[Daouia Moulay]

HELLO EVERYONE,
I run the PMG estimators for the quadratic model and the results show that positive and negative coeffiencients for the FD and its square term. in order to confirm this no linear relation i have to conduct UTEST , i installed the package of UTEST, but i could nt get the results of UTEST, what should i do ....is it wrong when i did PMG after that directly i proeeded with UTEST.... thank uou in advance.

[Daouia Moulay]

PLEASE Dear Clyde Schechter coud you help in this issue.tq

[Clyde Schechter]

What does PMG stand for? It's not a Stata command. If it's a user written program, what does it do and where does it come from?

You don't need to use a special package to look for non-linearity in a regression model. But you don't show any code or results, or error messages, and since I cannot read your mind, I can't advise you what went wrong or what to do.

Please post back with more, clearer information.

[Aye Aye Khaine]

Hello,
I did the U test. How shall I interpret? I read one of the above post about interpretation. I am just not sure I got it. So, I would like to ask about how to interpret. P value is insignificant. Does that mean that there is no shape? my model is linear without the squared term?



. utest agemo sq_age

Specification: f(x)=x^2
Extreme point: 42.57625

Test:
H1: U shape
vs. H0: Monotone or Inverse U shape

-------------------------------------------------
| Lower bound Upper bound
-----------------+-------------------------------
Interval | .00274 64.56667
Slope | -.0673668 .0347968
t-value | -15.02906 8.016549
P>|t| | 1.65e-50 6.40e-16
-------------------------------------------------

Overall test of presence of a U shape:
t-value = 8.02
P>|t| = 6.40e-16




Thanks so much

[Elzo Martijn]

Hello everyone,

I'm also trying to run the utest. However I get an error.

When I type "utest var1 var2" I get an error that says "var1 not found". However, this variable is definitely in my dataset and is not mispelled. Does anyone know what could be the problem?

[Clyde Schechter]

On the information you gave, it's anybody's guess.

For a helpful response, please post back showing all of the code and Stata output running from the original regression through the error message, copied from the Results window or your log file and pasted here into the Forum with no editing whatsoever. Also show example data using the -dataex- command. If you are running version 18, 17, 16 or a fully updated version 15.1 or 14.2, -dataex- is already part of your official Stata installation. If not, run -ssc install dataex- to get it. Either way, run -help dataex- to read the simple instructions for using it. -dataex- will save you time; it is easier and quicker than typing out tables. It includes complete information about aspects of the data that are often critical to answering your question but cannot be seen from tabular displays or screenshots. It also makes it possible for those who want to help you to create a faithful representation of your example to try out their code, which in turn makes it more likely that their answer will actually work in your data.

[Elzo Martijn]

Here is my data example:

* Example generated by -dataex-. For more info, type help dataex
clear
input float(distinctiveness ROA) byte country_group double fyear
  2.41941  -.05770894 1 2009
2.3605218 -.018773915 1 2010
1.8049095   -.0829839 1 2011
 4.361073  -.07979583 1 2012
  4.58747  -.04337953 1 2013
 4.387285   .06584268 1 2014
2.1018775    .1571827 1 2015
2.6896715   .05219019 1 2016
2.4569645   .03733754 1 2017
4.2377815   .02330802 1 2018
 3.631691   .02810234 1 2019
 4.561469  -.14328796 1 2020
 5.269302 -.029984804 1 2021
 4.944445 .0019624205 1 2022
        .   .11505918 1 2008
1.1607926   .10961862 1 2009
1.2873703   .07780013 1 2010
 1.293666   .07844546 1 2011
2.2510424    .0886878 1 2012
 3.596341   .05997253 1 2013
 3.781453   .05533616 1 2014
2.8537426   .10723204 1 2015
 2.498541  .026582615 1 2016
1.9335445  .006255738 1 2017
 1.209509   .03525226 1 2018
 1.462794   .05431084 1 2019
1.5537483   .06195898 1 2020
1.5147917   .09403425 1 2021
2.2141452   .09313791 1 2022
        .   .02396594 1 2008
2.8647904  -.12512152 1 2009
 2.437494   .09112713 1 2010
2.8047554   .11804293 1 2011
3.6549964   .00476757 1 2012
  4.19457    .6780942 1 2013
 3.805459   .07515766 1 2014
 3.597964   .07576048 1 2015
 4.509276  .063060716 1 2016
 5.148574   .20779055 1 2017
4.2189064   .08502997 1 2018
 3.073843   .15126067 1 2019
  2.80993   .12798376 1 2020
2.3431401    .1824762 1 2021
 3.162419   .10374164 1 2022
        .  .021654576 1 2008
 1.475866  .020374553 1 2009
1.1443872   .06038087 1 2010
1.2772894  -.11300465 1 2011
 .9592249   .05915627 1 2012
 1.364503  -.08197148 1 2013
 1.253932  .012129163 1 2014
1.1786025  .003678339 1 2015
 .7459515  .022344554 1 2016
 .7421259  .031006785 1 2017
  .923447   -.0416029 1 2018
1.2833335   .05383074 1 2019
 .8571225   .05321061 1 2020
2.3179297   .05330529 1 2021
2.5607474   .02852754 1 2022
        .   .07867005 1 2008
 1.404336   .05979891 1 2009
1.2621715   .05344399 1 2010
1.1667018   .05192424 1 2011
 1.378791   .06991135 1 2012
 1.393883   .08636513 1 2013
1.5630575   .09326527 1 2014
1.9288274   .09668262 1 2015
 1.447549   .08881543 1 2016
1.5450603   .02786805 1 2017
2.0083358   .11709622 1 2018
2.2620535   .10468822 1 2019
1.7103368   .07399436 1 2020
2.1154757   .08596246 1 2021
2.1337907   .07974307 1 2022
        .  -.11239897 1 2008
 1.759753  -.06418742 1 2009
1.9564258  -.02091696 1 2010
1.8765433  -.08330154 1 2011
2.1687102  -.08278885 1 2012
 2.401895  -.05958145 1 2013
2.3786397   .04982504 1 2014
1.7507926   .16098654 1 2015
 1.992114   .04787234 1 2016
1.7040844  .032026928 1 2017
3.4150546   .02339231 1 2018
2.7921176  .027430797 1 2019
3.5662324  -.12208337 1 2020
 4.388973  -.02497716 1 2021
4.0692444  .004806325 1 2022
        .   .02140806 1 2008
        .           . 1 2009
        .           . 1 2010
        .           . 1 2011
        .           . 1 2012
 1.720598  .034940504 1 2013
 1.893477  .036988616 1 2014
 1.639792  .032031715 1 2015
1.9246798   .03403548 1 2016
        .           . 1 2017
        .           . 1 2018
end

