ZeroModifiedLognormal {EnvStats}  R Documentation 
Density, distribution function, quantile function, and random generation
for the zeromodified lognormal distribution with parameters meanlog
,
sdlog
, and p.zero
.
The zeromodified lognormal (delta) distribution is the mixture of a lognormal distribution with a positive probability mass at 0.
dzmlnorm(x, meanlog = 0, sdlog = 1, p.zero = 0.5)
pzmlnorm(q, meanlog = 0, sdlog = 1, p.zero = 0.5)
qzmlnorm(p, meanlog = 0, sdlog = 1, p.zero = 0.5)
rzmlnorm(n, meanlog = 0, sdlog = 1, p.zero = 0.5)
x 
vector of quantiles. 
q 
vector of quantiles. 
p 
vector of probabilities between 0 and 1. 
n 
sample size. If 
meanlog 
vector of means of the normal (Gaussian) part of the distribution on the
log scale. The default is 
sdlog 
vector of (positive) standard deviations of the normal (Gaussian)
part of the distribution on the log scale. The default is 
p.zero 
vector of probabilities between 0 and 1 indicating the probability the random
variable equals 0. For 
The zeromodified lognormal (delta) distribution is the mixture of a
lognormal distribution with a positive probability mass at 0. This distribution
was introduced without a name by Aitchison (1955), and the name
\Delta
distribution was coined by Aitchison and Brown (1957, p.95).
It is a special case of a “zeromodified” distribution
(see Johnson et al., 1992, p. 312).
Let f(x; \mu, \sigma)
denote the density of a
lognormal random variable X
with parameters
meanlog=
\mu
and sdlog=
\sigma
. The density function of a
zeromodified lognormal (delta) random variable Y
with parameters
meanlog=
\mu
, sdlog=
\sigma
, and p.zero=
p
,
denoted h(y; \mu, \sigma, p)
, is given by:
h(y; \mu, \sigma, p) =  p  for y = 0 
(1  p) f(y; \mu, \sigma)  for y > 0

Note that \mu
is not the mean of the zeromodified lognormal
distribution on the log scale; it is the mean of the lognormal part of the
distribution on the log scale. Similarly, \sigma
is
not the standard deviation of the zeromodified lognormal distribution
on the log scale; it is the standard deviation of the lognormal part of the
distribution on the log scale.
Let \gamma
and \delta
denote the mean and standard deviation of the
overall zeromodified lognormal distribution on the log scale. Aitchison (1955)
shows that:
E[log(Y)] = \gamma = (1  p) \mu
Var[log(Y)] = \delta^2 = (1  p) \sigma^2 + p (1p) \mu^2
Note that when p.zero=
p
=0
, the zeromodified lognormal
distribution simplifies to the lognormal distribution.
dzmlnorm
gives the density, pzmlnorm
gives the distribution function,
qzmlnorm
gives the quantile function, and rzmlnorm
generates random
deviates.
The zeromodified lognormal (delta) distribution is sometimes used to model chemical concentrations for which some observations are reported as “Below Detection Limit” (the nondetects are assumed equal to 0). See, for example, Gilliom and Helsel (1986), Owen and DeRouen (1980), and Gibbons et al. (2009, Chapter 12). USEPA (2009, Chapter 15) recommends this strategy only in specific situations, and Helsel (2012, Chapter 1) strongly discourages this approach to dealing with nondetects.
A variation of the zeromodified lognormal (delta) distribution is the zeromodified normal distribution, in which a normal distribution is mixed with a positive probability mass at 0.
One way to try to assess whether a zeromodified lognormal (delta),
zeromodified normal, censored normal, or censored lognormal is the best
model for the data is to construct both censored and detectsonly probability
plots (see qqPlotCensored
).
Steven P. Millard (EnvStats@ProbStatInfo.com)
Aitchison, J. (1955). On the Distribution of a Positive Random Variable Having a Discrete Probability Mass at the Origin. Journal of the American Statistical Association 50, 901908.
Aitchison, J., and J.A.C. Brown (1957). The Lognormal Distribution (with special reference to its uses in economics). Cambridge University Press, London. pp.9499.
Crow, E.L., and K. Shimizu. (1988). Lognormal Distributions: Theory and Applications. Marcel Dekker, New York, pp.4751.
Gibbons, RD., D.K. Bhaumik, and S. Aryal. (2009). Statistical Methods for Groundwater Monitoring. Second Edition. John Wiley and Sons, Hoboken, NJ.
Gilliom, R.J., and D.R. Helsel. (1986). Estimation of Distributional Parameters for Censored Trace Level Water Quality Data: 1. Estimation Techniques. Water Resources Research 22, 135146.
Helsel, D.R. (2012). Statistics for Censored Environmental Data Using Minitab and R. Second Edition. John Wiley and Sons, Hoboken, NJ, Chapter 1.
Johnson, N. L., S. Kotz, and A.W. Kemp. (1992). Univariate Discrete Distributions. Second Edition. John Wiley and Sons, New York, p.312.
Owen, W., and T. DeRouen. (1980). Estimation of the Mean for Lognormal Data Containing Zeros and LeftCensored Values, with Applications to the Measurement of Worker Exposure to Air Contaminants. Biometrics 36, 707719.
USEPA (1992c). Statistical Analysis of GroundWater Monitoring Data at RCRA Facilities: Addendum to Interim Final Guidance. Office of Solid Waste, Permits and State Programs Division, US Environmental Protection Agency, Washington, D.C.
USEPA. (2009). Statistical Analysis of Groundwater Monitoring Data at RCRA Facilities, Unified Guidance. EPA 530/R09007, March 2009. Office of Resource Conservation and Recovery Program Implementation and Information Division. U.S. Environmental Protection Agency, Washington, D.C.
ZeroModified Lognormal (Alternative Parameterization),
Lognormal, LognormalAlt,
ZeroModified Normal,
ezmlnorm
, Probability Distributions and Random Numbers.
# Density of the zeromodified lognormal (delta) distribution with
# parameters meanlog=0, sdlog=1, and p.zero=0.5, evaluated at
# 0, 0.5, 1, 1.5, and 2:
dzmlnorm(seq(0, 2, by = 0.5))
#[1] 0.50000000 0.31374804 0.19947114 0.12248683
#[5] 0.07843701
#
# The cdf of the zeromodified lognormal (delta) distribution with
# parameters meanlog=1, sdlog=2, and p.zero=0.1, evaluated at 4:
pzmlnorm(4, 1, 2, .1)
#[1] 0.6189203
#
# The median of the zeromodified lognormal (delta) distribution with
# parameters meanlog=2, sdlog=3, and p.zero=0.1:
qzmlnorm(0.5, 2, 3, 0.1)
#[1] 4.859177
#
# Random sample of 3 observations from the zeromodified lognormal
# (delta) distribution with parameters meanlog=1, sdlog=2, and p.zero=0.4.
# (Note: The call to set.seed simply allows you to reproduce this example.)
set.seed(20)
rzmlnorm(3, 1, 2, 0.4)
#[1] 0.000000 0.000000 3.146641