powerGcE: powerGcE
In SharonLutz/powerGcE: runs the powerGcE function

Description Usage Arguments Value Author(s) Examples

View source: R/powerGcE.R

Empirical power analysis for a gene by environment interaction with a binary outcome and a normally distributed environmental exposure.

powerGcE(nCase = 407, nControl = 376, MAF = 0.49, meanE = 0, varE = 0.99, beta0 = -0.32, betaSNP = 0.17, betaE = 0.97, betaI = seq(-1, -0.75, by = 0.05), nSim = 1000, alpha = 5e-08, plot.output = TRUE, plot.name = "powerGcE.pdf", seed = 1)

`nCase`	is the number of cases
`nControl`	is the number of controls
`MAF`	is the minor allele frequency for the SNP
`meanE`	is the mean of the normally distributed environmental exposure
`varE`	is the variance of the normally distributed environmental exposure
`beta0`	For the binary outcome Y, the environmental exposure E, and the SNP, logit(P(Y=1))=Beta0+BetaSNPSNP+BetaEE+BetaISNPE
`betaSNP`	For the binary outcome Y, the environmental exposure E, and the SNP, logit(P(Y=1))=Beta0+BetaSNPSNP+BetaEE+BetaISNPE
`betaE`	For the binary outcome Y, the environmental exposure E, and the SNP, logit(P(Y=1))=Beta0+BetaSNPSNP+BetaEE+BetaISNPE
`betaI`	For the binary outcome Y, the environmental exposure E, and the SNP, logit(P(Y=1))=Beta0+BetaSNPSNP+BetaEE+BetaISNPE
`nSim`	is the number of simulations
`alpha`	is the alpha level, default=0.00000005
`plot.output`	if true, then a plot is outputted to the working directory.
`plot.name`	is the name of the plot.
`seed`	is set for reproducibility.

The SNP is generated from a binomial distribution and the environmental exposure from a normal distribution. Then, the binary outcome is generated from a binomial distribution such that logit(P(Y=1))=Beta0+BetaSNP*SNP+BetaE*E+BetaI*SNP*E where E is the environmental exposure. Then empirical power is calculated based on the proportion of simulations where the p-value for the interaction term is less than alpha.

Sharon Lutz

	powerGcE(nCase = 407, nControl = 376, MAF = 0.49, meanE = 0, varE = 0.99, beta0 = -0.32, betaSNP = 0.17, betaE = 0.97, betaI = seq(-1, -0.75, by = 0.05), nSim = 1000, alpha = 5e-08, plot.output = TRUE, plot.name = "powerGcE.pdf", seed = 1)