Help with time dummies

[Prathvajeeth Rajmohan]

Hi there new to the forum, I am investigating the effect of derivative use on firm value (with control variables added) on unbalanced panel data from 2015-2016

I have run 3 regression models, 1 simple OLS, and then the same model with industry dummies and then a firm-fixed effects model.


I was curious and tried my models again introducing a time dummy (1 for 2015, 0 for 2016), the time dummy were quite insignificant in each model. I performed a 2 tail test after each regression for the time dummy and one again it confirmed it wasn’t significant, so decided not to use them Is this correct?

Here are the various outputs:

OLS without time dummy:


ource | SS df MS Number of obs = 539
-------------+---------------------------------- F(11, 527) = 174.31
Model | 131.403067 11 11.9457334 Prob > F = 0.0000
Residual | 36.1158244 527 .068530976 R-squared = 0.7844
-------------+---------------------------------- Adj R-squared = 0.7799
Total | 167.518892 538 .311373405 Root MSE = .26178

-------------------------------------------------------------------------------------
firm value Coef. Std. Err. t P>|t| [95% Conf. Interval]
--------------------+----------------------------------------------------------------
lnassets | -.0175601 .0081555 -2.15 0.032 -.0335814 -.0015388
FXDerivatives10 | .0446019 .0267908 1.66 0.097 -.008028 .0972319
IRDerivatives10 | -.038192 .0283619 -1.35 0.179 -.0939083 .0175243
bookleverage_w1 | .3014549 .0633091 4.76 0.000 .1770857 .4258241
roa | .0501033 .0035524 14.10 0.000 .0431247 .0570818
z1 | .069638 .0044332 15.71 0.000 .060929 .078347
cratio_w1 | -.0920026 .0109629 -8.39 0.000 -.113539 -.0704662
rnd_rev | .0126128 .0022501 5.61 0.000 .0081925 .0170331
cash_to_totalassets | .2368669 .1432397 1.65 0.099 -.044524 .5182578
div_yield | -.0368795 .003593 -10.26 0.000 -.043938 -.0298211
roce_w1 | .0010044 .0004492 2.24 0.026 .0001219 .001887
_cons | .2019534 .0665961 3.03 0.003 .071127 .3327797

OLS with time dummy:

Source | SS df MS Number of obs = 539
-------------+---------------------------------- F(12, 526) = 159.49
Model | 131.403718 12 10.9503098 Prob > F = 0.0000
Residual | 36.1151742 526 .068660027 R-squared = 0.7844
-------------+---------------------------------- Adj R-squared = 0.7795
Total | 167.518892 538 .311373405 Root MSE = .26203

-------------------------------------------------------------------------------------
firm value | Coef. Std. Err. t P>|t| [95% Conf. Interval]
--------------------+----------------------------------------------------------------
lnassets | -.0175976 .0081723 -2.15 0.032 -.033652 -.0015433
FXDerivatives10 | .0446179 .0268166 1.66 0.097 -.0080628 .0972986
IRDerivatives10 | -.0381434 .028393 -1.34 0.180 -.093921 .0176342
bookleverage_w1 | .3015757 .0633808 4.76 0.000 .177065 .4260863
roa1 | .0501024 .0035557 14.09 0.000 .0431172 .0570875
z1 | .0696504 .0044393 15.69 0.000 .0609296 .0783713
cratio_w1 | -.0919885 .0109742 -8.38 0.000 -.1135471 -.0704299
rnd_rev | .0126132 .0022522 5.60 0.000 .0081887 .0170377
cash_to_totalassets | .236594 .1434019 1.65 0.100 -.0451168 .5183048
div_yield | -.0368644 .0035998 -10.24 0.000 -.0439361 -.0297927
roce_w1 | .0010059 .0004499 2.24 0.026 .000122 .0018898
year2015 | -.0022064 .0226742 -0.10 0.923 -.0467496 .0423367
_cons | .2031527 .0677885 3.00 0.003 .0699832 .3363221
-------------------------------------------------------------------------------------

Industry model without time dummy:

