A data mapping riddle.

classic Classic list List threaded Threaded
10 messages Options
Reply | Threaded
Open this post in threaded view
|

A data mapping riddle.

David Marso
Administrator
I have a solution which is really neat and tidy but wanted to see how others
approach the following type of situation.
 Recall a few weeks ago a user posed the question of getting all possible
pairs of Kappa coefficients for something like 30 raters.  

We generated a simple macro which basically gathered up all pairs in a
sequence
j1 x j2..j30, j2 x j3..j30, .....j29 x j30.

It occured to me that the resulting OMS output lacks the identifying
information for which pairs of raters contributed a given Kappa coefficient.

Riddle me this,  Given variables j1 ...j30 and a file containing the results
in the above sequence, how best to append the contributing variable names to
the coefficients for further analysis?



-----
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
Reply | Threaded
Open this post in threaded view
|

Re: A data mapping riddle.

Bruce Weaver
Administrator
David, are you talking about the Kappa output from this macro?

http://spssx-discussion.1045642.n5.nabble.com/interrater-reliabillity-but-for-any-pair-of-raters-td5735428.html#a5735437




David Marso wrote

> I have a solution which is really neat and tidy but wanted to see how
> others
> approach the following type of situation.
>  Recall a few weeks ago a user posed the question of getting all possible
> pairs of Kappa coefficients for something like 30 raters.  
>
> We generated a simple macro which basically gathered up all pairs in a
> sequence
> j1 x j2..j30, j2 x j3..j30, .....j29 x j30.
>
> It occured to me that the resulting OMS output lacks the identifying
> information for which pairs of raters contributed a given Kappa
> coefficient.
>
> Riddle me this,  Given variables j1 ...j30 and a file containing the
> results
> in the above sequence, how best to append the contributing variable names
> to
> the coefficients for further analysis?
>
>
>
> -----
> Please reply to the list and not to my personal email.
> Those desiring my consulting or training services please feel free to
> email me.
> ---
> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos
> ne forte conculcent eas pedibus suis."
> Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in
> abyssum?"
> --
> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>
> =====================
> To manage your subscription to SPSSX-L, send a message to

> LISTSERV@.UGA

>  (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD





-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
--
Bruce Weaver
bweaver@lakeheadu.ca
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.
Reply | Threaded
Open this post in threaded view
|

Re: A data mapping riddle.

David Marso
Administrator
Indeed I am.  Thanks for adding the link.  I should have included that in my
post.


Bruce Weaver wrote

> David, are you talking about the Kappa output from this macro?
>
> http://spssx-discussion.1045642.n5.nabble.com/interrater-reliabillity-but-for-any-pair-of-raters-td5735428.html#a5735437
>
>
>
>
> David Marso wrote
>> I have a solution which is really neat and tidy but wanted to see how
>> others
>> approach the following type of situation.
>>  Recall a few weeks ago a user posed the question of getting all possible
>> pairs of Kappa coefficients for something like 30 raters.  
>>
>> We generated a simple macro which basically gathered up all pairs in a
>> sequence
>> j1 x j2..j30, j2 x j3..j30, .....j29 x j30.
>>
>> It occured to me that the resulting OMS output lacks the identifying
>> information for which pairs of raters contributed a given Kappa
>> coefficient.
>>
>> Riddle me this,  Given variables j1 ...j30 and a file containing the
>> results
>> in the above sequence, how best to append the contributing variable names
>> to
>> the coefficients for further analysis?
>>
>>
>>
>> -----
>> Please reply to the list and not to my personal email.
>> Those desiring my consulting or training services please feel free to
>> email me.
>> ---
>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>> porcos
>> ne forte conculcent eas pedibus suis."
>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff
>> in
>> abyssum?"
>> --
>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>
>> LISTSERV@.UGA
>
>>  (not to SPSSX-L), with no body text except the
>> command. To leave the list, send the command
>> SIGNOFF SPSSX-L
>> For a list of commands to manage subscriptions, send the command
>> INFO REFCARD
>
>
>
>
>
> -----
> --
> Bruce Weaver

> bweaver@

> http://sites.google.com/a/lakeheadu.ca/bweaver/
>
> "When all else fails, RTFM."
>
> NOTE: My Hotmail account is not monitored regularly.
> To send me an e-mail, please use the address shown above.
>
> --
> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>
> =====================
> To manage your subscription to SPSSX-L, send a message to

> LISTSERV@.UGA

>  (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD





-----
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
Reply | Threaded
Open this post in threaded view
|

Re: A data mapping riddle.

Bruce Weaver
Administrator
So you're just looking to indicate which pair of judges it is for each row?
How about this?

