Author Topic: syntax help - Rasch Testlet Model  (Read 41 times)

fishbook

  • Newbie
  • *
  • Posts: 3
    • View Profile
    • Email
syntax help - Rasch Testlet Model
« on: July 12, 2021, 04:14:43 PM »
Hello! If an instrument consists of only a reading passage with several dichotomous questions, how to code it into a Rasch testlet model compared to a Rasch model? Thank you!
« Last Edit: July 18, 2021, 05:39:55 AM by dan_c »

dan_c

  • Administrator
  • Full Member
  • *****
  • Posts: 109
    • View Profile
    • Email
Re: syntax help
« Reply #1 on: July 12, 2021, 11:45:18 PM »
can you share your data?

If you have a column that indicates which passage/testlet each record belongs to then you simply:

Code: [Select]
model item; /* Rasch Model */
Code: [Select]
model item + passage; /* Facet Model - gives average difficulty of each passage/testlet */
Code: [Select]
model item + passage + item*passage; /* Facet Model - gives average difficulty of each passage/testlet plus an item-by-passage interaction */
You can evaluate model fit by considering nested models: https://conquestmanual.acer.org/s2-00.html#s2-05

fishbook

  • Newbie
  • *
  • Posts: 3
    • View Profile
    • Email
Re: syntax help
« Reply #2 on: July 13, 2021, 04:03:53 AM »
Thanks for the answer! The data are just a bunch of 1's and 0's for the 7 questions following the prompt, such as

1011111
0111011

Sorry I did not explain it clearly. I guess the basic Rasch model can be coded like
model item;
like you pointed out above. However, for the Rasch testlet model (Wang & Wilson, 2005) to account for LID, I need to include the "score" statement in addition to the "model" statement above. Does the following look right to you? The tricky part for me is that the entire test consists of only one testlet. Thanks!

score (0,1) (0,1) (0,1) ! items (1-7) ;

dan_c

  • Administrator
  • Full Member
  • *****
  • Posts: 109
    • View Profile
    • Email
Re: syntax help
« Reply #3 on: July 16, 2021, 02:18:32 AM »
I'm not sure it makes sense to model a single testlet - that will yield a bifactor model where all items load on one testlet factor and one trait factor.

perhaps you can share more about what you are trying to achieve? 

fishbook

  • Newbie
  • *
  • Posts: 3
    • View Profile
    • Email
Re: syntax help
« Reply #4 on: July 17, 2021, 03:11:33 AM »
The goal is to figure out an analysis model for this kind of instrument with only one testlet. I am thinking the model fit between the Rasch model and the Rasch testlet model may not be very different. What do you think? Can you please tell me how to code the bifactor model? Thank you!

dan_c

  • Administrator
  • Full Member
  • *****
  • Posts: 109
    • View Profile
    • Email
Re: syntax help
« Reply #5 on: July 18, 2021, 05:39:21 AM »
of course.

Here is a good paper on specifying the bifactor model in ConQuest: https://www.ierinstitute.org/fileadmin/Documents/IERI_Monograph/IERI_Monograph_Volume_01_Chapter_3.pdf

Brandt, S. (2008). Estimation of a Rasch model including subdimensions. IERI Monograph Series. Issues and Methodologies in Large-Scale Assessments, 1, 51–70.

Note there are several ways of specifying a bifactor model.

The simplest specification is one where you assume the items are measuring a set of dimensions with a particular structure.  Typically each item is reflective of a combination of a general dimension and a specific dimension.  Every item loads on the general dimension, and a subset of items load on each specific dimensions. The specific dimensions are orthogonal to the general dimension.

In ConQuest this would mean you would impose a covariance constraint: the covariance between D1 (your general dimension) and D2 to Dd is anchored at 0, where d is the number of specific dimensions.

Attached is a worked example.