Description Usage Arguments Value Warning Author(s) References Examples
Use proportional odds logistic regression to test for the association between a SNP (i.e. x) and secondary phenotype (i.e. y) while accounting for the ascertainment bias due to case-control sampling (i.e. d).
1 | SecondaryPhenotype(x, y, d, z = null, covariates = FALSE, sigLevel = 0.05)
|
x |
Let x be a vector of genotypes i.e. x=0,1,2 |
y |
Let y be a vector of the phenotype |
d |
Let d be a vector of case control status |
z |
Let z be a matrix of covariates |
sigLevel |
Let sigLevel be the significance level, default to 0.05 |
covariates |
covariates=FALSE (default) then the models will not be adjusted for covariates, covariates=TRUE then the model will be adjusted for covariates. |
whether or not the SNP is associated with the secondary phenotype Y given case-control sampling d
All covariates included in the model for adjustment must be entered as a matrix, not individually. For instance, variables age and gender should first be combined such that z=cbind(age,gender) and z is entered into the function instead of age and gender separately.
Sharon Lutz, Annie Thwing
Lutz SM, Hokanson JE, Lange C. (2014) An Alternative Hypothesis Testing Strategy for Secondary Phenotype Data in Case-Control Genetic Association Studies. Frontiers in Genetics. 5 (188).
1 2 3 4 5 6 7 8 9 | set.seed(1)
n<-1000
d<-c(rep(0,n/2),rep(1,n/2))
x<-rbinom(n,2,0.3)
z<-rnorm(n)
y<-rnorm(n,0.1*d+0.2*x+0.1*z)
SecondaryPhenotype(x,y,d,z,covariates=TRUE)
SecondaryPhenotype(x,y,d)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.