Description
The [INDIVIDUAL] section is used to define a probability distribution for model parameters. It is used to model interindividual variability for given parameters.
Scope
The [INDIVIDUAL] section is used in Mlxtran models for simulation with Mlxplore or Simulx. It is only needed for models that have parameters with interindividual variability. Mlxtran models for Monolix do not need this section because the parameter distributions are defined via the user interface.
Inputs
The inputs for the [INDIVIDUAL] section are the parameters that are declared in the input = { } list of the [INDIVIDUAL] section. These parameters are obtained from the [COVARIATE] section or from the executing program that can be Mlxplore or an Rscript in the case of Simulx.
Outputs
Every parameter that has been defined in the [INDIVIDUAL] section can be an output. Outputs from the [INDIVIDUAL] section are always an input for the [LONGITUDINAL] section. [INDIVIDUAL] output to [LONGITUDINAL] input matching is made by matching parameter names in the [INDIVIDUAL] section with parameters in the inputs = { } list of the [LONGITUDINAL] section.
Usage
The definition of probability distribution for a model parameter is done with the EQUATION: and DEFINITION: blocks. The EQUATION: block contains mathematical equations and the DEFINITION: block is used to definite probability distributions. The following syntax applies to define a probability distribution for the random variable X:
DEFINITION: X = {distribution= distributionType, parameter1 = Var1, covariate = c, coefficient = beta, parameter2 = Var2}
The arguments to the probability distribution definition are
 distributionType: is one of the following reserved keywords: normal, lognormal, logitnormal, or probitnormal. For use in Simulx, the keyword uniform is also accepted.
 parameter1: is one of the following reserved keywords: mean or typical
 parameter2: is one of the following reserved keywords: sd or var
 Var1: is a double number or a parameter
 Var2: is a double number or a parameter
 c = {..}: is a list of strings referring to the covariates
 beta = {…}: is a list of strings referring to the covariate coefficients
The reserved keywords meanings are
 normal: normal distribution:
 lognormal: lognormal distribution:
 logitnormal: logitnormal distribution:
 probitnormal: probitnormal distribution: , where is the cumulative distribution function of the distribution.
 mean: is the mean of the normal distribution
 typical: is the transformed mean
 sd: is the standard deviation of the normal distribution. If no variability is required, the user can set “novariability” and novariability will be computed
 var: is the variance of the normal distribution
 min: the lower bound of the interval for logitnormal or probitnormal distributions (default is 0)
 max: the upper bound of the interval for logitnormal or probitnormal distributions (default is 1)
These probability distribution are all Gaussian probability distributions that are defined through the existence of a monotonic transformation such that is normally distributed. Notice that the mean, standard deviation, and variance refer to the normal distributed variable. In pharmacometrics it is more common to use the typical value of the distribution. This is achieved by using the keyword typical instead of mean in the definition of the random variable. The relationship between the mean value and the typical value is the following:
where . Thus, typical is in the variable referential, while mean is in the transformed referential.
Examples

The parameter ka below is defined with a lognormal distribution, a typical value ka_pop and a standard deviation for the random effect omega_ka:
ka = {distribution=logNormal, typical=ka_pop, sd=omega_ka}

The parameter F below is defined with a logitnormal distribution in the interval [0,1], a typical value F_pop and no random effect.
F = {distribution=logitNormal, typical=F_pop, novariability}
 The parameter V below is defined with a logitnormal distribution in the interval [0.2,5], a typical value V_pop and a standard deviation for the random effect omega_V:
V = {distribution=logitNormal, min=0.2, max=5, typical=V_pop, sd=omega_V}

The parameter fu below is defined with a uniform distribution in the interval [0.2,0.6] (not accepted in Monolix):
fu = {distribution=uniform, min=0.2, max=0.6}
General probability distributions and inclusion of covariates
Linear Gaussian models with covariates
A linear Gaussian statistical model for the variable assumes that there exists a transformation , a typical value , a vector of individual covariates , a vector of coefficients and a random variable normally distributed such that
This model can be implemented with Mlxtran
, using the keywords typical, covariate and coefficient.
input = {Xpop, beta1, beta2, c1, c2, omega} DEFINITION: X = {distribution=lognormal, typical=Xpop, covariate={c1,c2}, coefficient={beta1,beta2}, sd=omega}
The keyword covariate is used to define the name of the covariates used in the correlation, and the coefficient keyword is used to complete the equation. Obviously, the number of parameters in the coefficient is equal to the number of covariates.
Non linear Gaussian model with covariates
A nonlinear Gaussian statistical model for the variable assumes that there exists a transformation , a vector of individual covariates , a vector of coefficients , a function and a random variable normally distributed such that
The mean of can be defined in a block DEFINITION:, with for example
input = {beta1, beta2, c1, c2, omega} EQUATION: mu = beta1*c1/(beta2 + c2) DEFINITION: X = {distribution=lognormal, mean=mu, sd=omega}
Non Gaussian model with covariates
Non Gaussian model for can be defined, at the condition that can be defined as a nonlinear function of normally distributed random variables. For example, let
It is not possible to express explicitly the distribution of as a transformation of a normal distribution. We therefore need a block EQUATION: for implementing this model:
input = {beta1, beta2, omega1, omega2} DEFINITION: eta1 = {distribution=normal, mean=0, sd=omega1} eta2 = {distribution=normal, mean=0, sd=omega2} EQUATION: X = (beta1 + eta1)/(1+beta2*exp(eta2))
Rules
 When defining a distribution with covariate, one can not define numerically the coefficients. For example, if we consider , one should write
input = {c} EQUATION: beta = 1 DEFINITION : X = {distribution=normal, typical=Xpop, covariate=c, coefficient=beta, sd=omega}
and define in the section <PARAMETER> or define it in an EQUATION: block. Otherwise, putting directly 1 instead of in the distribution definition will lead to an error.
 We strongly advise to define the distribution in the more synthetic way. If for example, you want to define a lognormally distributed volume with a dependence w.r.t. the weight , we encourage you not to define a lot of equations but to summarize it in the definition as for example
input = {Vpop, w, beta} EQUATION: cov = w/70 DEFINITION: V = {distribution=normal, typical=Vpop, covariate=cov, coefficient=beta, sd=omega}