xlink (version 1.0.1)

xlink_fit: Genetic association models for X-chromosome SNPs on continuous, binary and survival outcomes

Description

xlink_fit returns model fitting results for each SNP with the covariates.

Usage

xlink_fit(resp = c(), os = c(), ostime = c(), snps = c(),
  gender = c(), covars = c(), option = c(type = c(), male = c(),
  female = c(), MAF_v = 0), model = c(), data)

Arguments

resp

Response variable for continuous or binary model fitting.

os

Survival indicator, 1 for death, 0 for censoring.

ostime

Duration time of survival.

snps

SNP name list for model fitting.

gender

Gender information must be included in the data. Default setting is male=1 and female=0. If not as default setting, please provide male and female information in the option.

covars

Covariates list if needed.

option

There are three options. First, type has default 'all', which provides model fitting results for each SNP understanding as 'XCI', 'XCI-E' and 'XCI-S' type respectively. If type is chosen as 'XCI' or 'XCI-E', all the SNPS consider as 'XCI' or 'XCI-E' type in corresponding model. Secondly, if gender is not as default gender setting (male=1,female=0), male and female information should be provided here.The third one, MAF_v is the low bound of the minimum allele frequency, the SNP MAF below this value will not be used in xlink_fit.

model

Fitting model. For 'linear', fitting linear model. For 'binary', fitting logistic regression model. For 'survival', fitting survival model.

data

Data set.

Value

It returns estimated parameters, confidence interval and P value for each variable in the chosen model. The baseline and full model maximum likelihood estimation are provided. If type is 'all', best model choice is provided by using AIC as an benchmark.

References

Xu, Wei, and Meiling Hao. 'A unified partial likelihood approach for X-chromosome association on time-to-event outcomes.' Genetic epidemiology 42.1 (2018): 80-94.

Han, D., Hao, M., Qu, L., & Xu, W. (2019). A novel model for the X-chromosome inactivation association on survival data. Statistical Methods in Medical Research.

See Also

lm{stats} for linear model, glm{stats} for logistic regression model, and coxph{survival} for survival model.

Examples

# NOT RUN {
Covars<-c("Age","Smoking","Treatment")
SNPs<-c("snp_1","snp_2","snp_3")
xlink_fit(os="OS",ostime="OS_time",snps=SNPs,gender="gender",covars=Covars,
          option =list(MAF_v=0.05),model="survival",data = Rdata)
xlink_fit(resp="OS_time",snps=SNPs,gender="gender",option =list(type="XCI",MAF_v=0.05),
          model="linear",data = Rdata)
# }