Object containing information about estimated model quantities
The estimatedInfo
object contains information about estimated model
quantities (species, parameters, or compartments). Use this object to
specify which quantities in a SimBiology^{®} model are estimated, what parameter transforms are used, and
optionally, the initial estimates for these quantities when using sbiofit
or sbiofitmixed
.
creates
an empty estimInfo
= estimatedInfoestimatedInfo
object.
creates
an array of estimInfoArray
= estimatedInfo(transformedNames
)estimatedInfo
objects for quantities
specified in transformedNames
. The initial values
for these quantities are obtained from the SimBiology model when you
run sbiofit
or sbiofitmixed
.
defines
the initial transformed values of model quantities specified by estimInfoArray
= estimatedInfo(___,'InitialTransformedValue',itValues
)itValues
.
You cannot specify this namevalue pair along with the 'InitialValue'
namevalue
pair.
defines
the initial values of model quantities specified by estimInfoArray
= estimatedInfo(___,'InitialValue',iValues
)iValues
.
You cannot specify this namevalue pair along with the 'InitialTransformedValue'
namevalue
pair.
defines
the lower and upper bounds for parameter estimation specified by estimInfoArray
= estimatedInfo(___,'Bounds',boundValues
)boundValues
.
You cannot specify this namevalue pair along with the 'TransformedBounds'
namevalue
pair. All methods support parameter bounds in sbiofit
(that
is, fminsearch
, nlinfit
(Statistics and Machine Learning Toolbox), fminunc
(Optimization Toolbox), fmincon
(Optimization Toolbox), lsqcurvefit
(Optimization Toolbox), lsqnonlin
(Optimization Toolbox), patternsearch
(Global Optimization Toolbox), ga
(Global Optimization Toolbox), particleswarm
(Global Optimization Toolbox),
and scattersearch).
When using fminsearch
, nlinfit
,
or fminunc
with bounds, the objective function
returns Inf
if bounds are exceeded. When you turn
on options such as FunValCheck
, the optimization
may error if bounds are exceeded during estimation. If using nlinfit
,
it may report warnings about the Jacobian being illconditioned or
not being able to estimate if the final result is too close to the
bounds. sbiofitmixed
does not
support parameter bounds.
defines
the transformed bounds for parameter estimation specified by estimInfoArray
= estimatedInfo(___,'TransformedBounds',tBoundValues
)tBoundValues
.
You cannot specify this namevalue pair along with the 'Bounds'
namevalue
pair.
defines
which groups in the data have separate estimated values for parameters.
In other words, this allows you to estimate parameter values specific
for each group or category. For example, you can estimate parameters
based on individuals’ age or sex.estimInfoArray
= estimatedInfo(___,'CategoryVariableName',groups
)
Name  Character vector indicating the name of an estimated model quantity. Changing this
property also updates the 
Transform  Character vector indicating whether the quantity value is transformed during
estimation. Valid names are A log transform
ensures that the component value is always positive during estimation. The
The The logit function, which is the
inverse of sigmoid function, is defined as 
TransformedName  Readonly character vector that combines the transform name (such as

InitialValue  Empty matrix Changing this property
automatically updates the 
InitialTransformedValue  Empty matrix Changing this
property automatically updates the 
Bounds  Empty matrix The lower bound must be less than the upper bound. 
TransformedBounds  Empty matrix The lower bound must be less than the upper bound. 
CategoryVariableName  Character vector or cell array of character vectors specifying which groups in the data
have separate estimated values for the parameter. The character vector can be the name of a
variable in the data used for fitting or one of the keywords:
If you specify 
sbiofit
 sbiofitmixed
 groupedData
object
 CovariateModel object