diff and diff collineratiy

[burhan magden]

gen post_treat=post*treat

. reg lwage post treat post_treat age age2 educ marr i.year i.nuts2[pw=faktor] if sex==1&occ==3,robu
> st
(sum of wgt is 7.4033e+03)
note: post_treat omitted because of collinearity
note: 2017.year omitted because of collinearity

Linear regression Number of obs = 44,921
F(37, 44883) = 539.86
Prob > F = 0.0000
R-squared = 0.3403
Root MSE = .44571

------------------------------------------------------------------------------
| Robust
lwage | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
post | .4238119 .0102254 41.45 0.000 .40377 .4438538
treat | -.0369555 .0154131 -2.40 0.017 -.0671655 -.0067455
post_treat | 0 (omitted)
age | .0847557 .0018631 45.49 0.000 .081104 .0884075
age2 | -.0008307 .0000238 -34.93 0.000 -.0008773 -.0007841
educ | .0358419 .0005541 64.68 0.000 .0347558 .0369279
marr | .0871471 .0068072 12.80 0.000 .0738049 .1004894
|
year |
2010 | .0387298 .0101107 3.83 0.000 .0189127 .058547
2011 | .014438 .0098914 1.46 0.144 -.0049493 .0338253
2012 | .083935 .0098663 8.51 0.000 .0645969 .1032732
2014 | -.0232724 .0101649 -2.29 0.022 -.0431957 -.0033491
2015 | -.0296179 .0090395 -3.28 0.001 -.0473356 -.0119003
2016 | .0329562 .0087692 3.76 0.000 .0157685 .0501439
2017 | 0 (omitted)
|
nuts2 |
2 | -.1027361 .0138094 -7.44 0.000 -.1298026 -.0756695
3 | -.1496527 .0138345 -10.82 0.000 -.1767686 -.1225368
4 | -.1004428 .0106298 -9.45 0.000 -.1212774 -.0796082
5 | -.1525408 .014484 -10.53 0.000 -.1809296 -.124152
6 | -.0892759 .0126839 -7.04 0.000 -.1141367 -.0644152
7 | -.0956869 .0108507 -8.82 0.000 -.1169544 -.0744195
8 | -.077937 .0113978 -6.84 0.000 -.1002768 -.0555972
9 | .0466174 .0087169 5.35 0.000 .0295322 .0637026
10 | -.1937992 .0117453 -16.50 0.000 -.2168201 -.1707783
11 | -.0710223 .0134255 -5.29 0.000 -.0973366 -.0447081
12 | -.1526589 .0126282 -12.09 0.000 -.1774104 -.1279075
13 | -.1176439 .0166561 -7.06 0.000 -.1502902 -.0849976
14 | -.0231412 .0130792 -1.77 0.077 -.0487766 .0024942
15 | -.1461342 .0168414 -8.68 0.000 -.1791437 -.1131247
16 | -.058647 .0209157 -2.80 0.005 -.0996422 -.0176518
17 | .060174 .0139931 4.30 0.000 .0327473 .0876007
18 | -.0617659 .0149964 -4.12 0.000 -.0911591 -.0323728
19 | -.0685764 .0150703 -4.55 0.000 -.0981145 -.0390383
20 | .0008685 .0135818 0.06 0.949 -.025752 .027489
21 | -.0320731 .0217177 -1.48 0.140 -.0746401 .0104939
22 | -.106684 .0179845 -5.93 0.000 -.1419338 -.0714341
23 | .0413375 .018963 2.18 0.029 .0041697 .0785053
24 | -.182834 .0165629 -11.04 0.000 -.2152976 -.1503704
25 | -.0617177 .0189648 -3.25 0.001 -.098889 -.0245464
26 | .024102 .0229077 1.05 0.293 -.0207975 .0690016
|
_cons | -1.341882 .0336223 -39.91 0.000 -1.407782 -1.275981
------------------------------------------------------------------------------
hello
I'm doing a study on the effect of refugees on wages. But post_treat comes up with such a result. I'm a bit of a novice at Stata. The result is like this in DID, how can I solve this problem. Thanks

[Clyde Schechter]

It is not immediately obvious what post_treat is colinear with. The loss of the 2017.year variable due to colinearity is probably due to the post variable itself and, in a DID model is not a problem. But the loss of post_treat definitely is.

To figure out what is colinear with post_treat I would need a sample of your data that exhibits this same problem when run with that regression command. Please use the -dataex- command to post back with such an example. If you are running version 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.

[burhan magden]

thank you I solved the problem

[Clyde Schechter]

It would be nice if you posted your solution so others facing the same difficulty in the future might learn from what you have accomplished.