Source | SS df MS Number of obs = 539
-------------+---------------------------------- F(58, 480) = 43.84
Model | 140.917485 58 2.4296118 Prob > F = 0.0000
Residual | 26.6014073 480 .055419598 R-squared = 0.8412
-------------+---------------------------------- Adj R-squared = 0.8220
Total | 167.518892 538 .311373405 Root MSE = .23541

-------------------------------------------------------------------------------------
firm value | Coef. Std. Err. t P>|t| [95% Conf. Interval]
--------------------+----------------------------------------------------------------
lnassets | -.0152283 .0086275 -1.77 0.078 -.0321806 .001724
FXDerivatives10 | .0071845 .0285817 0.25 0.802 -.0489762 .0633452
IRDerivatives10 | -.0116745 .0278513 -0.42 0.675 -.0664002 .0430511
bookleverage_w1 | .175635 .0639462 2.75 0.006 .049986 .301284
roa . | .0476971 .0035201 13.55 0.000 .0407804 .0546137
z1 . | .063346 .0042326 14.97 0.000 .0550293 .0716627
cratio_w1 | -.0949652 .0115556 -8.22 0.000 -.117671 -.0722594
rnd_rev | .0065982 .002436 2.71 0.007 .0018116 .0113849
cash_to_totalassets | .2114229 .141328 1.50 0.135 -.0662752 .489121
div_yield | -.0318108 .0034352 -9.26 0.000 -.0385607 -.0250609
roce_w1 | .0007736 .0004437 1.74 0.082 -.0000983 .0016454
_cons | -.2267953 .1803996 -1.26 0.209 -.5812658 .1276753

industry model with time dummy:
Source | SS df MS Number of obs = 539
-------------+---------------------------------- F(59, 479) = 43.01
Model | 140.917686 59 2.38843536 Prob > F = 0.0000
Residual | 26.6012055 479 .055534876 R-squared = 0.8412
-------------+---------------------------------- Adj R-squared = 0.8216
Total | 167.518892 538 .311373405 Root MSE = .23566

-------------------------------------------------------------------------------------
firmvalue | Coef. Std. Err. t P>|t| [95% Conf. Interval]
--------------------+----------------------------------------------------------------
lnassets | -.0151998 .0086494 -1.76 0.079 -.0321952 .0017955
FXDerivatives10 | .0071648 .0286133 0.25 0.802 -.0490583 .0633878
IRDerivatives10 | -.011699 .0278832 -0.42 0.675 -.0664875 .0430896
bookleverage_w1 | .1755661 .0640229 2.74 0.006 .0497657 .3013665
roa | .0476972 .0035237 13.54 0.000 .0407733 .0546211
z1 . | .063337 .0042396 14.94 0.000 .0550064 .0716675
cratio_w1 | -.0949726 .0115682 -8.21 0.000 -.1177034 -.0722419
rnd_rev | .006597 .0024387 2.71 0.007 .0018052 .0113888
cash_to_totalassets | .211593 .1415031 1.50 0.135 -.0664505 .4896365
div_yield | -.0318182 .003441 -9.25 0.000 -.0385795 -.025057
roce_w1 | .0007726 .0004445 1.74 0.083 -.0001008 .0016459
year2015 | .0012352 .0204929 0.06 0.952 -.039032 .0415023
_cons | -.2275501 .1810209 -1.26 0.209 -.5832433 .1281431


firm fixed effects model without time dummy:


Fixed-effects (within) regression Number of obs = 539
Group variable: firmid Number of groups = 282

R-sq: Obs per group:
within = 0.3170 min = 1
between = 0.2210 avg = 1.9
overall = 0.2319 max = 2

