r(2000) error in Newey-West

[Guest]

Dear all,

I have monthly data on stock market and when I tried to use Newey-West standard errors to deal with heteroskedasticity and autocorrelation, Stata says that there is no observation. Below is my -dataex- :

* Example generated by -dataex-. To install: ssc install dataex
clear
input int date float(csad r_mt abs_r_mt)
15341         .          .         .
15372  10.40015 -21.771555 21.771555
15400 3.6831214  1.3696393 1.3696393
15431   5.40642   6.454342  6.454342
15461  4.572629 -1.0483736 1.0483736
15492  3.924419 -12.194602 12.194602
15522 4.0851216  15.245831 15.245831
15553  4.421038   3.213805  3.213805
15584  1.545293  -.3501535  .3501535
15614 2.0632555 -4.6421685 4.6421685
15645  3.666877  -14.84067  14.84067
15675 4.5075574 -4.4080067 4.4080067
15706 1.8428906 -2.1559913 2.1559913
15737   2.49485  11.278244 11.278244
15765 2.1604996 -1.2514616 1.2514616
15796 4.3232718  -1.257523  1.257523
15826 10.606026   3.962764  3.962764
15857  5.112213   6.413789  6.413789
15887  4.484928  -4.856054  4.856054
15918  6.263611   6.968433  6.968433
15949 2.9614744   -.802722   .802722
15979  3.076989  -.8465761  .8465761
16010 10.489506   19.19976  19.19976
16040 3.4005265 -1.0016072 1.0016072
16071  8.629517  -.3082933  .3082933
16102  4.420031   7.663479  7.663479
16131   7.91593  1.8529012 1.8529012
16162  4.938119     1.0648    1.0648
16192   4.95072 -14.607905 14.607905
16223 3.8892744  3.9174936 3.9174936
16253  5.702363  -5.584903  5.584903
16284  7.320863  -5.576176  5.576176
16315  6.825109 -10.216467 10.216467
16345  3.911943  10.581155 10.581155
16376  8.563342  -8.825836  8.825836
16406 4.0248747    7.06366   7.06366
16437  6.767444  -8.656428  8.656428
16468  9.667854   5.605936  5.605936
16496 4.4664264   9.692858  9.692858
16527 12.659364   2.459548  2.459548
16557   11.2451   -4.35966   4.35966
16588  7.937766  -11.16009  11.16009
16618  5.769467  -4.593168  4.593168
16649  8.396846   2.259447  2.259447
16680  9.871736  2.2887776 2.2887776
16710  6.986581  -.5051034  .5051034
16741  7.922635 -16.813925 16.813925
16771  3.609957   2.732373  2.732373
16802  5.349097   .7332054  .7332054
16833  7.527323   23.25859  23.25859
16861  6.718209  3.0368414 3.0368414
16892  7.630779    4.88974   4.88974
16922 10.340603   5.886937  5.886937
16953  9.688768   8.262988  8.262988
16983  5.447178 -2.6733925 2.6733925
17014  6.039441  -5.767948  5.767948
17045  5.145508  2.8006885 2.8006885
17075   14.2246  10.567738 10.567738
17106  9.340332   5.390509  5.390509
17136  8.937711  10.640285 10.640285
17167  12.09225  13.240386 13.240386
17198  13.75918  4.6114182 4.6114182
17226  7.096007   7.630084  7.630084
17257  7.987866   7.694463  7.694463
17287 11.686085  16.659527 16.659527
17318 10.900064   4.312224  4.312224
17348  17.43714  2.0001624 2.0001624
17379  7.945005  13.660383 13.660383
17410  8.063833 -1.5955248 1.5955248
17440  5.245726  3.9520586 3.9520586
17471  8.522331   .4120224  .4120224
17501  5.714562  -10.72098  10.72098
17532   5.00455   .7190944  .7190944
17563  7.142439  -10.26564  10.26564
17592  6.609317 -1.1376902 1.1376902
17623   11.2239  -16.59991  16.59991
17653  8.833878   6.459142  6.459142
17684  6.001316  -4.918726  4.918726
17714  8.055031 -15.197256 15.197256
17745  8.108354  -2.220311  2.220311
17776  8.099585 -18.786123 18.786123
17806  10.02093  -19.74054  19.74054
17837  13.65648  -32.34998  32.34998
17867  8.914493   14.30076  14.30076
17898   6.74604   4.287829  4.287829
17929  5.719338   4.822899  4.822899
17957  6.543387   6.488205  6.488205
17988  5.720366  15.008144 15.008144
18018  6.967344    3.38667   3.38667
18049  7.954954   19.29539  19.29539
18079  6.887875  12.942645 12.942645
18110  6.234223  10.758305 10.758305
18141  5.344579  -17.07722  17.07722
18171 4.5722775   6.080737  6.080737
18202  5.578828   8.842843  8.842843
18232  9.408226   12.99844  12.99844
18263 4.6079955  .06648097 .06648097
18294  5.668927   -7.62164   7.62164
18322  3.139144   4.595733  4.595733
18353 4.2208114   4.677813  4.677813
end
format %tm date

