144524
   unmarried |  -.0357809   .0264386    -1.35   0.176      -.08761
.0160482
      widdiv |  -.2524801   .0891609    -2.83   0.005    -.4272672
-.077693
     edyears |   .0499894   .0017928    27.88   0.000     .0464749
.053504
       urban |  -.0843149   .0150202    -5.61   0.000    -.1137597
-.0548701
      othact |   -.117553   .0231958    -5.07   0.000     -.163025
-.0720809
       daily |   .0528909   .0192471     2.75   0.006     .0151598
.090622
      public |   .3782054   .0282242    13.40   0.000      .322876
.4335349
       _cons |    1.11547   .0719105    15.51   0.000     .9745004
1.25644
----------------------------------------------------------------------------
--

. estimates store male

. regress logwage q04_1a agesq nonmuslim unmarried widdiv edyears urban
othact daily public  i
> f q02_1a==2

      Source |       SS       df       MS              Number of obs =
911
-------------+------------------------------           F( 10,   900) =
75.53
       Model |  345.167654    10  34.5167654           Prob > F      =
0.0000
    Residual |  411.300243   900   .45700027           R-squared     =
0.4563
-------------+------------------------------           Adj R-squared =
0.4502
       Total |  756.467897   910  .831283403           Root MSE      =
.67602

----------------------------------------------------------------------------
--
     logwage |      Coef.   Std. Err.      t    P>|t|     [95% Conf.
Interval]
-------------+--------------------------------------------------------------
--
      q04_1a |   .0249686   .0098448     2.54   0.011     .0056472
.0442901
       agesq |  -.0003035   .0001219    -2.49   0.013    -.0005429
-.0000642
   nonmuslim |   .1068738   .0562578     1.90   0.058     -.003538
.2172855
   unmarried |   -.176665   .0818691    -2.16   0.031    -.3373415
-.0159885
      widdiv |   .0578513   .0628656     0.92   0.358    -.0655289
.1812315
     edyears |   .0744867   .0051692    14.41   0.000     .0643416
.0846317
       urban |  -.0671306    .047878    -1.40   0.161    -.1610962
.0268349
      othact |  -.0737967   .2417162    -0.31   0.760    -.5481898
.4005964
       daily |   .0375057   .0580337     0.65   0.518    -.0763915
.1514028
      public |    .735572   .0722005    10.19   0.000      .593871
.8772729
       _cons |    1.07086   .1927252     5.56   0.000     .6926163
1.449103
----------------------------------------------------------------------------
--

. estimates store female

.
. oaxaca male female
area found where variable expected
r(198);

end of do-file


*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



____________________________________________________________________________
________
Sponsored Link

$420k for $1,399/mo.
Think You Pay Too Much For Your Mortgage?
Find Out! www.LowerMyBills.com/lre

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index