F(11,246) = 10.38
corr(u_i, Xb) = -0.6013 Prob > F = 0.0000

-------------------------------------------------------------------------------------
firm value . | Coef. Std. Err. t P>|t| [95% Conf. Interval]
--------------------+----------------------------------------------------------------
lnassets | -.3381877 .0604746 -5.59 0.000 -.4573017 -.2190736
FXDerivatives10 | .0952812 .0743215 1.28 0.201 -.0511064 .2416688
IRDerivatives10 | -.1214566 .0744892 -1.63 0.104 -.2681747 .0252614
bookleverage_w1 | .1692325 .1216745 1.39 0.166 -.0704241 .4088892
roa . | .020826 .0056757 3.67 0.000 .0096468 .0320051
z1 | .007085 .0148235 0.48 0.633 -.0221122 .0362821
cratio_w1 | -.0695064 .0227655 -3.05 0.003 -.1143466 -.0246663
rnd_rev | -.0109449 .0082216 -1.33 0.184 -.0271386 .0052488
cash_to_totalassets | .347916 .2082939 1.67 0.096 -.062351 .758183
div_yield | -.0214717 .0032936 -6.52 0.000 -.0279589 -.0149845
roce_w1 | .0003598 .0004738 0.76 0.448 -.0005734 .0012931
_cons | 2.916311 .4469079 6.53 0.000 2.036057 3.796565
--------------------+----------------------------------------------------------------
sigma_u | .61284951
sigma_e | .12766146
rho | .95841236 (fraction of variance due to u_i)
-------------------------------------------------------------------------------------
F test that all u_i=0: F(281, 246) = 7.01 Prob > F = 0.0000

.
Firm fixed effects with time dummy:

Fixed-effects (within) regression Number of obs = 539
Group variable: firmid Number of groups = 282

R-sq: Obs per group:
within = 0.3234 min = 1
between = 0.2051 avg = 1.9
overall = 0.2155 max = 2

F(12,245) = 9.76
corr(u_i, Xb) = -0.6938 Prob > F = 0.0000

-------------------------------------------------------------------------------------
lntobinsq | Coef. Std. Err. t P>|t| [95% Conf. Interval]
--------------------+----------------------------------------------------------------
lnassets | -.4007886 .0731027 -5.48 0.000 -.5447786 -.2567987
FXDerivatives10 | .1024007 .074275 1.38 0.169 -.0438983 .2486997
IRDerivatives10 | -.1037169 .07521 -1.38 0.169 -.2518575 .0444237
bookleverage_w1 | .207787 .1239924 1.68 0.095 -.0364401 .4520141
roa . | .0210163 .0056622 3.71 0.000 .0098636 .0321691
z1 . | .009197 .0148501 0.62 0.536 -.0200532 .0384471
cratio_w1 | -.0691649 .0227068 -3.05 0.003 -.1138904 -.0244394
rnd_rev | -.0119345 .008226 -1.45 0.148 -.0281371 .0042681
cash_to_totalassets | .3159089 .2088175 1.51 0.132 -.0953977 .7272156
div_yield | -.0212811 .0032873 -6.47 0.000 -.0277562 -.0148061
roce_w1 | .0004484 .0004762 0.94 0.347 -.0004894 .0013863
year2015 | -.0223946 .0147759 -1.52 0.131 -.0514986 .0067093
_cons | 3.333809 .523984 6.36 0.000 2.301721 4.365897
--------------------+----------------------------------------------------------------
sigma_u | .68593601
sigma_e | .12732622
rho | .9666914 (fraction of variance due to u_i)
-------------------------------------------------------------------------------------
F test that all u_i=0: F(281, 245) = 7.06 Prob > F = 0.0000

.


.



Im presuming this is an indication that theres next to no time-fixed effects element as its only over a 2 year period.

Do keep or drop the time dummies is what im asking?

any help would be appreciated.
Thanks

[Carlo Lazzaro]

Prash:
welcome to the list.
Some remarks about your post:
- regression models specification should be driven by the literature of your research field;
- if you're dealing with panel data, OLS is rarely the best way to go and, even when it is, you should cluster your standard errors on -panelid-, as your observations are far from being independent;
- categorical variables and interactions benefit the most from using the -fvvarlist- notation; hence, no need to create dummies by hand;
- you were correct in reporting what Stata gave you back, but you forgot to put all the stuff between CODE delimiters (see the FAQ on that and other useful topics), which avoid annoying formatting issues;
- you can explicitly test whether -i.year- is worth keeping, as you can see from the following toy-example:

. use http://www.stata-press.com/data/r14/nlswork.dta
(National Longitudinal Survey.  Young Women 14-26 years of age in 1968)

