. Author manuscript; available in PMC: 2016 Jan 31.

Published in final edited form as: Demography. 2015 Feb;52(1):329–354. doi: 10.1007/s13524-014-0358-x

Table 2.

Data structure used for simulations, by missing data pattern

Missing Data Pattern (joint observation with unauthorized status)	Unauthorized Status	DV (insurance coverage)	IV (income- to-poverty ratio)	Controls
	Unauthorized Status	DV (insurance coverage)	IV (income- to-poverty ratio)	X₁	X₂	…	X₇
DV and IV Jointly Observed
Donor (N ≈ 5,000)	X	X	X	X	X	…	X
Target (N ≈ 5,000)	.	X	X	X	X	…	X
DV Jointly Observed; IV Never Jointly Observed
Donor (N ≈ 5,000)	X	X	.	X	X	…	X
Target (N ≈ 5,000)	.	X	X	X	X	…	X
DV Never Jointly Observed; IV Jointly Observed
Donor (N ≈ 5,000)	X	.	X	X	X	…	X
Target (N ≈ 5,000)	.	X	X	X	X	…	X
DV and IV Never Jointly Observed
Donor (N ≈ 5,000)	X	.	.	X	X	…	X
Target (N ≈ 5,000)	.	X	X	X	X	…	X

Notes: X = completely observed; . = completely missing; DV = dependent variable; IV = independent variable.