You are here
Strategy to control type I error increases power to identify genetic variation using the full biological trajectory.
Thursday,2014-01-30 16:05 America/Los_Angeles — poolea2
| Title | Strategy to control type I error increases power to identify genetic variation using the full biological trajectory. |
| Publication Type | Journal Article |
| Year of Publication | 2013 |
| Authors | Benke, KS, Wu, Y, Fallin, DM, Maher, B, Palmer, LJ |
| Journal | Genet Epidemiol |
| Volume | 37 |
| Issue | 5 |
| Pagination | 419-30 |
| Date Published | 2013 Jul |
| ISSN | 1098-2272 |
| Keywords | Cohort Studies, Computer Simulation, Genetic Variation, Genome-Wide Association Study, Humans, Linear Models, Models, Genetic, Polymorphism, Single Nucleotide |
| Abstract | <p>Genome-wide association studies have been successful in identifying loci that underlie continuous traits measured at a single time point. To additionally consider continuous traits longitudinally, it is desirable to look at SNP effects at baseline and over time using linear-mixed effects models. Estimation and interpretation of two coefficients in the same model raises concern regarding the optimal control of type I error. To investigate this issue, we calculate type I error and power under an alternative for joint tests, including the two degree of freedom likelihood ratio test, and compare this to single degree of freedom tests for each effect separately at varying alpha levels. We show which joint tests are the optimal way to control the type I error and also illustrate that information can be gained by joint testing in situations where either or both SNP effects are underpowered. We also show that closed form power calculations can approximate simulated power for the case of balanced data, provide reasonable approximations for imbalanced data, but overestimate power for complicated residual error structures. We conclude that a two degree of freedom test is an attractive strategy in a hypothesis-free genome-wide setting and recommend its use for genome-wide studies employing linear-mixed effects models.</p> |
| DOI | 10.1002/gepi.21733 |
| Alternate Journal | Genet. Epidemiol. |
| PubMed ID | 23633177 |
| PubMed Central ID | PMC3877575 |
| Grant List | N01-HC-85085 / HC / NHLBI NIH HHS / United States R01 AG015928 / AG / NIA NIH HHS / United States U01 HL080295 / HL / NHLBI NIH HHS / United States N01-HC-85081 / HC / NHLBI NIH HHS / United States GET-101831 / / Canadian Institutes of Health Research / Canada N01 HC015103 / HC / NHLBI NIH HHS / United States R56 AG020098 / AG / NIA NIH HHS / United States AG-20098 / AG / NIA NIH HHS / United States N01HC55222 / HL / NHLBI NIH HHS / United States N01-HC-85086 / HC / NHLBI NIH HHS / United States N01HC85086 / HL / NHLBI NIH HHS / United States AG-027058 / AG / NIA NIH HHS / United States N01-HC-85082 / HC / NHLBI NIH HHS / United States N01 HC-55222 / HC / NHLBI NIH HHS / United States HHSN268201200036C / HL / NHLBI NIH HHS / United States N01-HC-85083 / HC / NHLBI NIH HHS / United States N01-HC-75150 / HC / NHLBI NIH HHS / United States N01-HC-85080 / HC / NHLBI NIH HHS / United States R01 HL080295 / HL / NHLBI NIH HHS / United States R01 AG020098 / AG / NIA NIH HHS / United States N01HC75150 / HL / NHLBI NIH HHS / United States N01-HC-85079 / HC / NHLBI NIH HHS / United States HL080295 / HL / NHLBI NIH HHS / United States N01-HC-85239 / HC / NHLBI NIH HHS / United States AG-023629 / AG / NIA NIH HHS / United States N01HC85079 / HL / NHLBI NIH HHS / United States R01 AG023629 / AG / NIA NIH HHS / United States R01 AG027058 / AG / NIA NIH HHS / United States N01 HC045133 / HC / NHLBI NIH HHS / United States N01 HC035129 / HC / NHLBI NIH HHS / United States R56 AG023629 / AG / NIA NIH HHS / United States N01-HC-85084 / HC / NHLBI NIH HHS / United States N01HC85081 / HL / NHLBI NIH HHS / United States |