LPM-package: LPM (Latent Probit Model)

In mingjingsi/LPM: LPM (Latent Probit Model)

Description

This package provides functions for fitting LPM, a latent probit model to characterize relationship among complex traits using summary statistics from multiple GWASs and functional annotations.

Details

Package:	LPM
Type:	Package
Version:	0.1.0
Date:	2018-07-10
License:	GPL (>= 2)
LazyLoad:	yes

This package contains three functions LPM, bLPM and bLPM_add to fit LPM and four functions post, assoc, test_rho and test_beta to make statistical inference for risk SNPs, relationship test and hypothesis testing of annotation enrichment.

Author(s)

Jingsi Ming and Can Yang

Maintainer: Jingsi Ming <[e-mail]>

See Also

LPM, bLPM, bLPM_add, post, assoc, test_rho, test_beta

Examples

  library(LPM)
  
  data(ExampleData)
  
  bLPMfit_first3 <- bLPM(ExampleData$data[1:3], X = ExampleData$X, coreNum = 2)
  bLPMfit <- bLPM_add(ExampleData$data[1:3], ExampleData$data[4], X = ExampleData$X, bLPMfit_first3, coreNum = 2)
  LPMfit <- LPM(bLPMfit)
  
  posterior1 <- post(ExampleData$data[1], X = ExampleData$X, id = 1, LPMfit)
  posterior13 <- post(ExampleData$data[c(1, 3)], X = ExampleData$X, id = c(1, 3), LPMfit)
  assoc.SNP <- assoc(posterior1, FDRset = 0.1, fdrControl = "global")
  
  p_value_test_rho <- test_rho(bLPMfit)
  result_test_beta <- test_beta(ExampleData$data, X = ExampleData$X, id = 1, LPMfit)

mingjingsi/LPM documentation built on April 2, 2020, 9:32 a.m.