Bookmark and Share

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: weighted kappa more than two raters


From   Richard Goldstein <[email protected]>
To   [email protected]
Subject   Re: st: weighted kappa more than two raters
Date   Tue, 14 Jan 2014 09:53:23 -0500

that is a large matrix not consistent with what I thought you were doing

so I went back and re-read your emails and see that you are attempting
something that the help file says you can but no examples are presented
in either the help file or the manual - I suggest you write to tech support

Rich

On 1/14/14, 9:23 AM, Thoret, Sophie wrote:
> My matrix is 
> 
> Ratings weighted by:
>    1.0000   0.8889   0.7778   0.6667   0.5556   0.4444   0.3333   0.2222
> 0.1111   0.0000
>    0.8889   1.0000   0.8889   0.7778   0.6667   0.5556   0.4444   0.3333
> 0.2222   0.1111
>    0.7778   0.8889   1.0000   0.8889   0.7778   0.6667   0.5556   0.4444
> 0.3333   0.2222
>    0.6667   0.7778   0.8889   1.0000   0.8889   0.7778   0.6667   0.5556
> 0.4444   0.3333
>    0.5556   0.6667   0.7778   0.8889   1.0000   0.8889   0.7778   0.6667
> 0.5556   0.4444
>    0.4444   0.5556   0.6667   0.7778   0.8889   1.0000   0.8889   0.7778
> 0.6667   0.5556
>    0.3333   0.4444   0.5556   0.6667   0.7778   0.8889   1.0000   0.8889
> 0.7778   0.6667
>    0.2222   0.3333   0.4444   0.5556   0.6667   0.7778   0.8889   1.0000
> 0.8889   0.7778
>    0.1111   0.2222   0.3333   0.4444   0.5556   0.6667   0.7778   0.8889
> 1.0000   0.8889
>    0.0000   0.1111   0.2222   0.3333   0.4444   0.5556   0.6667   0.7778
> 0.8889   1.0000
> 
> 
> 
> 
> Le 14/01/2014 15:10, « Richard Goldstein » <[email protected]> a
> écrit :
> 
>> 1. I would use -kapwgt-
>>
>> 2. I can't judge your matrix since you don't show it (use -matrix li-)
>>
>> Rich
>>
>> On 1/14/14, 8:54 AM, Thoret, Sophie wrote:
>>> Ok so ill try to re-explain better :
>>>
>>> I want to calculate a weighted kappa with 4 raters (this is a 10 outcome
>>> answer, that why i want to use a weighted kappa)
>>>
>>> So I used the fonction :
>>>             kap var1 var2 var3 var4  , wgt(w)
>>>
>>>
>>> With the weight prerecorded : w
>>> So i think i don’t have to use first -kapwgt-  ?
>>>
>>> If i did :  kap var1 var2, wgt(w)
>>> it’s work for 2 variables, but if i put more than 2 variables it does’t
>>> work, do you know how can i do to calculate a kappa with 4 variables and
>>> using a weigh ?
>>>
>>> Thanks again ,
>>>
>>> Le 14/01/2014 14:33, « Richard Goldstein » <[email protected]> a
>>> écrit :
>>>
>>>> your question is not clear to me but setting up a weight matrix is
>>>> described in the help file and in the documentation; have you looked?
>>>>
>>>> Rich
>>>>
>>>> On 1/14/14, 8:20 AM, Thoret, Sophie wrote:
>>>>> You said that i can¹t use the weight prerecorded ? Even if it¹s the
>>>>> good
>>>>> mat for each 2*2 raters
>>>>>
>>>>> So how can i recorded a mat for 3 or more raters ?
>>>>>
>>>>> Thanks
>>>>>
>>>>> Le 14/01/2014 14:10, « Richard Goldstein » <[email protected]> a
>>>>> écrit :
>>>>>
>>>>>> sounds like you did not follow the instructions and use -kapwgt-
>>>>>> first;
>>>>>> see -h kap-
>>>>>>
>>>>>> Rich
>>>>>>
>>>>>> On 1/14/14, 8:04 AM, Thoret, Sophie wrote:
>>>>>>> Hi,
>>>>>>>
>>>>>>> In the stata help for KAPPA we can see :
>>>>>>>
>>>>>>>   Interrater agreement, nonunique raters, variables record ratings
>>>>>>> for
>>>>>>> each rater
>>>>>>>
>>>>>>>         kap varname1 varname2 varname3 [...] [if] [in] [weight]
>>>>>>>
>>>>>>> Is it really possible to add weight with more than 2 raters, if yes
>>>>>>> how
>>>>>>> can i do it ? Because il i tape :
>>>>>>>        kap var1 var2 var3  , wgt(w)
>>>>>>> I¹ve got an error message :
>>>>>>>         option opts not allowed
>>>>>>>          r(198);
>>>>>>>
>>>>>>> I didn¹t find anywhere somethings about this topic,
>>>>>>>
>>>>>>> Can you help me,
>>>>>>>
>>>>>>> Thanks
>>>>>>>
>>>>>>> Sophie
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index