umx_make_MR_data: Simulate Mendelian Randomization data

Description

umx_make_MR_data returns a dataset containing 4 variables: A variable of interest (Y), a putative cause (X), a qtl (quantitative trait locus) influencing X, and a confounding variable (U) affecting both X and Y.

Usage

umx_make_MR_data(
  nSubjects = 1000,
  Vqtl = 0.02,
  bXY = 0.1,
  bUX = 0.5,
  bUY = 0.5,
  pQTL = 0.5,
  seed = 123
)

Value

- data.frame

Arguments

nSubjects: Number of subjects in sample
Vqtl: Variance of QTL affecting causal variable X (Default 0.02)
bXY: Causal effect of X on Y (Default 0.1)
bUX: Confounding effect of confounder 'U' on X (Default 0.5)
bUY: Confounding effect of confounder 'U' on Y (Default 0.5)
pQTL: Decreaser allele frequency (Default 0.5)
seed: value for the random number generator (Default 123)

Details

The code to make these Data. Modified from Dave Evans 2016 Boulder workshop talk.

Other Data Functions: noNAs(), prolific_anonymize(), prolific_check_ID(), prolific_read_demog(), umx, umxFactor(), umxHetCor(), umx_as_numeric(), umx_cont_2_quantiles(), umx_lower2full(), umx_make_TwinData(), umx_make_fake_data(), umx_make_raw_from_cov(), umx_merge_randomized_columns(), umx_polychoric(), umx_polypairwise(), umx_polytriowise(), umx_read_lower(), umx_rename(), umx_reorder(), umx_score_scale(), umx_select_valid(), umx_stack(), umx_strings2numeric()

Examples

Run this code

df = umx_make_MR_data(10000)
str(df)
if (FALSE) {
m1 = umxTwoStage(Y ~ X, ~qtl, data = df)
plot(m1)
}