[Rasch] FW: Why isn't the person separation better?

Trudy Mallinson trudy.mallinson at usc.edu
Thu Sep 2 02:01:33 EST 2010


Hi Kenny and others, thanks for your reply.  I'm attaching table 2.2.  There's a bit of a bubble of people at the upper end.
Let me know what you think.
Regards,
t.


TABLE 2.2 DOCS Test Items                        ZOU949WS.TXT  Sep  1  8:56 2010
INPUT: 426 Subjects  32 DOCS Stimuli  MEASURED: 426 Subjects  26 DOCS Stimuli  9 CATS WINSTEPS 3.70.0.2
--------------------------------------------------------------------------------
 
EXPECTED SCORE: MEAN  (Rasch-score-point threshold, ":" indicates Rasch-half-point threshold) (ILLUSTRATED BY AN OBSERVED CATEGORY)
-5   -4    -3    -2    -1     0     1     2     3     4     5
|-----+-----+-----+-----+-----+-----+-----+-----+-----+-----|  NUM   DOCS Stimuli
0                            0    :    1     :   2          2   30  ORIENENV
0                            0   :     1    :    2          2   31  TOTHBRSH
|                                                           |
0                           0    :    1     :   2           2   29  ORIENSLF
|                                                           |
|                                                           |
0                           0      :     2                  2   10  TRACKOBJ
0                           0     :      2                  2   11  TRAKFACE
0                       0   :    1     :   2                2   15  HAIR
|                                                           |
0                      0   :     1    :   2                 2   28  HEAT
|                                                           |
0                     0   :     1    :    2                 2    1  GREET
|                                                           |
0                       0      :     2                      2   12  FOCUSFAC
0                    0   :     1    :   2                   2   24  BELL
0     0     :         1        :       2         :     3    3   32  STATE
0                   0    :    1     :   2                   2   18  SCRUB
|                                                           |
0                      0     :      2                       2    9  FOCUSOBJ
0                  0    :    1     :   2                    2   23  NAME
0                  0    :    1     :   2                    2   13  AIR
0                  0    :    1     :   2                    2   17  HAND
0                  0   :     1    :    2                    2   25  COMMAND
|                                                           |
0                 0    :    1    :    2                     2   22  WHISTLE
0                0    :    1     :   2                      2   14  FEATHER
0                0    :    1     :   2                      2   21  CLAP
0                0   :     1    :    2                      2    6  ODOR
|                                                           |
0               0   :     1    :    2                       2    7  JOINT
0                  0     :      2                           2    8  BLINK
|                                                           |
0              0   :    1     :   2                         2   20  CUBE
0             0    :    1     :   2                         2   16  TOE
|                                                           |
|                                                           |
0          0   :     1    :    2                            2    2  JUICE
|-----+-----+-----+-----+-----+-----+-----+-----+-----+-----|  NUM   DOCS Stimuli
-5   -4    -3    -2    -1     0     1     2     3     4     5
 
                    1 1122222222211 1
3     21   5 22245680936383935533649288892916 11121 3  3 1 1   Subjects
            T        S       M       S        T
0                  10 20 30 50 70 80  90              99       PERCENTILE



On Aug 31, 2010, at 8:46 PM, Kenny Royal wrote:

> Hi Trudy,
>  
> We can rule out that it's instrument length and number of categories per item (your's look good), and we know that sample size and fit statistics have little to do with reliability and separation estimation, so perhaps you're encountering an issue of low sample ability variance or a problem with person-item targeting?  
>  
> Best,
>  
> Kenny
>  
> Kenneth D. Royal, Ph.D.
> Psychometrician
> American Board of Family Medicine
>              &
> Adjunct Professor
> University of Kentucky
> 
> --- On Tue, 8/31/10, Stephanou, Andrew <Stephanou at acer.edu.au> wrote:
> 
> From: Stephanou, Andrew <Stephanou at acer.edu.au>
> Subject: [Rasch] FW: Why isn't the person separation better?
> To: Rasch at ACER.edu.au
> Date: Tuesday, August 31, 2010, 6:55 PM
> 
> 
> Forwarded to the Rasch listserv on behalf of Trudy Mallinson, trudy.mallinson at usc.edu
> 
> 
> -----Original Message-----
> From: mallinso at usc.edu [mailto:mallinso at usc.edu] On Behalf Of Trudy Mallinson
> Sent: Wednesday, 1 September 2010 3:00 AM
> To: rasch
> Subject: Why isn't the person separation better?
> 
> Dear Listserv,
> 
> I am analyzing a small data set (about 200 participants, both admission and discharge currently in the dataset) and 32 items.  Everything about the instrument looks good - the items mostly fit, the rating scale (3 points) mostly works. The range of persons seems to form a fairly normal distribution, items are targeted on the people (mean -0.28 logits) with good range (min -4.07 logits, max 3.55 logits).  But the person separation is less than stellar at .84.  There are a few items where the middle category of the rating scale is "submerged" but not disordered.  When I combine it with one of the other categories, the SD increases a little but so does the error so it's a wash in terms of the separation.  I tried removing the misfitting items (not very misfitting at 1.3 - 1.4 infit MNSQ) same thing, increased SD, increased error, no change in separation.  I wondered if it could be a dimensionality problem - the PCA suggests it's unidimensional though.  I separated out the items into two groups.  Item psychometrics continue to look OK.  Separation for the vision items .82, for tactile items .82.  I created an xy plot of the person measures from the two set so items.  Scores clearly track together although the shape of the coordinates is basically a parallelogram.
> 
> Can any one suggest why, when everything about the items looks good, the separation is not great, and all the things I've tried don't seem to improve it in any meaningful way?
> 
> Thanks for your thoughts,
> 
> Trudy
> 
> Trudy Mallinson, PhD, OTR/L, NZROT
> 
> Assistant Professor
> 
> University of Southern California
> 
> Division of Occupational Science and Occupational Therapy
> 
> 1540 Alcazar Street, CHP 133, Room 101F
> 
> Los Angeles, CA 90089-9003
> 
> PH: (323) 442-2950
> 
> trudy.mallinson at usc.edu
> -----Inline Attachment Follows-----
> 
> _______________________________________________
> Rasch mailing list
> Rasch at acer.edu.au
> Unsubscribe: https://mailinglist.acer.edu.au/mailman/options/rasch/kdroya2%40yahoo.com
> 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://mailinglist.acer.edu.au/pipermail/rasch/attachments/20100901/4d0b3bd0/attachment.html 


More information about the Rasch mailing list