This is the init_notebook_mode
cell from ITables v2.1.4
(you should not see this message - is your notebook trusted?)
ATTE Coverage
The simulations are based on the the make_did_SZ2020-DGP with \(1000\) observations. Learners are only set to boosting, due to time constraints (and the nonlinearity of some of the DGPs).
DoubleML Version 0.8.2
Script did_cs_atte_coverage.py
Date 2024-08-12 10:37:13
Total Runtime (seconds) 14727.808935
Python Version 3.12.4
Observational Score
Coverage for 95.0%-Confidence Interval over 1000 Repetitions
LGBM |
LGBM |
1 |
False |
11.753 |
58.997 |
0.975 |
LGBM |
LGBM |
2 |
False |
13.528 |
69.471 |
0.980 |
LGBM |
LGBM |
3 |
False |
12.655 |
65.935 |
0.977 |
LGBM |
LGBM |
4 |
False |
16.051 |
84.199 |
0.986 |
LGBM |
LGBM |
5 |
False |
7.575 |
38.525 |
0.974 |
LGBM |
LGBM |
6 |
False |
7.297 |
36.612 |
0.969 |
LGBM |
LGBM |
1 |
True |
4.501 |
21.392 |
0.962 |
LGBM |
LGBM |
2 |
True |
5.015 |
24.341 |
0.955 |
LGBM |
LGBM |
3 |
True |
4.972 |
23.800 |
0.962 |
LGBM |
LGBM |
4 |
True |
5.458 |
28.363 |
0.959 |
LGBM |
LGBM |
5 |
True |
3.960 |
19.373 |
0.961 |
LGBM |
LGBM |
6 |
True |
3.787 |
17.992 |
0.942 |
Coverage for 90.0%-Confidence Interval over 1000 Repetitions
LGBM |
LGBM |
1 |
False |
11.753 |
49.512 |
0.941 |
LGBM |
LGBM |
2 |
False |
13.528 |
58.302 |
0.945 |
LGBM |
LGBM |
3 |
False |
12.655 |
55.335 |
0.936 |
LGBM |
LGBM |
4 |
False |
16.051 |
70.662 |
0.952 |
LGBM |
LGBM |
5 |
False |
7.575 |
32.331 |
0.936 |
LGBM |
LGBM |
6 |
False |
7.297 |
30.726 |
0.914 |
LGBM |
LGBM |
1 |
True |
4.501 |
17.953 |
0.913 |
LGBM |
LGBM |
2 |
True |
5.015 |
20.427 |
0.907 |
LGBM |
LGBM |
3 |
True |
4.972 |
19.973 |
0.909 |
LGBM |
LGBM |
4 |
True |
5.458 |
23.803 |
0.913 |
LGBM |
LGBM |
5 |
True |
3.960 |
16.258 |
0.911 |
LGBM |
LGBM |
6 |
True |
3.787 |
15.100 |
0.885 |
Experimental Score
Remark that the only two valid DGPs are DGP \(5\) and DGP \(6\). All other DGPs are invalid due to non-experimental treatment assignment.
Coverage for 95.0%-Confidence Interval over 1000 Repetitions
LGBM |
LGBM |
1 |
False |
3.992 |
12.425 |
0.786 |
LGBM |
LGBM |
2 |
False |
3.710 |
13.272 |
0.832 |
LGBM |
LGBM |
3 |
False |
2.942 |
12.072 |
0.901 |
LGBM |
LGBM |
4 |
False |
3.899 |
12.211 |
0.787 |
LGBM |
LGBM |
5 |
False |
2.957 |
14.238 |
0.951 |
LGBM |
LGBM |
6 |
False |
2.537 |
12.406 |
0.954 |
LGBM |
LGBM |
1 |
True |
4.006 |
12.434 |
0.795 |
LGBM |
LGBM |
2 |
True |
3.698 |
13.295 |
0.841 |
LGBM |
LGBM |
3 |
True |
2.915 |
12.084 |
0.900 |
LGBM |
LGBM |
4 |
True |
3.918 |
12.229 |
0.790 |
LGBM |
LGBM |
5 |
True |
2.931 |
14.248 |
0.946 |
LGBM |
LGBM |
6 |
True |
2.487 |
12.413 |
0.956 |
Coverage for 90.0%-Confidence Interval over 1000 Repetitions
LGBM |
LGBM |
1 |
False |
3.992 |
10.428 |
0.711 |
LGBM |
LGBM |
2 |
False |
3.710 |
11.139 |
0.747 |
LGBM |
LGBM |
3 |
False |
2.942 |
10.131 |
0.840 |
LGBM |
LGBM |
4 |
False |
3.899 |
10.248 |
0.700 |
LGBM |
LGBM |
5 |
False |
2.957 |
11.949 |
0.897 |
LGBM |
LGBM |
6 |
False |
2.537 |
10.411 |
0.904 |
LGBM |
LGBM |
1 |
True |
4.006 |
10.435 |
0.698 |
LGBM |
LGBM |
2 |
True |
3.698 |
11.157 |
0.762 |
LGBM |
LGBM |
3 |
True |
2.915 |
10.141 |
0.831 |
LGBM |
LGBM |
4 |
True |
3.918 |
10.263 |
0.704 |
LGBM |
LGBM |
5 |
True |
2.931 |
11.957 |
0.892 |
LGBM |
LGBM |
6 |
True |
2.487 |
10.418 |
0.911 |