"Variable not found" upon attempting to test, after running regression model.

[Som Nwegbu]

Hello, I'm using Stata 13 and working with complex survey data (DHS 2013). I'm having problems testing my predictor variables after running my model:

Please see document attached for the output/response.

Same thing happens even when I attempt to test the predictors individually. (NB: I tested the outcome variables successfully though).

Thank you for your help.
Som

[Carlo Lazzaro]

Som:
we do not see anything about what you typed and what Stata gave you back. Hence, I find impossible to reply.

[Som Nwegbu]

Thank you. I just noticed the error myself and amended the post.

[Carlo Lazzaro]

Som:
despite your laudable effort to amend your previous post, most of us do not open/use .docx and other common file formats.
As per FAQ the best way to post what you typed and what Stata gave you back is via CODE delimiters.
Besides, you can post an excerpt/example of your dataset via -dataex- from SSC.

[Som Nwegbu]

My sincere apologies, and thank you for setting me right. Here is the output with the code delimiters. I hope I got it right this time.

. mvreg anch inch dmchil limchild = i.exipv i.agemarr4 i.rel i.weduc i.Wempow i.wipv i.polyg i.chcomm

Equation Obs Parms RMSE "R-sq" F P

anch 16114 14 .4250494 0.2402 391.518 0.0000
inch 16114 14 .4204062 0.2882 501.4525 0.0000
dmchil 16114 14 .3526811 0.0900 122.5547 0.0000
limchild 16114 14 .4560623 0.1265 179.3537 0.0000


Coef. Std. Err. t P>t [95% Conf. Interval]

anch
exipv
Yes .0424252 .0092808 4.57 0.000 .0242339 .0606165

agemarr4
15-17 years -.0771878 .0094442 -8.17 0.000 -.0956996 -.058676
18-21 years -.1135442 .0105576 -10.75 0.000 -.1342383 -.0928501
22 years or older -.1770452 .011913 -14.86 0.000 -.200396 -.1536943

rel
catholic .115711 .0136041 8.51 0.000 .0890455 .1423765
other christian .0805618 .0092663 8.69 0.000 .0623987 .0987248

weduc
primary .0067942 .0102279 0.66 0.507 -.0132535 .026842
secondary -.1022443 .0103025 -9.92 0.000 -.1224384 -.0820503
higher than secondary -.0982048 .0153291 -6.41 0.000 -.1282516 -.068158

Wempow
Empowered .0284312 .0075755 3.75 0.000 .0135825 .04328

wipv
yes .0093565 .0116604 0.80 0.422 -.0134991 .0322122

polyg
Yes .0916139 .0083539 10.97 0.000 .0752393 .1079884

chcomm
Yes .7959637 .0124833 63.76 0.000 .7714949 .8204324
_cons .3550245 .0141289 25.13 0.000 .3273303 .3827187

inch
exipv
Yes -.0019619 .0091794 -0.21 0.831 -.0199545 .0160306

agemarr4
15-17 years -.0303042 .0093411 -3.24 0.001 -.0486137 -.0119946
18-21 years -.0983254 .0104423 -9.42 0.000 -.1187934 -.0778574
22 years or older -.18858 .0117829 -16.00 0.000 -.2116757 -.1654842

rel
catholic -.1310468 .0134554 -9.74 0.000 -.157421 -.1046727
other christian -.1755753 .0091651 -19.16 0.000 -.1935399 -.1576107

weduc
primary -.104613 .0101161 -10.34 0.000 -.1244417 -.0847842
secondary -.2921949 .0101899 -28.67 0.000 -.3121684 -.2722215
higher than secondary -.3748884 .0151617 -24.73 0.000 -.404607 -.3451699

Wempow
Empowered -.0774337 .0074927 -10.33 0.000 -.0921202 -.0627471

wipv
yes .0009854 .011533 0.09 0.932 -.0216205 .0235914

polyg
Yes .0382797 .0082626 4.63 0.000 .022084 .0544754

chcomm
Yes .0463013 .012347 3.75 0.000 .0220998 .0705027
_cons 1.877182 .0139746 134.33 0.000 1.849791 1.904574

dmchil
exipv
Yes -.0452851 .0077006 -5.88 0.000 -.0603792 -.030191

agemarr4
15-17 years .0020027 .0078363 0.26 0.798 -.0133573 .0173627
18-21 years -.0158285 .0087601 -1.81 0.071 -.0329993 .0013422
22 years or older .0365245 .0098847 3.70 0.000 .0171493 .0558997

rel
catholic -.1557431 .0112878 -13.80 0.000 -.1778686 -.1336177
other christian -.1505418 .0076886 -19.58 0.000 -.1656124 -.1354712

weduc
primary -.0786239 .0084865 -9.26 0.000 -.0952584 -.0619895
secondary -.0166112 .0085484 -1.94 0.052 -.033367 .0001446
higher than secondary -.0709052 .0127192 -5.57 0.000 -.0958363 -.0459741

