Table 2.

Comparison of mean-absolute-error (MAE) and rooted-mean-squared-error (RMSE) for Model 2 with different link functions.

p	SRF	Naive.Cox	Naive.km	Lu.id	Lu.exp	Wang.id	Wang.exp
Model 2: identity link, n = 3, 000, SNR = 0.3
5	0.1218	0.1386	0.1384	0.1388	0.1388	0.1382	0.1382
	0.1498	0.1658	0.1656	0.1660	0.1660	0.1656	0.1656
10	0.1257	0.1414	0.1412	0.1418	0.1418	0.1411	0.1411
	0.1525	0.1682	0.1679	0.1687	0.1687	0.1684	0.1684
20	0.1239	0.1390	0.1385	0.1393	0.1393	0.1387	0.1387
	0.1507	0.1662	0.1655	0.1667	0.1667	0.1663	0.1663
Model 2: log-exp link, n = 3, 000, SNR = 0.3
5	0.1201	0.1366	0.1364	0.1368	0.1368	0.1362	0.1362
	0.1479	0.1635	0.1633	0.1637	0.1637	0.1634	0.1634
10	0.1240	0.1395	0.1393	0.1399	0.1399	0.1392	0.1392
	0.1506	0.1660	0.1657	0.1664	0.1664	0.1661	0.1661
20	0.1222	0.1371	0.1366	0.1374	0.1374	0.1368	0.1368
	0.1487	0.1640	0.1633	0.1645	0.1645	0.1641	0.1641
Model 2: exp link, n = 3, 000, SNR = 0.3
5	21.030	23.794	23.733	23.915	23.911	23.542	23.541
	25.984	28.185	28.135	28.297	28.292	28.126	28.125
10	21.641	24.165	24.127	24.322	24.319	23.928	23.928
	26.357	28.475	28.430	28.618	28.614	28.473	28.472
20	21.368	23.802	23.712	23.956	23.952	23.571	23.571
	26.071	28.216	28.102	28.379	28.375	28.208	28.207

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.