Table 3.

Comparison of Mean-Absolute-Error (MAE) and Rooted-Mean-Squared-Error (RMSE) for Model 1 with different link functions and the censoring distribution is mis-specified with α = 0.5.

p	SRF	Naive.Cox	Naive.km	Lu.id	Lu.exp	Wang.id	Wang.exp
Model 1: identity link, n = 3, 000, SNR = 0.3
5	0.1361	0.1353	0.2051	0.1337	0.1344	0.1336	0.1342
	0.1706	0.1681	0.2457	0.1687	0.1693	0.1685	0.1690
10	0.1444	0.1430	0.2160	0.1402	0.1408	0.1403	0.1408
	0.1755	0.1732	0.2523	0.1726	0.1731	0.1725	0.1730
20	0.1392	0.1372	0.2078	0.1345	0.1351	0.1345	0.1351
	0.1723	0.1699	0.2484	0.1694	0.1700	0.1692	0.1698
Model 1: log-exp link, n = 3, 000, SNR = 0.3
5	0.1348	0.1341	0.2032	0.1325	0.1333	0.1324	0.1330
	0.1691	0.1667	0.2432	0.1673	0.1679	0.1671	0.1676
10	0.1431	0.1418	0.2139	0.1390	0.1396	0.1391	0.1396
	0.1740	0.1718	0.2497	0.1712	0.1717	0.1711	0.1716
20	0.1380	0.1360	0.2060	0.1335	0.1341	0.1334	0.1340
	0.1708	0.1685	0.2460	0.1681	0.1687	0.1679	0.1685
Model 1: exp link, n = 3, 000, SNR = 0.3
5	24.906	25.157	33.628	24.471	24.826	24.427	24.784
	30.984	30.687	39.205	30.609	30.852	30.591	30.800
10	26.381	26.553	35.410	25.738	26.015	25.678	25.996
	31.799	31.593	40.265	31.403	31.607	31.373	31.574
20	25.096	25.145	33.418	24.461	24.741	24.365	24.680
	30.940	30.746	39.152	30.609	30.831	30.551	30.759

The number of covariates p = 5, 10, 20, for each p, the first row is MAE, the second row is RMSE. SRF, proposed random forest-bases estimator; Naive.km, estimate based on Kaplan–Meier estimator without adjusting for the covariates; Naive.Cox, Cox regression based estimator; Lu.id, method of Tian et al. (2014) with identity link; Lu.exp, method of Tian et al. (2014) with exponential link; Wang.id, method of Wang and Schaubel (2018) with identity link; Wang:exp, method of Wang and Schaubel (2018) with exponential link.