# catsim – Computerized Adaptive Testing Simulator¶

## Quick start¶

catsim is a computerized adaptive testing simulator written in Python 3.4. It allow for the simulation of computerized adaptive tests, selecting different test initialization rules, item selection rules, proficiency reestimation methods and stopping criteria.

Computerized adaptive tests are educational evaluations, usually taken by examinees in a computer or some other digital means, in which the examinee’s proficiency is evaluated after the response of each item. The new proficiency is then used to select a new item, closer to the examinee’s real proficiency. This method of test application has several advantages compared to the traditional paper-and-pencil method, since high-proficiency examinees are not required to answer all the easy items in a test, answering only the items that actually give some information regarding his or hers true knowledge of the subject at matter. A similar, but inverse effect happens for those examinees of low proficiency level.

catsim allows users to simulate the application of a computerized adaptive test, given a sample of examinees, represented by their proficiency levels, and an item bank, represented by their parameters according to some Item Response Theory model.

### Installation¶

Install it using pip install catsim.

### Dependencies¶

catsim depends on the latest versions of NumPy, SciPy, Matplotlib and scikit-learn, which are automatically installed from pip.

To run the tests, you’ll need to install the testing requirements pip install catsim[testing].

To generate the documentation, Sphinx and its dependencies are needed.

### Basic Usage¶

1. Have an item matrix;
2. Have a sample of examinee proficiencies, or a number of examinees to be generated;
3. Create an initializer, an item selector, a proficiency estimator and a stopping criterion;
4. Pass them to a simulator and start the simulation.
5. Access the simulator’s properties to get specifics of the results;
from catsim.initialization import RandomInitializer
from catsim.selection import MaxInfoSelector
from catsim.reestimation import HillClimbingEstimator
from catsim.stopping import MaxItemStopper
from catsim.cat import generate_item_bank
initializer = RandomInitializer()
selector = MaxInfoSelector()
estimator = HillClimbingEstimator()
stopper = MaxItemStopper(20)
Simulator(generate_item_bank(100), 10).simulate(initializer, selector, estimator, stopper)


### Citing catsim¶

You can cite the package using the following bibtex entry:

@misc{catsim,
author = {Meneghetti, Douglas De Rizzo},
title = {catsim: Computerized Adaptive Testing Simulator},
url = {http://douglasrizzo.github.io/catsim/},
year = {2016},
doi = {10.5281/zenodo.46259}
}