OscatsAlgEstimate

OscatsAlgEstimate

Synopsis

struct              OscatsAlgEstimate;

Object Hierarchy

  GObject
   +----GInitiallyUnowned
         +----OscatsAlgorithm
               +----OscatsAlgEstimate

Properties

  "Dprior"                   GGslVector*           : Read / Write
  "Nposterior"               guint                 : Read / Write / Construct
  "Sigma"                    GGslMatrix*           : Read / Write
  "independent"              gboolean              : Read / Write
  "modelKey"                 gchar*                : Read / Write
  "mu"                       GGslVector*           : Read / Write
  "posterior"                gboolean              : Read / Write
  "thetaKey"                 gchar*                : Read / Write
  "tol"                      gdouble               : Read / Write / Construct

Description

Details

struct OscatsAlgEstimate

struct OscatsAlgEstimate;

Statistics algorithm ("administered"). Update the examinee's latent IRT ability estimate.

Property Details

The "Dprior" property

  "Dprior"                   GGslVector*           : Read / Write

Prior distribution for discrete dimensions as a vector of probabilities for all Prod_i n_i patterns, where n_i is the number of categories for discrete dimension i. The values should be ordered so that the lowest numbered binary dimension increases fasted, and the ordinal dimensions follow binary dimensions. The probabilities should sum to 1. Default: uniform. Note, this is used only when "posterior" is TRUE.


The "Nposterior" property

  "Nposterior"               guint                 : Read / Write / Construct

For the first N items, use Expected A Posteriori (EAP) estimation for continuous dimensions and Maximum A Posteriori (MAP) estimation for discrete dimensions. Switch to Maximum Likelihood (MLE) estimation after N items have been recorded. Note, EAP/MAP is always used as a fallback if the MLE fails to converge, e.g. for perfect response patterns.

Default value: 0


The "Sigma" property

  "Sigma"                    GGslMatrix*           : Read / Write

Population covariance matrix for the normal prior under EAP. (Note: The value is copied.) Default: identity.


The "independent" property

  "independent"              gboolean              : Read / Write

Continuous and discrete dimensions are independent.

Default value: TRUE


The "modelKey" property

  "modelKey"                 gchar*                : Read / Write

The key indicating which model to use for estimation. A NULL value or empty string indicates the item's default model.

Default value: NULL


The "mu" property

  "mu"                       GGslVector*           : Read / Write

Population mean for the normal prior under EAP. (Note: The value is copied.) Default: 0.


The "posterior" property

  "posterior"                gboolean              : Read / Write

Always use Expected A Posteriori (EAP) estimation for continuous dimensions and Maximum A Posteriori (MAP) estimation for discrete dimensions, instead of Maximum Likelihood (MLE). Note, EAP/MAP is always used as a fallback if the MLE fails to converge, e.g. for perfect response patterns.

Default value: FALSE


The "thetaKey" property

  "thetaKey"                 gchar*                : Read / Write

The key indicating which latent variable to use for estimation. A NULL value or empty string indicates the examinee's default estimation theta.

Default value: NULL


The "tol" property

  "tol"                      gdouble               : Read / Write / Construct

Tolerance for Newton-Raphson maximization (algorithm iterates until largest change in any dimension is less than tolerance).

Allowed values: >= G_MINDOUBLE

Default value: 1e-06