. xtreg ln_wage tenure i.year, fe

Fixed-effects (within) regression               Number of obs     =     28,101
Group variable: idcode                          Number of groups  =      4,699

R-sq:                                           Obs per group:
     within  = 0.1328                                         min =          1
     between = 0.1830                                         avg =        6.0
     overall = 0.1428                                         max =         15

                                                F(15,23387)       =     238.70
corr(u_i, Xb)  = 0.1302                         Prob > F          =     0.0000

------------------------------------------------------------------------------
     ln_wage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
      tenure |   .0210664   .0008028    26.24   0.000     .0194928      .02264
             |
        year |
         69  |   .0834009    .012716     6.56   0.000     .0584767    .1083252
         70  |   .0581181   .0118878     4.89   0.000     .0348173     .081419
         71  |   .1039541   .0117593     8.84   0.000     .0809051     .127003
         72  |    .111102   .0121416     9.15   0.000     .0873036    .1349004
         73  |   .1190714   .0117941    10.10   0.000     .0959542    .1421885
         75  |    .125436   .0117121    10.71   0.000     .1024795    .1483926
         77  |   .1726586   .0117994    14.63   0.000      .149531    .1957863
         78  |    .198183   .0120938    16.39   0.000     .1744784    .2218877
         80  |   .2041747    .012265    16.65   0.000     .1801345    .2282149
         82  |   .2078031   .0121494    17.10   0.000     .1839895    .2316166
         83  |   .2198642   .0124184    17.70   0.000     .1955233    .2442052
         85  |   .2606739   .0124265    20.98   0.000     .2363171    .2850307
         87  |    .266248   .0125421    21.23   0.000     .2416646    .2908314
         88  |   .3096376   .0127421    24.30   0.000     .2846622     .334613
             |
       _cons |   1.438391   .0093181   154.37   0.000     1.420127    1.456655
-------------+----------------------------------------------------------------
     sigma_u |  .39153681
     sigma_e |   .2976287
         rho |  .63377952   (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0: F(4698, 23387) = 8.08                 Prob > F = 0.0000

. testparm i.year

 ( 1)  69.year = 0
 ( 2)  70.year = 0
 ( 3)  71.year = 0
 ( 4)  72.year = 0
 ( 5)  73.year = 0
 ( 6)  75.year = 0
 ( 7)  77.year = 0
 ( 8)  78.year = 0
 ( 9)  80.year = 0
 (10)  82.year = 0
 (11)  83.year = 0
 (12)  85.year = 0
 (13)  87.year = 0
 (14)  88.year = 0

       F( 14, 23387) =   68.47
            Prob > F =    0.0000

.

[Prathvajeeth Rajmohan]

Hi Carlo, thanks so much for the reply, I did infact look into the testparm i.year command yesterday but i was not sure how to implement it with my regression.

The panel data actually stems from 2013 to 2016, (for firms without most recent data we used 2013-2014, 2014-2015, but there were very few only about 5) but as my the focus of my investigation is 2015-2016, I used the command:


xtreg lntobinsq lnassets FXDerivatives10 IRDerivatives10 bookleverage_w1 roa_w1 zscore_w1 cratio_w1 rnd_rev cash_to_totalassets div_yield roce_w1 if inlist(year,2015,2016), fe

  
xtreg lntobinsq lnassets FXDerivatives10 IRDerivatives10  bookleverage_w1 roa_w1 zscore_w1 cratio_w1 rnd_rev cash_to_totalassets div_yield roce_w1 if inlist(year,2015,2016), fe

Fixed-effects (within) regression               Number of obs     =        539
Group variable: firmid                          Number of groups  =        282

R-sq:                                           Obs per group:
     within  = 0.3170                                         min =          1
     between = 0.2210                                         avg =        1.9
     overall = 0.2319                                         max =          2

                                                F(11,246)         =      10.38
corr(u_i, Xb)  = -0.6013                        Prob > F          =     0.0000

