. Author manuscript; available in PMC: 2010 Sep 1.

Published in final edited form as: Atl Econ J. 2009 Sep 1;37(3):299–314. doi: 10.1007/s11293-009-9185-7

Table 3.

Regression Results, Fully Interacted Model

	Physical Restraints	Catheters	Anti-psychotics	Feeding Tubes
Black	−0.0884^**	−0.0505^**	−0.1784^**	−0.0593^**
Private-pay	−0.0013^*	0.0017^**	−0.0147^**	−0.0013^**
Other payer	−0.0230	0.0112^**	0.0058^*	−0.0172^**
High School education	−0.0087^**	0.0050^**	−0.0136^**	−0.0018^**
Some college education	−0.0082^**	0.0088^**	−0.0220^**	−0.0046^**
College education	−0.0062^**	−0.0003	−0.0226^**	−0.0036^**
Education missing	−0.0011	−0.0137^**	−0.0194^**	−0.0049^**
Private-pay ^* Black	0.0127^**	0.0263^**	0.0114^*	0.0150^**
Other payer ^* Black	0.0529^**	0.0064	0.0133	−0.0324^**
High School education ^* Black	−0.0042	−0.0018	0.0108^*	0.0073^**
Some college education ^* Black	−0.0062	0.0026	0.0051	−0.0035
College education ^* Black	−0.0212^**	0.0021	0.0326^**	−0.0092^*
Education missing ^* Black	0.0004	−0.0007	0.0044	0.0125^**
Home fixed effects	Y	Y	Y	Y
N	1,545,356	1,545,372	882,505	1,545,369

Models also include age, gender, indications for length-of-stay by quarter, marital status, dummy variables for limitations in activities of daily living, dummy variables for cognitive performance score, and time indicated by quarters. All of these variables are also interacted with the black dummy variable.

= statistically significant at 5% level;

^**

= statistically significant at 1% level.