Skip to main content
. Author manuscript; available in PMC: 2015 Mar 9.
Published in final edited form as: J Biopharm Stat. 2014;24(3):634–648. doi: 10.1080/10543406.2014.888444

Table 1.

Monte Carlo results (based on 500 replicates): Linear regression with missing covariate where N = 100, X1 ~ N(2,1), X2 ~ N(2,1), Y ~ N(b0 + b1 * X1 + b2 * X2, 4), missing rate = 0.33, Spearman correlation coefficient between X1 and X2: 0.00, Spearman correlation coefficient between X1 and Y: 0.29, and Spearman correlation coefficient between X2 and Y: −0.29

b0 = 10.000
b1 = 1.333
b2 = −1.333
Method Esta SDb SEc CRd Est SD SE CR Est SD SE CR
FO 10.044 1.248 1.213 94.2 1.332 0.421 0.406 93.8 −1.360 0.416 0.404 94.4
CC 10.259 1.352 1.273 92.6 1.031 0.454 0.448 90.0 −0.374 0.514 0.493 49.2
IPWDR12 10.519 4.616 13.685 90.2 1.157 1.441 4.146 87.2 −1.409 1.275 4.308 94.2
IPWDR21 10.052 1.621 1.810 94.0 1.351 0.639 0.754 94.0 −1.376 0.514 0.593 94.4
IPWDR22 9.755 3.073 2.667 93.8 1.452 0.986 1.150 94.0 −1.296 0.927 0.936 94.0
NNMIB12 M1: misspecified; M2: correctly specified
(3,0.8,0.2)e 10.631 1.413 1.494 92.8 1.055 0.520 0.576 94.8 −1.389 0.448 0.444 94.2
(3,0.5,0.5) 10.494 1.461 1.560 94.0 1.103 0.539 0.607 95.8 −1.353 0.454 0.449 94.4
(3,0.2,0.8) 10.409 1.507 1.600 93.6 1.124 0.564 0.625 96.4 −1.319 0.450 0.450 94.8
(5,0.8,0.2) 10.724 1.357 1.479 93.4 1.010 0.489 0.571 94.8 −1.395 0.445 0.439 95.0
(5,0.5,0.5) 10.583 1.413 1.529 94.0 1.065 0.509 0.595 95.4 −1.367 0.446 0.442 94.4
(5,0.2,0.8) 10.516 1.468 1.567 94.4 1.070 0.531 0.608 94.8 −1.332 0.447 0.442 94.4
NNMIB21 M1: correctly specified; M2: misspecified
(3,0.8,0.2) 10.219 1.511 1.473 92.6 1.266 0.581 0.575 94.0 −1.375 0.453 0.430 93.4
(3,0.5,0.5) 10.355 1.491 1.473 92.6 1.205 0.560 0.576 94.6 −1.392 0.453 0.434 93.6
(3,0.2,0.8) 10.565 1.423 1.460 93.8 1.110 0.537 0.569 94.4 −1.414 0.449 0.436 94.0
(5,0.8,0.2) 10.286 1.502 1.464 93.0 1.235 0.568 0.570 94.0 −1.381 0.454 0.428 92.8
(5,0.5,0.5) 10.432 1.457 1.456 94.2 1.167 0.554 0.565 94.2 −1.397 0.451 0.431 93.6
(5,0.2,0.8) 10.626 1.386 1.440 94.2 1.079 0.510 0.559 95.4 −1.417 0.446 0.433 93.6
NNMIB22 M1: correctly specified; M2: correctly specified
(3,0.8,0.2) 10.134 1.534 1.516 94.0 1.292 0.587 0.596 94.0 −1.347 0.457 0.430 92.8
(3,0.5,0.5) 10.184 1.536 1.535 93.8 1.263 0.591 0.603 93.0 −1.343 0.457 0.435 93.6
(3,0.2,0.8) 10.231 1.540 1.587 92.8 1.220 0.583 0.622 94.6 −1.320 0.457 0.441 94.4
(5,0.8,0.2) 10.211 1.518 1.489 92.8 1.258 0.581 0.582 93.4 −1.357 0.452 0.428 93.2
(5,0.5,0.5) 10.241 1.517 1.512 93.0 1.235 0.571 0.592 94.4 −1.349 0.452 0.431 93.8
(5,0.2,0.8) 10.328 1.512 1.542 93.0 1.176 0.563 0.600 94.8 −1.331 0.451 0.435 94.6
a

Average of 500 point estimates.

b

Empirical standard deviation of 500 point estimates.

c

Average of 500 estimated standard errors.

d

Coverage rate of 500, 95% confidence intervals.

e

(NN, w1, w2).