RRate-functions: Estimating Replication Rate for primary associations
In RRate: Estimating Replication Rate for Genome-Wide Association Studies

Description Usage Arguments Details Value Author(s) References See Also Examples

repRateEst implements a replication rate estimation method. Two-component mixture prior is used in the estimation.

1 2	repRateEst(MUhat, SE, SE2, zalpha2, zalphaR2, boot = 100, output = TRUE, idx = TRUE, dir = "output", info = TRUE)

`MUhat`	The observed effect size (log-odds ratio) in the primary study.
`SE`	The standard error of the observed log-odds ratio in the primary study.
`SE2`	The standard error of the observed log-odds ratio in the replication study.
`zalpha2`	The critical value of z-values in the primary study, i.e. z_alpha/2.
`zalphaR2`	The critical value of z-values in the replication study, i.e. z_alphaR/2.
`boot`	The resampling number of bootstrop used for estimating the credible interval of the RR.
`output`	Bool value. To determine whether to output the estimated results in the dir or not.
`idx`	The indexes of the SNPs having been further inverstigated in the replication study. We only calculate RR for primary associations with indexes in `idx`.
`dir`	The directory to save the estimated results. It has effect when `output=T`
`info`	Bool value. To determine whether to show the parematers inference results in the terminal or not.

The RR estimation is based on the following two-component mixture model: mu=pi_0 delta_0+(1-pi_0) N(0, sigma_0^2).

Details can be seen the following reference paper.

repRateEst returns the RR, lfdr, prediction power and infered parameters. The returened value is a LIST:

`idx`	The index of the SNPs which RR are estimated.
`pi0`	The proportion of nonassociated SNPs.
`sigma02`	The variance of the associated SNPs' effect sizes
`RR`	Estimated replication rate.
`RRlow`	The lower limit of the 95% CI for RR.
`RRhigh`	The upper limit of the 95% CI for RR.
`lfdr`	Estimated local false discovery rate of the primary study
`lfdrLow`	The lower limit of the 95% CI for lfdr.
`lfdrHigh`	The upper limit of the 95% CI for lfdr.
`predPower`	The Bayesian predictive power of the replication study.
`predPowerLow`	The lower limit of the 95% CI for predPower.
`perdPowerHigh`	The upper limit of the 95% CI for predPower.
`GRR`	The Global Replication Rate (Mean value of RR)
`GRRlow`	The lower limit of the 95% CI for GRR.
`GRRhigh`	The upper limit of the 95% CI for GRR.

Wei Jiang, Jing-Hao Xue and Weichuan Yu

Maintainer: Wei Jiang <wjiangaa@connect.ust.hk>

Jiang, W., Xue, J-H, and Yu, W. What is the probability of replicating a statistically significant association in genome-wide association studies?. Submitted.

RRate, SEest, repSampleSizeRR, repSampleSizeRR2, HLtest

alpha<-5e-6               #Significance level in the primary study
alphaR<-5e-3              #Significance level in the replication study
zalpha2<-qnorm(1-alpha/2)
zalphaR2<-qnorm(1-alphaR/2)

##Load data
data('smryStats1')        #Example of summary statistics in 1st study
n2.0<-2000                #Number of individuals in control group
n2.1<-2000                #Number of individuals in case group

SE2<-SEest(n2.0, n2.1, smryStats1$F_U, smryStats1$F_A) #SE in replication study
######  RR estimation  ######
RRresult<-repRateEst(log(smryStats1$OR),smryStats1$SE, SE2,zalpha2,zalphaR2, output=TRUE,dir='.')
RR<-RRresult$RR           #Estimated RR