mJAM_get_condp: Get conditional p-value under mJAM model
In USCbiostats/hJAM: Hierarchical Joint Analysis of Marginal Summary Statistics

mJAM_get_condp

R Documentation

Get conditional p-value under mJAM model

Description

Get conditional p-value under mJAM model

Usage

mJAM_get_condp(
  GItGI,
  GIty,
  yty,
  yty_med,
  N_GWAS,
  g = NULL,
  selected_id,
  use_robust_var_est = FALSE,
  use_median_yty_ethnic = NULL,
  rare_id = NULL
)

Arguments

`GItGI`	A list of transformed statistics from 'get_XtX()' for each study.
`GIty`	A list of transformed statistics from 'get_z()' for each study.
`yty`	A list of transformed statistics from 'get_yty()' for each study.
`yty_med`	A numeric vector of median yty across all SNPs within each study.
`N_GWAS`	A numeric vector of GWAS sample size for each study.
`g`	Hyperparameter in g-prior. If 'NULL', it will be set to 'sum(N_GWAS)'.
`selected_id`	A numeric vector of IDs of previously selected index SNP(s).
`use_robust_var_est`	whether to use linear combination of median yty and individual yty.
`use_median_yty_ethnic`	A numeric vector of study index in which median_yty is used for all SNPs in 'selected_id'.
`rare_id`	A numeric vector of IDs for rare SNP(s) which we do not apply weighting. Instead, we use the individual estimate of yty for these SNPs for robustness.

Value

which_condp_min: The index of which SNP has the smallest conditional p-value.
condp_min: The smallest conditional p-value.
condp: A vector of all conditional p-values.
effect_est: A vector of all conditional effect estimates.
se_est: A vector of standard errors of all the conditional effect estimates.
condp_mx: A complete matrix recording all conditional effect est & se for testing SNPs and 'selected_id'.