DATASET ACTIVATE Kappa.
NUMERIC J1 J2 (F2.0).
COMPUTE #case = 0.
LOOP # = 1 to 29.
 LOOP ## = #+1 to 30.
  COMPUTE #case = #case+1.
  DO IF $CASENUM EQ #case.
   COMPUTE J1 = #.
   COMPUTE J2 = ##.
  END IF.
 END LOOP.
END LOOP.
CROSSTABS J1 by J2.



David Marso wrote

> Indeed I am.  Thanks for adding the link.  I should have included that in
> my
> post.
>
>
> Bruce Weaver wrote
>> David, are you talking about the Kappa output from this macro?
>>
>> http://spssx-discussion.1045642.n5.nabble.com/interrater-reliabillity-but-for-any-pair-of-raters-td5735428.html#a5735437
>>
>>
>>
>>
>> David Marso wrote
>>> I have a solution which is really neat and tidy but wanted to see how
>>> others
>>> approach the following type of situation.
>>>  Recall a few weeks ago a user posed the question of getting all
>>> possible
>>> pairs of Kappa coefficients for something like 30 raters.  
>>>
>>> We generated a simple macro which basically gathered up all pairs in a
>>> sequence
>>> j1 x j2..j30, j2 x j3..j30, .....j29 x j30.
>>>
>>> It occured to me that the resulting OMS output lacks the identifying
>>> information for which pairs of raters contributed a given Kappa
>>> coefficient.
>>>
>>> Riddle me this,  Given variables j1 ...j30 and a file containing the
>>> results
>>> in the above sequence, how best to append the contributing variable
>>> names
>>> to
>>> the coefficients for further analysis?
>>>
>>>
>>>
>>> -----
>>> Please reply to the list and not to my personal email.
>>> Those desiring my consulting or training services please feel free to
>>> email me.
>>> ---
>>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>>> porcos
>>> ne forte conculcent eas pedibus suis."
>>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff
>>> in
>>> abyssum?"
>>> --
>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>
>>> =====================
>>> To manage your subscription to SPSSX-L, send a message to
>>
>>> LISTSERV@.UGA
>>
>>>  (not to SPSSX-L), with no body text except the
>>> command. To leave the list, send the command
>>> SIGNOFF SPSSX-L
>>> For a list of commands to manage subscriptions, send the command
>>> INFO REFCARD
>>
>>
>>
>>
>>
>> -----
>> --
>> Bruce Weaver
>
>> bweaver@
>
>> http://sites.google.com/a/lakeheadu.ca/bweaver/
>>
>> "When all else fails, RTFM."
>>
>> NOTE: My Hotmail account is not monitored regularly.
>> To send me an e-mail, please use the address shown above.
>>
>> --
>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>
>> LISTSERV@.UGA
>
>>  (not to SPSSX-L), with no body text except the
>> command. To leave the list, send the command
>> SIGNOFF SPSSX-L
>> For a list of commands to manage subscriptions, send the command
>> INFO REFCARD
>
>
>
>
>
> -----
> Please reply to the list and not to my personal email.
> Those desiring my consulting or training services please feel free to
> email me.
> ---
> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos
> ne forte conculcent eas pedibus suis."
> Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in
> abyssum?"
> --
> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>
> =====================
> To manage your subscription to SPSSX-L, send a message to

> LISTSERV@.UGA

>  (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD





-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
--
Bruce Weaver
bweaver@lakeheadu.ca
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.
Reply | Threaded
Open this post in threaded view
|

Re: A data mapping riddle.

Maguin, Eugene
When I saw David's riddle, I thought about what you did but I came away thinking that David might actually have in mind making the rater pair be the variable label for that particular variable. My no very informed impression is that this cannot be done in syntax. Could I be wrong?
Gene Maguin

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Bruce Weaver
Sent: Thursday, February 8, 2018 3:05 PM
To: [hidden email]
Subject: Re: A data mapping riddle.

So you're just looking to indicate which pair of judges it is for each row?
How about this?

DATASET ACTIVATE Kappa.
NUMERIC J1 J2 (F2.0).
COMPUTE #case = 0.
LOOP # = 1 to 29.
 LOOP ## = #+1 to 30.
  COMPUTE #case = #case+1.
  DO IF $CASENUM EQ #case.
   COMPUTE J1 = #.
   COMPUTE J2 = ##.
  END IF.
 END LOOP.
END LOOP.
CROSSTABS J1 by J2.



