Skip to main content

Table 2 Linear regression modeling

From: Perinatal, neonatal, developmental and demographic predictors of intelligence at 4 years of age among low birth weight children: a panel study with a 2-year follow-up

 

Model 1

Model 2

Model 3

Model 4

 

16 variables from bivariate analysis (Bayley 5 subscales at 2 years separately)

16 variables from bivariate analysis (Bayley 5 subscales at 2 years separately)

12 variables from bivariate analysis (Bayley at 2 years aggregated)

12 variables from bivariate analysis (Bayley at 2 years aggregated)

Regression

linear regression

stepwise backward regression

linear regression

stepwise backward regression

No of significant predictors

1

5

2

4

Adjusted R2

0.5362

0.5491

0.5474

0.5701

RMSE

12.292

12.12

12.144

11.835

F

8.23

25.36

11.08

34.15

p > F

0.0000

0.0000

0.0000

0.0000

AIC

808.8262

796.4019

803.0702

790.6543

  1. AIC Akaike information criterion, BSID Bayley Scales of Infant and Toddler Development, RMSE Root mean square error