Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Fitting mixture models to birth weight data: a case study.

H Oja1, M Koiranen, P Rantakallio

  • 1Department of Applied Mathematics and Statistics, University of Oulu, Finland.

Biometrics
|September 1, 1991
PubMed
Summary

This study on birth weight and gestational age in Finland found earlier birth data had more errors. Correcting for these errors in gestational age assessment resolved differences in birth weight curves between cohorts.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Hyperemesis gravidarum and cardiometabolic risk factors in adolescents: a follow-up of the Northern Finland Birth Cohort 1986.

BJOG : an international journal of obstetrics and gynaecology·2017
Same author

Is geographical distance a barrier in the use of public primary health services among rural and urban young adults? Experience from Northern Finland.

Public health·2015
Same author

The impact of first year adherence to antiretroviral therapy on long-term clinical and immunological outcomes in the DART trial in Uganda and Zimbabwe.

Tropical medicine & international health : TM & IH·2012
Same author

Estimation of population attributable fraction (PAF) for disease occurrence in a cohort study design.

Statistics in medicine·2010
Same author

Serum alpha- and gamma-tocopherol concentrations and risk of advanced beta cell autoimmunity in children with HLA-conferred susceptibility to type 1 diabetes mellitus.

Diabetologia·2008
Same author

Body size from birth to adulthood and bone mineral content and density at 31 years of age: results from the northern Finland 1966 birth cohort study.

Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA·2005

Area of Science:

  • Perinatal epidemiology
  • Biostatistics

Background:

  • Comparing birth weight by gestational age in two Finnish cohorts (1966 and 1985-1986) revealed unexpected differences.
  • Mean birth weight before 39 weeks was lower in the later cohort, despite a higher overall mean birth weight.

Purpose of the Study:

  • To investigate the hypothesis that increased gestational age assessment errors in the earlier cohort caused the observed birth weight discrepancies.
  • To develop and apply a statistical model to account for potential errors in gestational age estimation.

Main Methods:

  • Proposed a mixture model with a nonparametric regression function to analyze birth weight data.
  • Employed the expectation-maximization (EM) algorithm for maximum likelihood estimation of model parameters.
  • Developed a technique to assess the impact of gestational age errors on intrauterine growth curves.

Related Experiment Videos

Main Results:

  • The mixture model indicated a higher risk of gestational age underestimation in the earlier (1966) cohort.
  • After applying the mixture model correction, the differences between the intrauterine growth curves of the two cohorts largely disappeared.
  • The model demonstrated that gestational age error probability is dependent on the observed gestational age.

Conclusions:

  • Gestational age misclassification in the earlier cohort likely explains the observed paradoxes in birth weight data.
  • The proposed mixture model and error correction technique effectively reconcile discrepancies in perinatal growth data.
  • This methodology offers a robust approach for analyzing birth cohorts with potential gestational age assessment inaccuracies.