[Rasch] neutral categories in scales

Mike Linacre mike at winsteps.com
Sun Feb 24 09:13:58 EST 2013


Ian:

If you are using Winsteps and want to ignore 3 out of 12345, then
CODES=1245
STKEEP=NO
or
CODES=1245
NEWSCORE=1234

Both of these analyze the 1245 data as 1234

OK?

Mike L.

On 2/23/2013 4:57 AM, Bond, Trevor wrote:
 > Ian,
 > No need to recode to zero
 > Just changeValid codes to 1245
 > Ok?
 > Person reliability depends on items, and vice versa.
 > Collegially
 > TGB
 >
 >
 > Sent from 007's iPad
 >
 > On 23/02/2013, at 8:48 AM, "Ian Blackman" 
<ian.blackman at flinders.edu.au> wrote:
 >
 >> Hi all
 >> Could I please have some advice.... I have some data with 5 
categories with a middle category being neutral (rated as 3). I wish to 
remove that neutral category as i do not believe it is measuring a 
continuum of the latent trait being estimated. Is there any literature 
that supports this belief and secondly, would the reliability of the 
items be influenced if the neutral category was recoded to zero. Many 
thanks



More information about the Rasch mailing list