Item Characteristic Curves
Plots of item characteristic curves can be obtained by selecting this option. ConstructMap produces probability curves for P(x=0) through P(x=max score) on the item selected by the user.
- Select Item Characteristic Curves from the menu.
- Set the ICC Map Options, as shown in Table 1 below, then click OK.
- The graphic is automatically saved as a jpeg file in the folder specified in step 2, but you can use File – Save As PNG to save it in the Portable Network Graphics format, which may produce a higher quality image for print or web pages and usually produces a smaller file.
- Print the graphic using File – Print.
- Close the window by clicking on the OK button.
|Title||The title you provide will appear at the top of the map.|
|File Name||Use the Browse... button to select the folder you want and then enter the filename you want the map to be stored in. ConstructMap will automatically store the report as a jpeg file, so you do not need to add the .jpg to your filename.|
|Item||Browse... to the Item Set and then to the item that you want to be graphed.|
|Ability on X-Axis||Select Yes if you want proficiencies (in logits) along the x-axis. Select No if you want proficiencies along the y-axis.|
|Min Range||Enter the minimum logit value to be displayed.|
|Max Range||Enter the maximum logit value to be displayed.|
|Show in Grayscale||Select the Yes option if you want the entire map, including the probability curves, to be displayed in black and white. Selecting this option activates an automatic selecting of different line styles.|
|Background Color||Click the Change Color button to modify the background color for the map. You may find the map easier to read and reproduce if you select white as the background color.|
As shown in Figure 2, an expected probability curve for each possible score on the item has been drawn. The item and the Item Set it belongs to are included in the title area of the graph.
The intersections of the curves indicate the points at which it is equally likely for a student to get a response at the two levels. In this example, a student with an ability location near -1.0 is equally likely to achieve a score of 0 or 1 on the item, and this is the location of item 1, step 1. A student with an ability location near 0.25 is equally likely to achieve a score of 1 or 2 on the item, and this is the location of item 1, step 2. We might also note in this example that students with an ability level of about -0.5 are equally likely to achieve a score of 0 or 2, but that it is more likely for students at this level to achieve a score of 1 on the item.