Improving estimation in genetic models using prior information

Espen Moen Eilertsen
2016 Norsk Epidemiologi  
Statistical models used to investigate research questions in behavioral genetics often require large amounts<br />of data. This paper introduces some key concepts of Bayesian analysis and illustrates how these methods<br />can aid model estimation when the data does not provide enough information to reliably answer research<br />questions. The use of informative prior distributions is discussed as a method of incorporating information<br />from other sources than the data at hand. The procedure
more » ... is illustrated with an ACE model decomposition of<br />the variance of antisocial personality disorder. The data originates from the Norwegian Twin Registry, and<br />includes adult twins assessed with the Structured Interview for DSM Personality (SIDP-IV). Inclusion of<br />prior information lead to a shift with respect to conclusions about the presence of shared environmental<br />effects compared to a traditional analysis. Small and medium sized studies should consider use of prior<br />information to aid estimation of population parameters.
doi:10.5324/nje.v26i1-2.2017 fatcat:cevopjwjrvgahaj5erp7kgrb5q