Skip to main content
. Author manuscript; available in PMC: 2019 Jun 12.
Published in final edited form as: Stat Methods Med Res. 2018 May 2;28(6):1676–1688. doi: 10.1177/0962280218772592

Table 7.

Monte Carlo simulation study: estimation of Cox regression with dependent censoring, where T ~ Weibull(eln(2)X−ln(2)Z,1.5), C ~ Weibull(e−2X+0.1Z,1.4), X~BernoullipZ=11+e0.250.5Z and δx~BernoulliPZ,δt,Y=11+e1.5+0.5Z2Y.

 βx = ln(2) = 0.693 βz = ln(2) = 0.693
Method  Esta  SDb  SEc  RMSEd  CRe  Est  SD  SE  RMSE  CR Divf
N = 200
 FO  0.688  0.201  0.195  0.201  94.3  −0.714  0.308  0.316  0.309  95.5
 CC  0.671  0.329  0.320  0.330  94.2  −0.940  0.531  0.518  0.586  92.6
 PMM1  0.721  0.310  0.303  0.311  96.1  −0.703  0.319  0.330  0.319  95.2
 AIPW11  0.705  0.331  0.296  0.331  91.8  −0.716  0.327  0.373  0.328  96.1 0
 NNMI11(0.8,0.2)  0.717  0.338  0.315  0.339  93.0  −0.705  0.322  0.332  0.322  94.3
 NNMI11(0.2,0.8)  0.692  0.339  0.320  0.339  94.1  −0.690  0.317  0.330  0.317  94.3
 AIPW12  0.739  0.321  0.208  0.324  81.5  −0.779  0.378  0.450  0.388  96.1 191
 NNMI12(0.8,0.2)  0.721  0.304  0.296  0.305  95.5  −0.713  0.325  0.331  0.326  94.1
 NNMI12(0.2,0.8)  0.720  0.286  0.286  0.287  96.6  −0.714  0.322  0.331  0.323  94.7
 AIPW21  0.706  0.331  0.296  0.331  92.1  −0.715  0.327  0.373  0.328  96.2 0
 NNMI21(0.8,0.2)  0.724  0.331  0.313  0.332  94.0  −0.707  0.322  0.332  0.322  94.1
 NNMI21(0.2,0.8)  0.696  0.335  0.319  0.335  94.4  −0.690  0.317  0.329  0.317  94.5
N = 400
 FO  0.683  0.143  0.136  0.143  93.6  −0.701  0.228  0.221  0.228  95.0
 CC  0.660  0.235  0.220  0.237  92.2  −0.927  0.379  0.358  0.445  88.8
 PMM1  0.699  0.219  0.217  0.219  95.1  −0.698  0.238  0.231  0.238  94.9
 AIPW11  0.691  0.230  0.206  0.230  92.2  −0.706  0.241  0.247  0.241  96.4 0
 NNMI11(0.8,0.2)  0.697  0.233  0.217  0.233  94.0  −0.700  0.240  0.231  0.240  94.7
 NNMI11(0.2,0.8)  0.688  0.234  0.224  0.234  94.2  −0.687  0.236  0.230  0.236  95.2
 AIPW12  0.713  0.217  0.144  0.218  81.0  −0.760  0.279  0.270  0.287  94.9 150
 NNMI12(0.8,0.2)  0.700  0.213  0.205  0.213  94.5  −0.705  0.239  0.230  0.239  95.3
 NNMI12(0.2,0.8)  0.708  0.199  0.196  0.200  95.8  −0.708  0.238  0.230  0.238  94.8
 AIPW21  0.690  0.230  0.206  0.230  92.3  −0.706  0.240  0.247  0.240  96.3 0
 NNMI21(0.8,0.2)  0.700  0.232  0.216  0.232  94.1  −0.701  0.240  0.231  0.240  94.6
 NNMI21(0.2,0.8)  0.688  0.234  0.221  0.234  94.4  −0.687  0.236  0.229  0.236  95.1

Note: Censoring rate: 0.35; Missing rate: 0.60.

a

Average of 1000 point estimates.

b

Empirical standard deviation.

c

Average estimated standard error.

d

Root mean square error: square root of bias2 + SD2.

e

Coverage rate of 1000 95% confidence intervals.

f

Number of disconvergences for AIPW.