Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Data preparation for Multilevel and Item Response Models
From
Scott Baldwin <[email protected]>
To
[email protected]
Subject
Re: st: Data preparation for Multilevel and Item Response Models
Date
Wed, 20 Apr 2011 18:30:12 -0600
Try the following.
*some item level data in wide format
webuse bg2, clear
*6 items
*reshape to long format
reshape long bg2cost, i(clinid) j(item)
*the gen option of tabulate will create the dummy variables -- one for each item
*add the quietly prefix to suppress the tabulate outpute
tabulate item, gen(item)
Depending on how your data are structured you may need to do make some
adjustments.
Best,
Scott
On Wed, Apr 20, 2011 at 3:12 PM, Christopher Sanford <[email protected]> wrote:
> I am attempting to run a factor analysis for binary data and am requesting help
> in preparing my data. Before running GLLAMM I know that I I need to do three
> things:
>
> 1. Create dummy variables for each of the test items
> 2. Stack the item responses
> 3. Reshape the data into long form
>
> How do I create dummy variables for each item (not the responses)? I have
> searched online and have only found examples of creating dummy variables for the
> response categories.
>
> I should be able to stack the responses and reshape the data using the help
> feature in Stata.
>
> Thank you for your help.
>
> Christopher Sanford
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/