BEGIN:VCALENDAR VERSION:2.0 CALSCALE:GREGORIAN PRODID:UW-Madison-Physics-Events BEGIN:VEVENT SEQUENCE:0 UID:UW-Physics-Event-3483 DTSTART:20141007T170500Z DTEND:20141007T180000Z DTSTAMP:20260414T122613Z LAST-MODIFIED:20140925T061833Z LOCATION:4274 Chamberlin Hall (Refreshments will be served) SUMMARY:Using distance correlation and SS-ANOVA to assess associations of familial relationships\, lifestyle factors\, diseases and mortalit y \, Chaos & Complex Systems Seminar\, Jing Kong\, UW Department of St atistics DESCRIPTION:We present a method for examining mortality as it is seen to run in families\, and lifestyle factors that are also seen to run i n families\, in a sub-population of the Beaver Dam Eye Study that has died by 2011. We observe that pairwise distance between death age in r elated persons is on average less than pairwise distance in death age between random pairs of unrelated persons. Our goal is to examine the hypothesis that pairwise di fferences in lifestyle factors correlate w ith the observed pairwise diff erences in death age that run in famili es. Szekely and coworkers have recently developed a method called dist ance correlation\, that is suitable for this task with some enhancemen ts relevant to the particular task at hand. We build a Smoothing Splin e ANOVA (SS-ANOVA) model for predicting death age based on four major lifestyle factors generally known to be related to mortality and four of the major diseases contributing to mortality\, to develop a lifesty le mortality risk vector and a disease mortality risk vector. We then examine to what extent pairwise diff erences in these scores correlate with the pairwise di fferences in mortality as they occur between fam ily members and between unrelated persons. We fi nd signfi cant distan ce correlations between death ages\, lifestyle factors\, and family re lationships. Considering only sib pairs compared to unrelated persons\ , distance correlation between siblings and mortality is\, not surpris ingly\, stronger than that between more distantly related family membe rs and mortality. The overall methodological approach here easily adap ts to exploring relationships between multiple clusters of variables w ith observable (real-valued) attributes\, and other factors for which only possibly nonmetric pairwise dissimilarities are observed.
\n URL:https://www.physics.wisc.edu/events/?id=3483 END:VEVENT END:VCALENDAR