lambdap: Distribution functions for the Lambda prime / non-central...

lambdapR Documentation

Distribution functions for the Lambda prime / non-central Lambda distribution

Description

Density, distribution function, quantile function and random generation for the lambda prime distribution.

Usage

dlambdap(x, df, ncp, log = FALSE)
plambdap(q, df, ncp, lower.tail = TRUE, log.p = FALSE)
qlambdap(p, df, ncp, lower.tail = TRUE, log.p = FALSE)
rlambdap(n, df, ncp)

dlambdap(x, df, ncp, log = FALSE)

plambdap(q, df, ncp, lower.tail = TRUE, log.p = FALSE)

qlambdap(p, df, ncp, lower.tail = TRUE, log.p = FALSE)

rlambdap(n, df, ncp)

Arguments

x, q

vector of quantiles

df

the degrees of freedom of the distribution

ncp

the non-centrality parameter (t) of the distribution

log, log.p

logical; if TRUE, probabilities / densities are given as logarithms

lower.tail

logical; if TRUE (default), probabilities are P[X <= x], otherwise, P[X > x]

p

vector of probabilities

n

number of observations

Details

These functions compute LeCoutre's Lambda prime \Lambda' distribution with df degrees of freedom (denoted df or \nu) and a non-centrality parameter (denoted ncp or t, and being the observed t-statistic). It is a continuous probability distribution that frequently arises in the sampling distribution of confidence limits for a normal mean and for inferences regarding signal-to-noise or standardized effect sizes. The distribution is generally asymmetric, and its shape adapts based on its parameters. When the non-centrality parameter (t) is zero, or if the degrees of freedom grow large (\chi^2_{df} / df \to 0), it reduces / converges to the standard normal distribution. Formally:

\Lambda'_{df}(t) = z + t \sqrt{\chi^2_{df} / df}

The non-central t distribution is the non-centrality parameter \Lambda plus the standard normal z distribution, all divided by the square root of the usual chi-square distribution divided by the degrees of freedom:

t'_{df}(\Lambda) = (\Lambda + z) / \sqrt{\chi^2_{df} / df}

A \Lambda' distributed random variable can be viewed as a confidence level on a non-central t (with the confidence intervals being computed as percent points of the \Lambda' distribution).

Value

dlambdap gives the density, plambdap gives the distribution function (probabilities), qlambdap gives the quantile function, and rlambdap generates a random vector with lambda prime distributed values.

References

LeCoutre, B. (2007). Another look at confidence intervals for the noncentral t distribution. Journal of Modern Applied Statistical Methods, 6(1), 107–116. https://doi.org/10.22237/jmasm/1177992600

See Also

t distribution functions: stats::dt(), stats::pt(), stats::qt(), and stats::rt().

Examples

set.seed(1)
dlambdap(11.1, df = 9, ncp = 10) # 0.1294471
plambdap(11.1, df = 9, ncp = 10) # 0.7134134
qlambdap(0.01, df = 9, ncp = 10) # 4.245347
rv <- rlambdap(100, df = 50, ncp = 2)
mean(rv) # 2.077029
pv <- plambdap(rv,  df = 50, ncp = 2)
summary(pv)
#     Min. 1st Qu.  Median    Mean 3rd Qu.    Max.
#  0.01715 0.31579 0.51642 0.52259 0.74839 0.99703
qv <- qlambdap(pv,  df = 50, ncp = 2)
summary(qv)
#     Min. 1st Qu.  Median    Mean 3rd Qu.    Max.
#  -0.1677  1.5007  2.0319  2.0770  2.6726  4.7966
# absolute difference between the original random vector and
# the quantile vector calculated from the probabilities of the
# original random vector (< 1e-12)
max(abs(qv - rv)) # 0.0000000000002498002


pwrss documentation built on Oct. 14, 2026, 9:06 a.m.