parallel_iter {Qval} | R Documentation |
A tool for the \beta
Method
Description
This function performs a single iteration of the \beta
method for A item's validation. It is designed
to be used in parallel computing environments to speed up the validation process of the \beta
method.
The function is a utility function for validation
, and it should not be called independently by the user.
Usage
parallel_iter(
i,
Y,
P.alpha.Xi,
P.alpha,
pattern,
ri,
Ni,
Q.pattern.ini,
model,
criter,
search.method,
P_GDINA,
Q.beta,
L,
K,
alpha.P,
get.MLRlasso,
priority
)
Arguments
i |
Item number that need to be validated. |
Y |
Observed data matrix for validation. |
P.alpha.Xi |
Individual posterior |
P.alpha |
Attribute prior weights. |
pattern |
The attribute mastery pattern matrix. |
ri |
A vector that contains the numbers of examinees in each knowledge state who correctly answered item |
Ni |
A vector that contains the total numbers of examinees in each knowledge state. |
Q.pattern.ini |
Initial pattern number for the model. |
model |
Model object used for fitting (e.g., GDINA). |
criter |
Fit criterion ("AIC", "BIC", "CAIC", or "SABIC"). |
search.method |
Search method for model selection ("beta", "ESA", "SSA", or "PAA"). |
P_GDINA |
Function to calculate probabilities for GDINA model. |
Q.beta |
Q-matrix for validation. |
L |
Number of latent pattern. |
K |
Number of attributes. |
alpha.P |
Individuals' marginal mastery probabilities matrix (Tu et al., 2022) |
get.MLRlasso |
Function for Lasso regression with multiple linear regression. |
priority |
Vector of priorities for PAA method search. |
Value
An object of class validation
is a list
containing the following components:
fit.index.pre |
The previous fit index value after applying the selected search method. |
fit.index.cur |
The current fit index value after applying the selected search method. |
Q.pattern.cur |
The pattern that corresponds to the optimal model configuration for the current iteration. |
priority |
The priority vector used in the PAA method, if applicable. |