8.6 Item Response Model
- Miles Skinner (Unlicensed)
Report showing two facet IRT model and Item characteristic curve. Note: assumptions are made around size of cohort.
Item Response Theory
Item | Description | Useful links |
|---|---|---|
Difficulty | 3Pl model | https://docs.scipy.org/doc/scipy/reference/generated/scipy.optimize.curve_fit.html |
Discrimination | 3PL modle | https://docs.scipy.org/doc/scipy/reference/generated/scipy.optimize.curve_fit.html |
Pseudo-guess | This is only showed if it is more than 1. 3PL model | |
Chi-squared test |
| https://docs.scipy.org/doc/scipy/reference/generated/scipy.optimize.curve_fit.html |
In addition to the Scipy links, here is the wiki page that describes the 3 parameters above for IRT.
Item Characteristic curve (Passing Probability)
Classical Test Theory
Item | Description | Useful links |
|---|---|---|
Facility | facility = mean_score of the station / max_score of the station |
|
Discrimination (point-biserial) | The item discrimination index is a point biserial correlation coefficient. Its possible range is -1.00 to 1.00. A positive result indicates that there is a high correlation between higher performing candidates giving a correct response to the item. | |
Frequency | In SBA item type frequency of answers is calculated. If candidate have not responded it is included in calculation. Facility and Frequency of most chosen answer should be the same. From Practique 5.4.0 > , beside answer letters columns for Frequency there is No Response column as well to show the whole picture. |
|