- Notifications
You must be signed in to change notification settings - Fork71
psychometrics package, including MIRT(multidimension item response theory), IRT(item response theory),GRM(grade response theory),CAT(computerized adaptive testing), CDM(cognitive diagnostic model), FA(factor analysis), SEM(Structural Equation Modeling) .
License
inuyasha2012/pypsy
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
psychometrics package, including structural equation model, confirmatoryfactor analysis, unidimensional item response theory, multidimensionalitem response theory, cognitive diagnosis model, factor analysis andadaptive testing. The package is still a doll. will be finished infuture.
- binary response data IRT (two parameters, three parameters).
- grade respone data IRT (GRM model)
- EM algorithm (2PL, GRM)
- MCMC algorithm (3PL）
The approximate polychoric correlation is calculated, and the slopeinitial value is obtained by factor analysis of the polychoriccorrelation matrix.
- E step uses GH integral.
- M step uses Newton algorithm (sparse matrix is divided into nonsparse matrix).
Gradient projection algorithm
GH integrals can only estimate low dimensional parameters.
- Dina
- ho-dina
- EM algorithm
- MCMC algorithm
- maximum likelihood estimation (only for estimating skill parametersof subjects)
- contains three parameter estimation methods(ULS, ML and GLS).
- based on gradient descent
- can be used for continuous data, binary data and ordered data.
- based on gradient descent
- binary and ordered data based on Polychoric correlation matrix.
For the time being, only for the calculation of full information itemfactor analysis, it is very simple.
principal component analysis
gradient projection
Thurston IRT model (multidimensional item response theory model forpersonality test)
Maximum information method for multidimensional item response theory
- numpy
- progressbar2
pip install psy
See demo
- theta parameterization of CCFA
- parameter estimation of structural equation models for multivariatedata
- Bayesin knowledge tracing (Bayesian knowledge tracking)
- multidimensional item response theory (full information item factoranalysis)
- high dimensional computing algorithm (adaptive integral, etc.)
- various item response models
- cognitive diagnosis model
- G-DINA model
- Q matrix correlation algorithm
- Factor analysis
- maximum likelihood estimation
- various factor rotation algorithms
- adaptive
- adaptive cognitive diagnosis
- other adaption model
- standard error and P value
- code annotation, testing and documentation.
About
psychometrics package, including MIRT(multidimension item response theory), IRT(item response theory),GRM(grade response theory),CAT(computerized adaptive testing), CDM(cognitive diagnostic model), FA(factor analysis), SEM(Structural Equation Modeling) .