SS {ThresholdROC}

Sample size estimation (two-state setting)

Description

Estimates the sample size and the optimum sample size ratio needed for a given width, costs, disease prevalence and significance level under the assumption of binormality.

Usage

SS(par1.1, par1.2, par2.1, par2.2=NULL, rho, width,
   costs=matrix(c(0, 0, 1, (1-rho)/rho), 2, 2, byrow=TRUE),
   R=NULL, var.equal=FALSE, alpha=0.05)

Arguments

par1.1

healthy population mean.

par1.2

healthy population standard deviation.

par2.1

diseased population mean.

par2.2

diseased population standard deviation. It can be omitted when assuming equal variances (that is, when var.equal=TRUE) and in this situation the common variance is assumed to be equal to par1.2.

rho

disease prevalence.

width

desired interval width.

costs

cost matrix. Costs should be entered as a 2x2 matrix, where the first row corresponds to the true positive and true negative costs and the second row to the false positive and false negative costs. Default cost values are a combination of costs that yields R=1, which is equivalent to the Youden index method (for details about this concept, see References). It must be set to NULL if the user prefers to set R (see next argument).

R

if the cost matrix costs is not set, R desired (the algorithm will choose a suitable combination of costs that leads to R). Default, NULL (which leads to R=1 using the default costs).

var.equal

a logical variable indicating whether to use equal variances. Default, FALSE.

alpha

significance level for the confidence interval. Default, 0.05.

Value

an object of class SS which is a list with eight components:

ss2

sample size for the diseased group

ss1

sample size for the healthy group

epsilon

sample size ratio between non-diseased and diseased subjects

width

width of the confidence interval provided by the user

alpha

significance level provided by the user

costs

cost matrix provided by the user

R

R term, the product of the non-disease odds and the cost ratio (for further details about this concept, see References)

prev

disease prevalence provided by the user

References

Skaltsa K, Jover L, Carrasco JL. (2010). Estimation of the diagnostic threshold accounting for decision costs and sampling uncertainty. Biometrical Journal 52(5):676-697.

Examples

par1.1 <- 0
par1.2 <- 1
par2.1 <- 2
par2.2 <- 1
rho <- 0.3
width <- 0.5
SS(par1.1, par1.2, par2.1, par2.2, rho, width, var.equal=TRUE)