Here is my panel data regression:

. xtreg ROA L.distinctiveness L.revt L.gsector L.years_represented L.i.fyear if country_group == 1, fe vce (robust)
note: L.gsector omitted because of collinearity.
note: L.years_represented omitted because of collinearity.

Fixed-effects (within) regression               Number of obs     =      2,815
Group variable: gvkey                           Number of groups  =        270

R-squared:                                      Obs per group:
     Within  = 0.0310                                         min =          1
     Between = 0.0243                                         avg =       10.4
     Overall = 0.0139                                         max =         15

                                                F(16,269)         =       5.65
corr(u_i, Xb) = -0.0608                         Prob > F          =     0.0000

                                     (Std. err. adjusted for 270 clusters in gvkey)
-----------------------------------------------------------------------------------
                  |               Robust
              ROA | Coefficient  std. err.      t    P>|t|     [95% conf. interval]
------------------+----------------------------------------------------------------
  distinctiveness |
              L1. |  -.0015056   .0030078    -0.50   0.617    -.0074273    .0044161
                  |
             revt |
              L1. |   6.90e-08   1.41e-07     0.49   0.626    -2.09e-07    3.47e-07
                  |
          gsector |
              L1. |          0  (omitted)
                  |
years_represented |
              L1. |          0  (omitted)
                  |
          L.fyear |
            2008  |   .0421653   .0332719     1.27   0.206    -.0233412    .1076717
            2009  |   .0285579   .0220759     1.29   0.197    -.0149055    .0720213
            2010  |   .0310205   .0222719     1.39   0.165    -.0128289    .0748699
            2011  |   .0234227   .0214147     1.09   0.275     -.018739    .0655844
            2012  |    .017083   .0221533     0.77   0.441    -.0265328    .0606989
            2013  |   .0072515   .0223574     0.32   0.746    -.0367662    .0512691
            2014  |   .0044142   .0222827     0.20   0.843    -.0394565     .048285
            2015  |   .0134424   .0219327     0.61   0.540    -.0297392     .056624
            2016  |   .0204061   .0220255     0.93   0.355    -.0229582    .0637704
            2017  |   .0225698   .0219171     1.03   0.304     -.020581    .0657207
            2018  |   .0098817   .0220969     0.45   0.655    -.0336232    .0533866
            2019  |    -.00988    .022773    -0.43   0.665    -.0547159    .0349559
            2020  |     .02179   .0223877     0.97   0.331    -.0222873    .0658674
            2021  |   .0199841   .0229793     0.87   0.385     -.025258    .0652261
                  |
            _cons |   .0297377   .0261264     1.14   0.256    -.0217006    .0811759
------------------+----------------------------------------------------------------
          sigma_u |  .05104149
          sigma_e |  .06464462
              rho |  .38401718   (fraction of variance due to u_i)
-----------------------------------------------------------------------------------

. utest distinctiveness ROA
end

At the end you see me trying to do the utest, but it gives me an error "distinctiveness not found". Furthermore, the word 'utest' doesn't seem to get blue indicating that STATA sees it as a command.

[Clyde Schechter]

You are using -utest- incorrectly. The two variables you specify in -utest- have to be the linear and quadratic term variables on the right hand side of the regression. ROA cannot be there. Moreover, as your regression did not include a quadratic term, you can't even use -utest- at all on this.

Added:

Furthermore, the word 'utest' doesn't seem to get blue indicating that STATA sees it as a command.

-utest- is not an official Stata command; it is user-written. The syntax highlighting only applies to official Stata commands.