Peer-reviewed article
Quantifying and adjusting for selection biases in the Norwegian Mother, Father and Child Cohort Study using population-wide individual-level registry information.
Rayner C, Hannigan LJ, Badini I, Demange PA, Ofstad SB et al. ·
Summary
Written by AI, not yet AICS's view · claude-haiku-4-5-20251001This is a methodological study about statistical techniques for addressing selection bias in a large Norwegian cohort study of mothers and children. It does not evaluate an intervention for child well-being or assess outcomes affecting children. Instead, it focuses on improving data analysis methods to account for research participants who drop out or don't participate.
Key points
- The study analyzes participation patterns in the Norwegian Mother, Father and Child Cohort Study (MoBa), with only 29% of eligible mothers returning the first questionnaire
- Inverse probability weighting techniques substantially reduced bias in sample characteristics (93% reduction) and associations (75% reduction)
- Attrition weights were less effective than participation weights at correcting for selective participation bias
- Unweighted sample estimates differed significantly from target-population values, demonstrating systematic bias
Limitations
This is a methodological paper addressing statistical adjustment techniques, not a study of child health or well-being outcomes. It cannot tell us whether any interventions improve children's health, development, protection or participation.
Abstract
Background Selective participation in research studies hampers researchers' ability to draw valid and generalizable inferences from analyses. Quantifying and adjusting for selective participation are desirable but can be challenging given the paucity of data for non-participants. Methods We used individual-level information from population registers to predict baseline and continued participation in the Norwegian Mother, Father and Child Cohort Study (MoBa). Inverse probability weights were computed from logistic regression models with elastic-net regularization. We predicted selective participation and attrition in 296 987 mothers, of whom 29% returned the first MoBa questionnaire and 12.5% returned a follow-up questionnaire 8 years later. To quantify bias, we computed sample characteristics and exposure-outcome associations in the target population and stratified samples. To compare approaches for adjusting for bias, we computed weighted sample estimates by using three sets of weights. Results Unweighted sample estimates were systematically different from target-population values, indicating bias due to selective participation. Baseline participation weights substantially reduced the impact of selection bias on mean values by 93% and associations by 75%. Attrition weights reduced attrition bias on mean values by 78% and associations by 50% but were less effective for reducing participation bias (22% and 14% respectively). Conclusion In this sample, characteristics and effect estimates are substantially different from target-population values. Participation weights were relatively effective at reducing bias due to selective participation but attrition weights were not. Estimates from studies that use attrition weights may still contain non-negligible selection bias-particularly if the baseline sample is not representative of the target population. Future studies should prioritize opportunities for deriving sampling weights for participation as well as attrition.