Here are the problematic results:

. tsset date, monthly
        time variable:  date, 3238m6 to 3512m5, but with gaps
                delta:  1 month

. newey csad c.abs_r_mt##c.abs_r_mt, lag(1) force
no observations
r(2000);

.

Why is there 'no observations'? Below is my 'normal' regression.

.  reg csad c.abs_r_mt##c.abs_r_mt

      Source |       SS           df       MS      Number of obs   =       108
-------------+----------------------------------   F(2, 105)       =      6.12
       Model |  93.9271731         2  46.9635866   Prob > F        =    0.0031
    Residual |   805.43128       105  7.67077409   R-squared       =    0.1044
-------------+----------------------------------   Adj R-squared   =    0.0874
       Total |  899.358453       107  8.40521918   Root MSE        =    2.7696

------------------------------------------------------------------------------
        csad |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
    abs_r_mt |    .043472   .1171705     0.37   0.711    -.1888554    .2757994
             |
  c.abs_r_mt#|
  c.abs_r_mt |   .0046852   .0049204     0.95   0.343    -.0050709    .0144414
             |
       _cons |   6.077043   .5529866    10.99   0.000     4.980573    7.173513
------------------------------------------------------------------------------

[William Lisowski]

You do not understand how Stata datetime variables work.

Here are the first five dates in your data, with two different formats.

. format %tm date

. list date in 1/5

     +---------+
     |    date |
     |---------|
  1. |  3238m6 |
  2. |  3241m1 |
  3. |  3243m5 |
  4. | 3245m12 |
  5. |  3248m6 |
     +---------+

. format %td date

. list date in 1/5

     +-----------+
     |      date |
     |-----------|
  1. | 01jan2002 |
  2. | 01feb2002 |
  3. | 01mar2002 |
  4. | 01apr2002 |
  5. | 01may2002 |
     +-----------+

You have Stata daily dates, and you attempted to make them monthly dates by changing the format. That is not correct, as a simple inspection shows.

You will want to follow the instructions for using your Stata Internal Format (SIF) daily date variable to create a new SIF monthly date variable following the guidance in help datetime, which is without a doubt the most visited documentation on my system, with the second-most-visited being Chapter 24 (Working with dates and times) of the Stata User's Guide PDF available from the PDF Documentation item on Stata's Help menu. Before working with dates and times, any Stata user should read the very detailed Chapter 24 thoroughly. After that, the help datetime documentation will usually be enough to point the way. Some people may be able to remember everything without have to continually refer to the documentation, but I for one am not such a person

[Nick Cox]

Same points made within https://www.statalist.org/forums/for...tions-on-r-198

Please try to run just one thread at any time when the issues are so similar. .