Show Posts

This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.


Messages - dan_c

Pages: 1 ... 4 5 [6]
76
General Discussion / MOVED: Missing items and discrimination
« on: July 25, 2017, 01:07:29 AM »
This topic has been moved to Q&A.


77
Questions and Answers / Re: Missing items and discrimination
« on: July 23, 2017, 06:34:03 AM »
I'm not sure what you mean by "getting" the missing items. Item discrimination is reported in the output from a call to itanal.

Can you provide an example of what you are trying to do?

See this post for more info:

Some users want to ask questions, report bugs, or provide examples of functionality in ConQuest.

To make this easy and to ensure the members of the forum can follow along and reproduce the issue (and maybe contribute their own solutions), it would be helpful to post a minimum working example.
...

78
Questions and Answers / Re: Covariance matrix is not positive definite
« on: April 11, 2017, 08:14:52 AM »
The benefit of producing a minimum working example is twofold - the community gets to see a example it can replicate and potentially solve, and producing the example often weeds out errors related to messy real-world data and syntax. Could you edit tutorial 7 to add partial credit and cross loadings and see if you can replicate your error?

Note, the other common issue related to identification of within-item models:

Quote
If ConQuest is being used to estimate a model that has within-item multidimensionality, then the set command argument constraints=cases must be provided. ConQuest can be used to estimate a within-item multidimensional model without constraints=cases. This will, however, require the user to define and import a design matrix. The comprehensive description of how to construct design matrices for multidimensional models is beyond the scope of this manual.
ConQuest Command Reference p88.

79
Questions and Answers / Re: Covariance matrix is not positive definite
« on: April 06, 2017, 09:19:58 PM »
Can you create a small working example to replicate the problem?

https://conquest-forums.acer.edu.au/index.php?topic=1239.msg1475#msg1475

81
Questions and Answers / Re: Running a DIF analysis
« on: April 05, 2017, 09:03:28 AM »
Can you create a small working example to replicate the problem?

https://conquest-forums.acer.edu.au/index.php?topic=1239.msg1475#msg1475

82
ConQuest News / Minimum working examples
« on: February 14, 2017, 03:58:12 AM »
Some users want to ask questions, report bugs, or provide examples of functionality in ConQuest.

To make this easy and to ensure the members of the forum can follow along and reproduce the issue (and maybe contribute their own solutions), it would be helpful to post a minimum working example.

A minimum working example is the smallest possible example that illustrates a problem that is fully self contained. That is, any user should be able to recreate the issue using the syntax and data you provide.

ConQuest doesn't have any built in example data sets or analyses, but there is a notes and tutorial page that provides simple examples of syntax and data: https://www.acer.edu.au/conquest/notes-tutorials. Using these as the basis of a minimum working example has a few benefits:

  • The syntax is a simple starting point and avoids complex labelling, formatting, or analysis that users may include in their own analysis
  • The data is not proprietry or confidential and therefore there is no problem with sharing it on the forum

I have attached an example skeleton of a minimum working example. What do you think? Feel free to edit/change/offer suggestions...

83
Questions and Answers / Re: Monte carlo Multidimensional models
« on: February 14, 2017, 03:08:28 AM »
For info, I ran Example 7b (5 dimensions) with both default (Gauss - took a full week) and Monte Carlo estimation

Here's the output:

Quote
Estimation method was: Gauss-Hermite Quadrature with 759375 nodes
...
Cases in file: 583  Cases in estimation: 578
Final Deviance:     7948.35604
Akaike Information Criterion (AIC): 8090.35604
Total number of estimated parameters: 71
The number of iterations: 456

Quote
Estimation method was: MonteCarlo with 1000 nodes
...
Cases in file: 583  Cases in estimation: 578
Final Deviance:     7949.80685
Akaike Information Criterion (AIC): 8091.80685
Total number of estimated parameters: 71
The number of iterations: 258

This is the kind of difference in precision i would expect.

See:
https://www.acer.edu.au/files/Conquest-Tutorial-7-MultidimensionalModels.pdf

84
Questions and Answers / Re: Monte carlo Multidimensional models
« on: February 08, 2017, 12:10:03 AM »
You would expect small differences between the residual deviances for models using gauss (default) and montecarlo integration - due to differences in precision.

The large difference you mention does seem far too big. Can you produce a small, reproducible example (perhaps using the example datasets https://www.acer.edu.au/conquest/notes-tutorials)? Or alternatively, perhaps you an email me your data and syntax?

Pages: 1 ... 4 5 [6]