Prev Next initialize

@(@\newcommand{\R}[1]{ {\rm #1} } \newcommand{\B}[1]{ {\bf #1} } \newcommand{\W}[1]{ \; #1 \; }@)@This is cppad_mixed--20220519 documentation: Here is a link to its current documentation .
Initialization After Constructor

Syntax
Public
Purpose
mixed_object
fixed_vec
random_vec
size_map
     n_fixed
     n_random
     quasi_fixed
     A_nr
     A_nnz
     ran_like_fun.size_var
     fix_like_fun.size_var
     Other Fields
Example

Syntax
size_map = mixed_object.initialize(fixed_vec, random_vec)

Public
This cppad_mixed base_class member function is public.

Purpose
Some of the cppad_mixed initialization requires calling the derived class version of the ran_likelihood function. Hence this initialization cannot be done until after the derived constructor completes.

mixed_object
We use mixed_object to denote an object of a class that is derived from the cppad_mixed base class.

fixed_vec
This argument has prototype
     const CppAD::vector<double>& fixed_vec
 It specifies the value of the fixed effects vector @(@ \theta @)@ at which certain CppAD::ADFun objects are recorded.

random_vec
This argument has prototype
     const CppAD::vector<double>& random_vec
 It specifies the value of the random effects vector @(@ u @)@ at which certain CppAD::ADFun objects are recorded.

size_map
The return value has prototype
     std::map<std::string, size_t> size_map
 It represent the size of certain aspects of the problem.

n_fixed
the number of fixed effects.

n_random
the number of fixed effects.

quasi_fixed
If this is one (zero) are a using a quasi-Newton (Newton) method for optimizing the fixed effects.

A_nr
is the number of rows in the liner constraint matrix A (the matrix has n_fixed columns).

A_nnz
is the number of non-zeros in the liner constraint matrix A.

ran_like_fun.size_var
is the number of variables in the algorithm that maps the fixed and random effects to the part of the likelihood that depend on the random effects.

fix_like_fun.size_var
is the number of variables in the algorithm that maps the fixed effects to the part of the likelihood that does not depend on the random effects.

Other Fields
Not all the fields in size_map are specified, but they can be inspected. For example,
     std::map<std::string, size_t>::iterator itr;
     for(itr = size_map.begin(); itr != size_map.end(); itr++)
          std::cout << itr->first << " = " << itr->second << "\n";
Example
The file derived_ctor.cpp contains an example of using initialize.
Input File: src/initialize.cpp