Censored data paired t-test
Performs a parametric test of whether the mean difference between two columns of paired censored data equals 0. Assumes that the paired differences follow a gaussian (normal) distribution.
cen_paired(xd, xc, yd, yc, alternative = "two.sided", printstat = TRUE)
xd: The first column of data values plus detection limitsxc: The column of censoring indicators, where 1 (or TRUE) indicates a detection limit in the xd column, and 0 (or FALSE) indicates a detected value in xd.yd: The second column of data values plus detection limits, or a single number representing a standard / guideline value.yc: The column of censoring indicators for yd, where 1 (or TRUE) indicates a detection limit in the yd column, and 0 (or FALSE) indicates a detected value in yd. Not needed if yd is a single standard number.alternative: The usual notation for the alternate hypothesis. Default is “two.sided”. Options are “greater” or “less”.printstat: Logical TRUE/FALSE option of whether to print the resulting statistics in the console window, or not. Default is TRUE.A list of statistics containing the following components:
n Number of observationsZ The value of the test statisticp.value the p-value of the testMean difference the mean difference between xd and ydYou may also test for whether the mean of the xd data exceeds a standard by entering the single number for the standard as yd. In that case no yc is required.
data(atrazine) cen_paired(atrazine$June,atrazine$JuneCen,atrazine$Sept,atrazine$SeptCen) # Comparing standard/guieline value cen_paired(atrazine$June, atrazine$JuneCen, 0.01, alternative = "greater")
Helsel, D.R., 2011. Statistics for Censored Environmental Data using Minitab and R, 2nd ed. John Wiley & Sons, USA, N.J.
survival::survreg