Skip to main content

Table 3 Negative binomial regression model for over dispersed count data (numbers of exacerbations)

From: Withdrawal of inhaled corticosteroids can be safe in COPD patients at low risk of exacerbation: a real-life study on the appropriateness of treatment in moderate COPD patients (OPTIMO)

Exacerbations (T6)

RR (95% CI)

Std. err.

p-value

ICS*

0.8777 (0.679-1.135)

0.115

0.321

Age

1.004 (0.999-1.018)

0.007

0.594

Smoke habits

0.834 (0.576-1.207)

0.157

0.335

FEV 1 %pred (T0)

1.008 (0.997-1.020)

0.006

0.170

CAT (T0)

1.035 (1.020-1.052)

0.008

0.000

BMI

0.980 (0.956-1.005)

0.013

0.122

Gender

1.043 (0.786-1.385)

0.151

0.768

Constant

0.174 (0.343-0.881)

0.144

0.058

Alpha**

0.239 (0.065-0.878)

0.159

0.043

  1. (pseudo R2 = 0.0199; p-value = 0.0012).
  2. *reference group “NO ICS”.
  3. **parameter for over dispersed count data (likelihood-ratio test of alpha = 0).