MKinfer (version 1.3)

mdplot: Visualize MD.

Description

The function visualizes the mean difference (MD) of two groups, assuming two normal distributions. In addition, the sensitivity and specificity based on the optimal cutoff (Youden's J statistic) can be added.

Usage

mdplot(delta, sd1 = 1, sd2 = 1, constant = 3, n = 501, alpha = 0.25, 
        lwd = 1, col1 = "darkblue", col2 = "darkred", xlim, 
        addSens = TRUE, digits = 3)

Value

ggplot object

Arguments

delta

(absolute) mean difference of the two groups.

sd1

standard deviation of first group.

sd2

standard deviation of second group.

constant

used to define the plot range (constant*sd).

n

integer; the number of values at which the two normal densities are evaluated.

alpha

opacity used for geom_area.

lwd

linewidth of the plotted lines.

col1

color of density of first group.

col2

color of density of second group.

xlim

limits of x-axis. If missing, calculated based on constant and the specified SDs.

addSens

logical; should sensitivity and specificity be added to the plot.

digits

number of digits used for sensitivity and specificity.

Author

Matthias Kohl

Details

The function can be used to demonstrate (standardized) effect sizes and how these effect sizes transform into sensitivities and specificities.

The two standard diviations are assumed to be equal if their difference is smaller than 1e-08.

References

B\"ohning D, B\"ohning W, Holling H (2008). Revisiting Youden's index as a useful measure of the misclassification error in meta-analysis of diagnostic studies. Stat Methods Med Res. 17(6), 543-54.

J.H. Zhang, T.D.Y. Chung and K.R. Oldenburg (1999). A simple statistical parameter for use in evaluation and validation of high throughput screening assays. Journal of Biomolecular Screening 4 (2): 67-73.

Examples

## small effect size
mdplot(delta = 0.2)
## medium effect size
mdplot(delta = 0.5)
## large effect size
mdplot(delta = 0.8)
## z-factor = 0  (z-factor = 1 - 3*2*sd/delta); see Zhang et al. (1999)
mdplot(delta = 6)
## z-factor = 0.5  (z-factor = 1 - 3*2*sd/delta); see Zhang et al. (1999)
mdplot(delta = 12)

## unequal variances
mdplot(delta = 0.8, sd1 = 1, sd2 = 2)
mdplot(delta = 0.8, sd1 = 2, sd2 = 1)