Fit a systematic error model
fitSystematicErrorModel(
logRr,
seLogRr,
trueLogRr,
estimateCovarianceMatrix = FALSE,
legacy = FALSE
)Arguments
- logRr
A numeric vector of effect estimates on the log scale.
- seLogRr
The standard error of the log of the effect estimates. Hint: often the standard error = (log(<lower bound 95 percent confidence interval>) - log(<effect estimate>))/qnorm(0.025).
- trueLogRr
A vector of the true effect sizes.
- estimateCovarianceMatrix
Should a covariance matrix be computed? If so, confidence intervals for the model parameters will be available.
- legacy
If true, a legacy error model will be fitted, meaning standard deviation is linear on the log scale. If false, standard deviation is assumed to be simply linear.
Value
An object of type systematicErrorModel.
Details
Fit a model of the systematic error as a function of true effect size. This model is an extension of the method for fitting the null distribution. The mean and log(standard deviations) of the error distributions are assumed to be linear with respect to the true effect size, and each component is therefore represented by an intercept and a slope.
Examples
controls <- simulateControls(n = 50 * 3, mean = 0.25, sd = 0.25, trueLogRr = log(c(1, 2, 4)))
model <- fitSystematicErrorModel(controls$logRr, controls$seLogRr, controls$trueLogRr)
model
#> meanIntercept meanSlope sdIntercept sdSlope
#> 0.24339542 1.01498772 0.18418950 0.04939429
#> attr(,"class")
#> [1] "systematicErrorModel"