From: Strong consistency rates for the estimators in a heteroscedastic EV model with missing responses
n | p | \(\hat{g}_{n}^{W_{1}}(\cdot )\) | \(\hat{g}_{n}^{I_{1}}(\cdot )\) | \(\hat{g}_{n}^{W_{2}}(\cdot )\) | \(\hat{g}_{n}^{I_{2}}(\cdot )\) | \(\hat{f}_{n}(\cdot )\) |
---|---|---|---|---|---|---|
50 | 0.1 | 0.1199 | 0.1134 | 0.1112 | 0.1028 | 0.2816 |
100 | 0.1 | 0.0646 | 0.0577 | 0.0557 | 0.0547 | 0.1563 |
200 | 0.1 | 0.0401 | 0.0397 | 0.0374 | 0.0346 | 0.0945 |
50 | 0.25 | 0.1504 | 0.1335 | 0.1314 | 0.1304 | 0.3413 |
100 | 0.25 | 0.0795 | 0.0785 | 0.0752 | 0.0705 | 0.2048 |
200 | 0.25 | 0.0510 | 0.0505 | 0.0461 | 0.0434 | 0.1011 |
50 | 0.5 | 0.1700 | 0.1580 | 0.1718 | 0.1525 | 0.3693 |
100 | 0.5 | 0.1134 | 0.1082 | 0.1027 | 0.1018 | 0.2305 |
200 | 0.5 | 0.0583 | 0.0568 | 0.0531 | 0.0508 | 0.1550 |