Table 5.

Multiple regression model out-of-pocket costs by age category (under 65 vs. 65 and over), income, and burden category (High vs. Low)

	Dependent variable:		Out-of-pocket costs (OOPC)
Variable	Coefficient (SE)	Beta	95% Confidence Interval	P value
Age >65 years	-$139.86 (108.93)	1.28	-$30.93, -$248.79	P>0.1 NS
Income
<$20,000	-$517.35 (215.69)	2.40	-$301.66, -$733.04	P<0.05
$20,000-$39,999	-$380.48 (166.58)	2.28	-$213.90, -$547.07	P<0.05
$40,000-$59,999	-$133.25 (162.84)	0.82	-$296.08, $29.57	P>0.1 NS
$60,000-$79,999	-$264.73 (164.73)	1.61	-$429.45, -$100.00	P>0.1 NS
$80,000-$99,999	$6.54 (165.21)	0.04	-$158.68, $171.75	P>0.1 NS
High Burden	$766.56 (117.40)	6.53	$649.16, $883.96	P<0.01
Constant	$510.53 (113.37)	4.50	$397.16, $623.90	P<0.01

Observations 827

R2 0.064

Adjusted R2 0.056

Residual Std. Error 1,490.401 (df = 819)

F Statistic 7.978 (df = 7; 819) p<0.01

“$100,000+” is income reference, “small burden” is burden reference, “Under 65” is age reference. Hypotheses: Lower OOPC patient 65 years and over; higher income patients higher OOPC; higher burden patients higher OOPC.

NOTES: Standardized beta = coefficient/SE; 74 pts income was “don’t know” (n=73) or “missing” (n=1)