A Bayesian functional approach to test models of life course epidemiology over continuous time.

"additional simulation experiments are considered in the supplementary material (available as supplementary data at ije online) to compare the proposed method with alternative estimation procedures frlm and spt are implemented in r with software available on github."

"additional simulation experiments are considered in the supplementary material (available as supplementary data at ije online) to compare the proposed method with alternative estimation procedures frlm and spt are implemented in r with software available on github.; a package including all the functions to perform the analyses is included on github at the following address: [ https://github com/jbodelet/frlm ]. additional simulation experiments are considered in the supplementary material (available as supplementary data at ije online) to compare the proposed method with alternative estimation procedures frlm and spt are implemented in r with software available on github."

"Conflict of interest None declared."

"Funding This work was supported by the Jacobs Foundation and by NIH Grants R01- HD087061 (MPIs K.H. and M.J.S.) specifically for the present analyses), P30-AG017265, R01-AG043404 and R01-AG033590; by the Swiss National Science Foundation (10531C-197964 to M.J.S.); and by the Jacobs Center for Productive Youth Development (University of Zürich). S.H. was supported by the National Institute on Aging (1R01AG067621). This research uses data from Add Health, a programme directed by Robert Hummer and designed by J. Richard Udry, Peter S. Bearman and K.M.H. (University of North Carolina at Chapel Hill). The Add Health programme is funded by Grant P01-HD31921 from the Eunice Kennedy Shriver National Institute of Child Health and Human Development, with cooperative funding from 23 other federal agencies and foundations [https://www.cpc.unc.edu/projects/addhealth/about/funders]."