-------------------------------------------------------------------------------------
          lntobinsq |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
--------------------+----------------------------------------------------------------
           lnassets |  -.3381877   .0604746    -5.59   0.000    -.4573017   -.2190736
    FXDerivatives10 |   .0952812   .0743215     1.28   0.201    -.0511064    .2416688
    IRDerivatives10 |  -.1214566   .0744892    -1.63   0.104    -.2681747    .0252614
    bookleverage_w1 |   .1692325   .1216745     1.39   0.166    -.0704241    .4088892
             roa_w1 |    .020826   .0056757     3.67   0.000     .0096468    .0320051
          zscore_w1 |    .007085   .0148235     0.48   0.633    -.0221122    .0362821
          cratio_w1 |  -.0695064   .0227655    -3.05   0.003    -.1143466   -.0246663
            rnd_rev |  -.0109449   .0082216    -1.33   0.184    -.0271386    .0052488
cash_to_totalassets |    .347916   .2082939     1.67   0.096     -.062351     .758183
          div_yield |  -.0214717   .0032936    -6.52   0.000    -.0279589   -.0149845
            roce_w1 |   .0003598   .0004738     0.76   0.448    -.0005734    .0012931
              _cons |   2.916311   .4469079     6.53   0.000     2.036057    3.796565
--------------------+----------------------------------------------------------------
            sigma_u |  .61284951
            sigma_e |  .12766146
                rho |  .95841236   (fraction of variance due to u_i)
-------------------------------------------------------------------------------------
F test that all u_i=0: F(281, 246) = 7.01                    Prob > F = 0.0000

.

How exactly could use the testpharm command on this to test the 2015 and 2016 dummies? Thanks

[Carlo Lazzaro]

Prash:
assuming that your data are already in -long- format (as they should be for carrying out a panel data regression), you should simply include among your set of predictors:

i.year

.
Elaborating a bit on my previous code:

. use "http://www.stata-press.com/data/r14/nlswork.dta", clear
(National Longitudinal Survey.  Young Women 14-26 years of age in 1968)

. xtreg ln_wage tenure i.year if year!=88, fe

Fixed-effects (within) regression               Number of obs     =     25,859
Group variable: idcode                          Number of groups  =      4,588

R-sq:                                           Obs per group:
     within  = 0.1297                                         min =          1
     between = 0.1750                                         avg =        5.6
     overall = 0.1374                                         max =         14

                                                F(14,21257)       =     226.19
corr(u_i, Xb)  = 0.1301                         Prob > F          =     0.0000

------------------------------------------------------------------------------
     ln_wage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
      tenure |   .0217211   .0008557    25.38   0.000     .0200439    .0233984
             |
        year |
         69  |   .0834391   .0122015     6.84   0.000     .0595233     .107355
         70  |   .0600081   .0114124     5.26   0.000     .0376389    .0823772
         71  |    .106002   .0113001     9.38   0.000     .0838529     .128151
         72  |   .1144726   .0116731     9.81   0.000     .0915924    .1373528
         73  |   .1228439    .011348    10.83   0.000     .1006011    .1450868
         75  |   .1292465   .0112872    11.45   0.000     .1071227    .1513702
         77  |   .1777827     .01139    15.61   0.000     .1554574    .2001079
         78  |   .2042005   .0116969    17.46   0.000     .1812737    .2271272
         80  |   .2114531   .0118719    17.81   0.000     .1881832     .234723
         82  |   .2155586      .0118    18.27   0.000     .1924297    .2386875
         83  |   .2286295    .012103    18.89   0.000     .2049067    .2523523
         85  |   .2686142   .0121517    22.11   0.000      .244796    .2924324
         87  |   .2749306   .0123183    22.32   0.000     .2507858    .2990755
             |
       _cons |   1.430543   .0089414   159.99   0.000     1.413017    1.448069
-------------+----------------------------------------------------------------
     sigma_u |  .38335797
     sigma_e |  .28499418
         rho |  .64405339   (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0: F(4587, 21257) = 7.98                 Prob > F = 0.0000

. testparm i.year

 ( 1)  69.year = 0
 ( 2)  70.year = 0
 ( 3)  71.year = 0
 ( 4)  72.year = 0
 ( 5)  73.year = 0
 ( 6)  75.year = 0
 ( 7)  77.year = 0
 ( 8)  78.year = 0
 ( 9)  80.year = 0
 (10)  82.year = 0
 (11)  83.year = 0
 (12)  85.year = 0
 (13)  87.year = 0

       F( 13, 21257) =   66.17
            Prob > F =    0.0000

.

