Skip to main content

Table 2 Regression analyses. Factors associated with unknown smoking status. N = 855,704.

From: Evaluation of incomplete maternal smoking data using machine learning algorithms: a study from the Medical Birth Registry of Norway

Known smoking status = 0 / Unknown smoking status = 1

1999–2014

 

Unadjusted

Full model a

 

RR (95% CI)

RR (95% CI)

Continuous variables:

 Age of mother

1.02 (1.01–1.02)

1.00 (1.00–1.00)

 Parity

0.98 (0.98–0.99)

1.02 (1.02–1.03)

 Year of child birth

1.01 (1.01–1.01)

1.03 (1.03–1.03)

 Paper-based form

ref

ref

 Electronic form

0.47 (0.47–0.48)

0.58 (0.57–0.59)

 Norway/ Nordic Countries

ref

ref

 Europe outside the Nordic region

1.35 (1.32–1.38)

1.15 (1.12–1.17)

 Asia

1.68 (1.65–1.71)

1.17 (1.15–1.19)

 Africa

2.02 (1.98–2.07)

1.26 (1.23–1.29)

 Others

1.42 (1.35–1.49)

1.09 (1.04–1.14)

 No SGA-10

ref

ref

 SGA-10

1.15 (1.13–1.17)

1.02 (1.00–1.04)

 Married, living together, etc.

ref

ref

 Divorced, living alone, etc.

1.01 (1.00–1.03)

1.02 (1.00–1.04)

 Medium education

ref

ref

 University education

1.19 (1.18–1.21)

0.97 (0.96–0.98)

 Primary education

1.13 (1.12–1.15)

1.04 (1.02–1.06)

  1. aFull model, with institutions included. Compared to the reference group “small hospitals”, the RR of the 16 largest hospitals ranged from RR 0.33 (CI 0.30–0.36) to RR 4.74 (CI 4.67–4.83)