Concentration models
Let denote a random variable from a lognormal distribution. Then, the log transformed variable is normally distributed with and variance .
The probability density function (p.d.f.) of y may be expressed as:
where is the limit of reporting and is an indicator function for . For the p.d.f. of reduces to the usual lognormal density.
The left truncated density for may be expressed as:
with the standard normal c.d.f. and .
Model parameters are estimated using maximum likelihood estimation based on the loglikelihood functions specified below. The loglikelihood functions are evaluated in R, using the optim algorithm to find estimates for and .
Mixture zero spike and censored lognormal
The loglikelihood may be expressed as:
where , is the standard normal c.d.f., , with number of censored values number of uncensored values and .
Multiple values for LOR are allowed.
Censored lognormal
When the loglikelihood reduces to:
Multiple values for LOR are allowed.
Mixture censored spike and truncated lognormal
Ignoring the values below , the loglikelihood may be expressed as:
Only one value for LOR is allowed.
Mixture censored spike and lognormal
Ignoring the values below , the loglikelihood may be expressed as:
Only one value for LOR is allowed.