Wempow
Empowered -.0705726 .0062857 -11.23 0.000 -.0828933 -.058252

wipv
yes .0081457 .0096751 0.84 0.400 -.0108186 .02711

polyg
Yes -.0517344 .0069316 -7.46 0.000 -.0653211 -.0381478

chcomm
Yes -.0861196 .0103579 -8.31 0.000 -.1064223 -.0658168
_cons 1.050703 .0117233 89.62 0.000 1.027724 1.073682

limchild
exipv
Yes .0586822 .0099579 5.89 0.000 .0391636 .0782008

agemarr4
15-17 years .0124821 .0101333 1.23 0.218 -.0073803 .0323446
18-21 years .0500045 .0113279 4.41 0.000 .0278005 .0722084
22 years or older -.0061054 .0127822 -0.48 0.633 -.03116 .0189492

rel
catholic .1472927 .0145966 10.09 0.000 .1186816 .1759037
other christian .1487904 .0099424 14.97 0.000 .1293022 .1682786

weduc
primary .1180335 .0109741 10.76 0.000 .096523 .1395439
secondary .156371 .0110542 14.15 0.000 .1347035 .1780384
higher than secondary .2093811 .0164476 12.73 0.000 .177142 .2416202

Wempow
Empowered .09369 .0081282 11.53 0.000 .0777579 .1096222

wipv
yes .0281382 .0125112 2.25 0.025 .0036149 .0526614

polyg
Yes .0238543 .0089634 2.66 0.008 .006285 .0414236

chcomm
Yes .1778668 .0133942 13.28 0.000 .1516128 .2041209
_cons .002826 .0151598 0.19 0.852 -.0268888 .0325409


. test exipv agemarr4 rel weduc Wempow wipv polyg chcomm
exipv not found
r(111);

end of do-file

r(111);

Som
PS: I want to follow the guidelines for posting, however, I'm struggling with making the formatting readable. This was my reason for posting it as a word document initially (the formatting was perfect that way). Oh well...I hope it makes sense.

[Carlo Lazzaro]

Som:
unfortunately it is still the same situation reported in #2. Sorry for this.

[Som Nwegbu]

Thank you for trying Carlo. I appreciate the effort.

[Carlo Lazzaro]

Som:
the output can be improved but is readable now.
What if you replace -test- with -testparm-?

[Phil Bromiley]

You might try running mvreg,coefl after your mvreg. This will tell you exactly how Stata refers to the parameters. I don't use mvreg, but it is possible that you need both a variable and a dependent variable identifier to specify the right parameter to test.

[Clyde Schechter]

Sorry to come late to the party. Phil Bromiley has hit the nail on the head here. When you use factor-variable notation in your regression command (which is almost always a good idea!) you have to use the appropriate corresponding notation in your -test-/-testparm- commands. There is nothing about this that is specific to -mvreg-. Here's a simple example:

. sysuse auto, clear
(1978 Automobile Data)

. regress price mpg i.foreign i.rep78

      Source |       SS           df       MS      Number of obs   =        69
-------------+----------------------------------   F(6, 62)        =      3.94
       Model |   159087839         6  26514639.9   Prob > F        =    0.0021
    Residual |   417709119        62  6737243.86   R-squared       =    0.2758
-------------+----------------------------------   Adj R-squared   =    0.2057
       Total |   576796959        68  8482308.22   Root MSE        =    2595.6

------------------------------------------------------------------------------
       price |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         mpg |  -299.6068   63.34525    -4.73   0.000    -426.2322   -172.9815
             |
     foreign |
    Foreign  |   1102.334   901.7772     1.22   0.226    -700.2928    2904.961
             |
       rep78 |
          2  |   841.3622   2055.452     0.41   0.684    -3267.428    4950.153
          3  |   1285.116   1901.486     0.68   0.502    -2515.901    5086.132
          4  |   1155.571   1984.561     0.58   0.562     -2811.51    5122.652
          5  |   2353.179   2130.577     1.10   0.274    -1905.784    6612.142
             |
       _cons |   10856.24   2266.757     4.79   0.000      6325.06    15387.43
------------------------------------------------------------------------------

. 
. capture noisily test foreign
foreign not found

. 
. test 1.foreign

 ( 1)  1.foreign = 0

       F(  1,    62) =    1.49
            Prob > F =    0.2262

. 
. capture noisily testparm rep78
no such variables;
the specified varlist does not identify any testable coefficients

. 
. testparm i.rep78

 ( 1)  2.rep78 = 0
 ( 2)  3.rep78 = 0
 ( 3)  4.rep78 = 0
 ( 4)  5.rep78 = 0

       F(  4,    62) =    0.49
            Prob > F =    0.7465

After you do this enough, you start to remember what the relevant notation is. Until then, as Phil Bromiley suggest, run the command again with the -coeflegend- option and Stata will show you exactly what to call things.

[Som Nwegbu]

Thank you all for your input. I will try out all your suggestions and see where it takes me. Once again, thank you

[Som Nwegbu]

It worked! -testparm- worked. Thanks again