LeastSq Class Reference

Base class for the nonlinear least squares branch of the iterator hierarchy. More...

Inheritance diagram for LeastSq:

List of all members.

Protected Member Functions
	LeastSq ()
	default constructor
	LeastSq (Model &model)
	standard constructor
	LeastSq (NoDBBaseConstructor, Model &model)
	alternate constructor
	~LeastSq ()
	destructor
void	derived_pre_run ()
void	run ()
	run the iterator; portion of run_iterator()
void	derived_post_run ()
void	print_results (ostream &s)
virtual void	minimize_residuals ()=0
	for the least squares branch.
void	read_observed_data ()
	read user data file to load observed data points
void	get_confidence_intervals ()
	Calculate confidence intervals on estimated parameters.
Static Protected Member Functions
static void	primary_resp_recast (const Variables &native_vars, const Variables &scaled_vars, const Response &native_response, Response &scaled_response)
	(user) to iterator space
Protected Attributes
int	numLeastSqTerms
	number of least squares terms
LeastSq *	prevLSqInstance
	pointer containing previous value of leastSqInstance
bool	weightFlag
	flag indicating whether weighted least squares is active
String	obsDataFilename
	filename from which to read observed data
bool	obsDataFlag
	flag indicating whether user-supplied data is active
RealVector	obsData
	storage for user-supplied data for computing residuals
RealVector	confBoundsLower
	lower bounds for confidence intervals on calibration parameters
RealVector	confBoundsUpper
	upper bounds for confidence intervals on calibration parameters
Static Protected Attributes
static LeastSq *	leastSqInstance
	pointer to LeastSq instance used in static member functions

---

Detailed Description

Base class for the nonlinear least squares branch of the iterator hierarchy.

The LeastSq class provides common data and functionality for least squares solvers (including NL2OL, NLSSOLLeastSq, and SNLLLeastSq.

---

Constructor & Destructor Documentation

LeastSq

(

Model &

model

)

[protected]

standard constructor

This constructor extracts the inherited data for the least squares branch and performs sanity checking on gradient and constraint settings.

---

Member Function Documentation

void derived_pre_run

(

)

[protected, virtual]

This function should be invoked (or reimplemented) by any derived implementations of derived_pre_run() (which would otherwise hide it).

Reimplemented from Minimizer.

Reimplemented in SNLLLeastSq.

void run

(

)

[inline, protected, virtual]

run the iterator; portion of run_iterator()

Iterator supports a construct/pre-run/run/post-run/destruct progression. This function is the virtual run function for the iterator class hierarchy. All derived classes need to redefine it.

Reimplemented from Iterator.

void derived_post_run

(

)

[protected, virtual]

Implements portions of post_run specific to LeastSq for scaling back to native variables and functions. This function should be invoked (or reimplemented) by any derived implementations of derived_post_run() (which would otherwise hide it).

Reimplemented from Minimizer.

Reimplemented in SNLLLeastSq.

void print_results

(

ostream &

s

)

[protected, virtual]

Redefines default iterator results printing to include nonlinear least squares results (residual terms and constraints).

Reimplemented from Iterator.

void primary_resp_recast	(	const Variables &	native_vars,
		const Variables &	scaled_vars,
		const Response &	native_response,
		Response &	iterator_response
	)			[static, protected]

(user) to iterator space

Least squares function map from user/native space to iterator/scaled space using a RecastModel. If no scaling also copies constraints.

void read_observed_data

(

)

[protected]

read user data file to load observed data points

read user's observation data for computation of least squares residuals (currently reading on all processors -- need to read once and broadcast)

void get_confidence_intervals

(

)

[protected]

Calculate confidence intervals on estimated parameters.

Calculate individual confidence intervals for each parameter. These bounds are based on a linear approximation of the nonlinear model.

---

The documentation for this class was generated from the following files:

• DakotaLeastSq.H
• DakotaLeastSq.C

---