Linear Regression in Genetic Association Studies

Bůžková, Petra
February 2013
PLoS ONE;Feb2013, Vol. 8 Issue 2, p1
Academic Journal
In genomic research phenotype transformations are commonly used as a straightforward way to reach normality of the model outcome. Many researchers still believe it to be necessary for proper inference. Using regression simulations, we show that phenotype transformations are typically not needed and, when used in phenotype with heteroscedasticity, result in inflated Type I error rates. We further explain that important is to address a combination of rare variant genotypes and heteroscedasticity. Incorrectly estimated parameter variability or incorrect choice of the distribution of the underlying test statistic provide spurious detection of associations. We conclude that it is a combination of heteroscedasticity, minor allele frequency, sample size, and to a much lesser extent the error distribution, that matter for proper statistical inference.


Related Articles

  • A Unified Framework for Association Analysis with Multiple Related Phenotypes. Stephens, Matthew // PLoS ONE;Jul2013, Vol. 8 Issue 7, p1 

    We consider the problem of assessing associations between multiple related outcome variables, and a single explanatory variable of interest. This problem arises in many settings, including genetic association studies, where the explanatory variable is genotype at a genetic variant. We outline a...

  • El intervalo entre aborto espontáneo y una nueva concepción no afecta el resultado perinatal. Antonio Arraztoa V., José; Serra T., Ramón; de Mayo G., Tomás; Olivares A., Felipe; Gabler P., Carolina; Ramírez A., Sebastián; Osorio F., Eduardo // Revista Chilena de Obstetricia y Ginecología;2012, Vol. 77 Issue 6, p423 

    Objective: To determine the probability of a new spontaneous abortion based on the time between a previous abortion and a new conception. Methods: Retrospective cohort study realized in Clinica Davila and Hospital Parroquial de San Bernardo, Santiago, Chile, between January 2007 and September...

  • Transcranial Doppler velocimetry in aneurysmal subarachnoid haemorrhage: intra- and interobserver agreement and relation to angiographic vasospasm and mortality. Staalsø, J. M.; Edsen, T.; Romner, B.; Olsen, N. V. // BJA: The British Journal of Anaesthesia;Apr2013, Vol. 110 Issue 4, p577 

    Background Transcranial Doppler measurements of the middle cerebral artery flow velocity are widely used as an indicator of vasospasm after aneurysmal subarachnoid haemorrhage (SAH). We investigated inter- and intraoperator agreement in SAH patients and healthy volunteers using colour-coded...

  • Predictors of the number of under-five malnourished children in Bangladesh: application of the generalized poisson regression model. Islam, Mohammad Mafijul; Alam, Morshed; Tariquzaman, Md; Kabir, Mohammad Alamgir; Pervin, Rokhsona; Begum, Munni; Hossain Khan, Md Mobarak // BMC Public Health;2013, Vol. 13 Issue 1, p1 

    Background: Malnutrition is one of the principal causes of child mortality in developing countries including Bangladesh. According to our knowledge, most of the available studies, that addressed the issue of malnutrition among under-five children, considered the categorical...

  • Effects on employees of controlling working hours and working schedules. Kubo, T.; Takahashi, M.; Togo, F.; Liu, X.; Shimazu, A.; Tanaka, K.; Takaya, M. // Occupational Medicine;Mar2013, Vol. 63 Issue 2, p148 

    Background High levels of control over working time and low variability in working hours have been associated with improved health-related outcomes. The potential mechanisms for this association remain unclear. Aims To examine how work-time control and variability of working times are associated...

  • Amazon Forest Fires Between 2001 and 2006 and Birth Weight in Porto Velho. Prass, Taiane; Lopes, Sílvia; Dórea, José; Marques, Rejane; Brandão, Katiane // Bulletin of Environmental Contamination & Toxicology;Jul2012, Vol. 89 Issue 1, p1 

    Birth weight data (22,012 live-births) from a public hospital in Porto Velho (Amazon) was used in multiple statistical models to assess the effects of forest-fire smoke on human reproductive outcome. Mean birth weights for girls (3,139 g) and boys (3,393 g) were considered statistically...

  • The effect of non-differential measurement error on bias, precision and power in Mendelian randomization studies. Pierce, Brandon L; VanderWeele, Tyler J // International Journal of Epidemiology;Oct2012, Vol. 41 Issue 5, p1383 

    Background Mendelian randomization (MR) studies assess the causality of associations between exposures and disease outcomes using data on genetic determinants of the exposure. In this work, we explore the effect of exposure and outcome measurement error in MR studies.Methods For continuous...

  • Can population differences in chemotherapy outcomes be inferred from differences in pharmacogenetic frequencies? Loh, M; Chua, D; Yao, Y; Soo, R A; Garrett, K; Zeps, N; Platell, C; Minamoto, T; Kawakami, K; Iacopetta, B; Soong, R // Pharmacogenomics Journal;Oct2013, Vol. 13 Issue 5, p423 

    Inter-ethnic differences in drug handling and frequencies of pharmacogenetic variants are increasingly being characterized. In this study, we systematically assessed the feasibility of inferring ethnic trends in chemotherapy outcomes from inter-ethnic differences in pharmacogenetic variant...

  • Mapping health outcome measures from a stroke registry to EQ-5D weights. Ghatnekar, Ola; Eriksson, Marie; Glader, Eva-Lotta // Health & Quality of Life Outcomes;2013, Vol. 11 Issue 1, p1 

    Purpose: To map health outcome related variables from a national register, not part of any validated instrument, with EQ-5D weights among stroke patients. Methods: We used two cross-sectional data sets including patient characteristics, outcome variables and EQ-5D weights from the national...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics