Compute method performance metrics

Compute method performance metrics

computeMetrics(
  logRr,
  seLogRr = NULL,
  ci95Lb = NULL,
  ci95Ub = NULL,
  p = NULL,
  trueLogRr
)

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). If not provided the standard error will be inferred from the 95 percent confidence interval.

ci95Lb

The lower bound of the 95 percent confidence interval. IF not provided it will be inferred from the standard error.

ci95Ub

The upper bound of the 95 percent confidence interval. IF not provided it will be inferred from the standard error.

p

The two-sided p-value corresponding to the null hypothesis of no effect. IF not provided it will be inferred from the standard error.

trueLogRr

A vector of the true effect sizes

Details

Compute the AUC, coverage, mean precision, MSE, type 1 error, type 2 error, and the fraction non- estimable.

Examples

library(EmpiricalCalibration)
data <- simulateControls(n = 50 * 3, trueLogRr = log(c(1, 2, 4)))
computeMetrics(logRr = data$logRr, seLogRr = data$seLogRr, trueLogRr = data$trueLogRr)
#> Setting levels: control = FALSE, case = TRUE
#> Setting direction: controls < cases
#>          auc     coverage        meanP          mse        type1        type2 
#>         1.00         0.72       136.49         0.03         0.24         0.00 
#> nonEstimable 
#>         0.00