[Prathvajeeth Rajmohan]

Hi Carlo, thanks so much:

I tried but I got this:

. xtreg lntobinsq lnassets FXDerivatives10 IRDerivatives10  bookleverage_w1 roa_w1 zscore_w1 cratio_w1 rnd_rev cash_to_totalassets div_yield roce_w1 i.year if year!=2015 & 2016, fe

note: lnassets omitted because of collinearity
note: FXDerivatives10 omitted because of collinearity
note: IRDerivatives10 omitted because of collinearity
note: bookleverage_w1 omitted because of collinearity
note: roa_w1 omitted because of collinearity
note: zscore_w1 omitted because of collinearity
note: cratio_w1 omitted because of collinearity
note: rnd_rev omitted because of collinearity
note: cash_to_totalassets omitted because of collinearity
note: div_yield omitted because of collinearity
note: roce_w1 omitted because of collinearity
note: 2016.year omitted because of collinearity

Fixed-effects (within) regression               Number of obs     =        268
Group variable: firmid                          Number of groups  =        268

R-sq:                                           Obs per group:
     within  =      .                                         min =          1
     between =      .                                         avg =        1.0
     overall =      .                                         max =          1

                                                F(0,0)            =       0.00
corr(u_i, Xb)  =      .                         Prob > F          =          .

-------------------------------------------------------------------------------------
          lntobinsq |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
--------------------+----------------------------------------------------------------
           lnassets |          0  (omitted)
    FXDerivatives10 |          0  (omitted)
    IRDerivatives10 |          0  (omitted)
    bookleverage_w1 |          0  (omitted)
             roa_w1 |          0  (omitted)
          zscore_w1 |          0  (omitted)
          cratio_w1 |          0  (omitted)
            rnd_rev |          0  (omitted)
cash_to_totalassets |          0  (omitted)
          div_yield |          0  (omitted)
            roce_w1 |          0  (omitted)
                    |
               year |
              2016  |          0  (omitted)
                    |
              _cons |   .5625006          .        .       .            .           .
--------------------+----------------------------------------------------------------
            sigma_u |  .53287457
            sigma_e |          .
                rho |          .   (fraction of variance due to u_i)
-------------------------------------------------------------------------------------
F test that all u_i=0: F(267, 0) = .                         Prob > F =      .

. 
end of do-file

im guessing my initial command is wrong?:

 .  xtreg lntobinsq lnassets FXDerivatives10 IRDerivatives10  bookleverage_w1 roa_w1 zscore_w1 cratio_w1 rnd_rev cash_to_totalassets div_yield roce_w1 i.year if year!=2015 & 2016, fe

what exactly should it be? thanks so much for the reply.

[Carlo Lazzaro]

Prash:
I overlooked -inlist- in your previous code.
Try:

xtreg lntobinsq lnassets FXDerivatives10 IRDerivatives10  bookleverage_w1 roa_w1 zscore_w1 cratio_w1 rnd_rev cash_to_totalassets div_yield roce_w1 i.year if inlist(year,2015,2016), fe

and then test -i.year- via -parmtest-.

[Prathvajeeth Rajmohan]

Fixed-effects (within) regression               Number of obs     =        539
Group variable: firmid                          Number of groups  =        282

R-sq:                                           Obs per group:
     within  = 0.3234                                         min =          1
     between = 0.2051                                         avg =        1.9
     overall = 0.2155                                         max =          2

                                                F(12,245)         =       9.76
corr(u_i, Xb)  = -0.6938                        Prob > F          =     0.0000

