Skip to main content

Table 3 Effect of ICU admission on in-hospital mortality using standard linear regression (crude and adjusted ordinary least squares models) and instrumental variable-based analyses (double and triple stage least squares models)

From: Benefits of ICU admission in critically ill patients: Whether instrumental variable methods or propensity scores should be used

 

Risk Difference

95CI

p-value

Crude OLS

-0.06

-0.08--0.03

< 0.01

Adjusted OLS

0.03

0.01-0.05

0.01

Propensity matched cohort

0.04

0.01-0.08

< 0.01

2LS

0.01

-2.45-2.30

0.99

3LS

-0.05

-1.41-0.89

0.49

  1. The association measure is the absolute mortality difference (with 95% confidence interval, 95CI). OLS: ordinary least squares, 2LS: double stage least squares, 3LS: triple stage least squares.
Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us