-------------------------------------------------------------------------------------
          lntobinsq |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
--------------------+----------------------------------------------------------------
           lnassets |  -.4007886   .0731027    -5.48   0.000    -.5447786   -.2567987
    FXDerivatives10 |   .1024007    .074275     1.38   0.169    -.0438983    .2486997
    IRDerivatives10 |  -.1037169     .07521    -1.38   0.169    -.2518575    .0444237
    bookleverage_w1 |    .207787   .1239924     1.68   0.095    -.0364401    .4520141
             roa_w1 |   .0210163   .0056622     3.71   0.000     .0098636    .0321691
          zscore_w1 |    .009197   .0148501     0.62   0.536    -.0200532    .0384471
          cratio_w1 |  -.0691649   .0227068    -3.05   0.003    -.1138904   -.0244394
            rnd_rev |  -.0119345    .008226    -1.45   0.148    -.0281371    .0042681
cash_to_totalassets |   .3159089   .2088175     1.51   0.132    -.0953977    .7272156
          div_yield |  -.0212811   .0032873    -6.47   0.000    -.0277562   -.0148061
            roce_w1 |   .0004484   .0004762     0.94   0.347    -.0004894    .0013863
                    |
               year |
              2016  |   .0223946   .0147759     1.52   0.131    -.0067093    .0514986
                    |
              _cons |   3.311415   .5163692     6.41   0.000     2.294325    4.328504
--------------------+----------------------------------------------------------------
            sigma_u |  .68593601
            sigma_e |  .12732622
                rho |   .9666914   (fraction of variance due to u_i)
-------------------------------------------------------------------------------------
F test that all u_i=0: F(281, 245) = 7.06                    Prob > F = 0.0000

. 
end of do-file

. testparm i.year

 ( 1)  2016.year = 0

       F(  1,   245) =    2.30
            Prob > F =    0.1309

Hi think this have worked,, could I just clarify though that 2016.year is indeed the year dummy that takes 1 if 2016 and 0 if not ie 2015,

And there is only 1 dummy as there are 2 time periods in total, and its right that its only showing the 2016 dummy? Thanks

[Carlo Lazzaro]

Prash:
your interpretation of the dummy variables is correct.
Besides, it is right that only 2016 is shown under -testparm-.
You can use the -baselevels- option to get a clearer insight on how Stata works with categorical variables:

use "http://www.stata-press.com/data/r14/nlswork.dta", clear
(National Longitudinal Survey.  Young Women 14-26 years of age in 1968)
. xtreg ln_wage tenure i.year if inlist(year, 68,69), fe baselevels

Fixed-effects (within) regression               Number of obs     =      2,494
Group variable: idcode                          Number of groups  =      1,712

R-sq:                                           Obs per group:
     within  = 0.1221                                         min =          1
     between = 0.0015                                         avg =        1.5
     overall = 0.0110                                         max =          2

                                                F(2,780)          =      54.25
corr(u_i, Xb)  = -0.0327                        Prob > F          =     0.0000

------------------------------------------------------------------------------
     ln_wage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
      tenure |  -.0027612   .0147746    -0.19   0.852    -.0317639    .0262415
             |
        year |
         68  |          0  (base)
         69  |   .1056817   .0125823     8.40   0.000     .0809826    .1303809
             |
       _cons |   1.437883    .009534   150.82   0.000     1.419167    1.456598
-------------+----------------------------------------------------------------
     sigma_u |  .38357724
     sigma_e |  .19795551
         rho |  .78967997   (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0: F(1711, 780) = 4.85                   Prob > F = 0.0000

. testparm i.year

 ( 1)  69.year = 0

       F(  1,   780) =   70.55
            Prob > F =    0.0000

[Prathvajeeth Rajmohan]

He carlo Thanks so much for all the help, I just wanted to confirm something though: this code you put

xtreg lntobinsq lnassets FXDerivatives10 IRDerivatives10  bookleverage_w1 roa_w1 zscore_w1 cratio_w1 rnd_rev cash_to_totalassets div_yield roce_w1 i.year if inlist(year,2015,2016), fe

That is the fixed effects model with the dummy for 2016 included right? So if I did find that the dummy as insignificant, I couldn't use that regression I presume, I'd have to the take the dummy out i.e remove the i.year part of the code I presume. thanks so much.

[Carlo Lazzaro]

Prash:
yes, you're right.