David Marso wrote

> Indeed I am.  Thanks for adding the link.  I should have included that
> in my post.
>
>
> Bruce Weaver wrote
>> David, are you talking about the Kappa output from this macro?
>>
>> http://spssx-discussion.1045642.n5.nabble.com/interrater-reliabillity
>> -but-for-any-pair-of-raters-td5735428.html#a5735437
>>
>>
>>
>>
>> David Marso wrote
>>> I have a solution which is really neat and tidy but wanted to see
>>> how others approach the following type of situation.
>>>  Recall a few weeks ago a user posed the question of getting all
>>> possible pairs of Kappa coefficients for something like 30 raters.
>>>
>>> We generated a simple macro which basically gathered up all pairs in
>>> a sequence
>>> j1 x j2..j30, j2 x j3..j30, .....j29 x j30.
>>>
>>> It occured to me that the resulting OMS output lacks the identifying
>>> information for which pairs of raters contributed a given Kappa
>>> coefficient.
>>>
>>> Riddle me this,  Given variables j1 ...j30 and a file containing the
>>> results in the above sequence, how best to append the contributing
>>> variable names to the coefficients for further analysis?
>>>
>>>
>>>
>>> -----
>>> Please reply to the list and not to my personal email.
>>> Those desiring my consulting or training services please feel free
>>> to email me.
>>> ---
>>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>>> porcos ne forte conculcent eas pedibus suis."
>>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum
>>> cliff in abyssum?"
>>> --
>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>
>>> =====================
>>> To manage your subscription to SPSSX-L, send a message to
>>
>>> LISTSERV@.UGA
>>
>>>  (not to SPSSX-L), with no body text except the command. To leave
>>> the list, send the command SIGNOFF SPSSX-L For a list of commands to
>>> manage subscriptions, send the command INFO REFCARD
>>
>>
>>
>>
>>
>> -----
>> --
>> Bruce Weaver
>
>> bweaver@
>
>> http://sites.google.com/a/lakeheadu.ca/bweaver/
>>
>> "When all else fails, RTFM."
>>
>> NOTE: My Hotmail account is not monitored regularly.
>> To send me an e-mail, please use the address shown above.
>>
>> --
>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>
>> LISTSERV@.UGA
>
>>  (not to SPSSX-L), with no body text except the command. To leave the
>> list, send the command SIGNOFF SPSSX-L For a list of commands to
>> manage subscriptions, send the command INFO REFCARD
>
>
>
>
>
> -----
> Please reply to the list and not to my personal email.
> Those desiring my consulting or training services please feel free to
> email me.
> ---
> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
> porcos ne forte conculcent eas pedibus suis."
> Cum es damnatorum possederunt porcos iens ut salire off sanguinum
> cliff in abyssum?"
> --
> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>
> =====================
> To manage your subscription to SPSSX-L, send a message to

> LISTSERV@.UGA

>  (not to SPSSX-L), with no body text except the command. To leave the
> list, send the command SIGNOFF SPSSX-L For a list of commands to
> manage subscriptions, send the command INFO REFCARD





-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Reply | Threaded
Open this post in threaded view
|

Re: A data mapping riddle.

David Marso
Administrator
I am actually looking for another pair of variables in each row containing
the variable name for the contributing variable/rater.  Think of how one can
get a variable name into a manipulable form in a system file [two ways come
to mind].

jX jY Kappa XY
-------------------
j1 j2 Kappa_1_2
j1 j3 Kappa_1_3
....
j29 j30 Kappa_29_30

Preferred solution does not require knowing the number of raters.


Maguin, Eugene wrote
> When I saw David's riddle, I thought about what you did but I came away
> thinking that David might actually have in mind making the rater pair be
> the variable label for that particular variable. My no very informed
> impression is that this cannot be done in syntax. Could I be wrong?
> Gene Maguin
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:

> SPSSX-L@.UGA

> ] On Behalf Of Bruce Weaver
> Sent: Thursday, February 8, 2018 3:05 PM
> To:

> SPSSX-L@.UGA

> Subject: Re: A data mapping riddle.
>
> So you're just looking to indicate which pair of judges it is for each
> row?
> How about this?
>
> DATASET ACTIVATE Kappa.
> NUMERIC J1 J2 (F2.0).
> COMPUTE #case = 0.
> LOOP # = 1 to 29.
>  LOOP ## = #+1 to 30.
>   COMPUTE #case = #case+1.
>   DO IF $CASENUM EQ #case.
>    COMPUTE J1 = #.
>    COMPUTE J2 = ##.
>   END IF.
>  END LOOP.
> END LOOP.
> CROSSTABS J1 by J2.
>
>
>
> David Marso wrote
>> Indeed I am.  Thanks for adding the link.  I should have included that
>> in my post.
>>
>>
>> Bruce Weaver wrote
>>> David, are you talking about the Kappa output from this macro?
>>>
>>> http://spssx-discussion.1045642.n5.nabble.com/interrater-reliabillity
>>> -but-for-any-pair-of-raters-td5735428.html#a5735437
>>>
>>>
>>>
>>>
>>> David Marso wrote
>>>> I have a solution which is really neat and tidy but wanted to see
>>>> how others approach the following type of situation.
>>>>  Recall a few weeks ago a user posed the question of getting all
>>>> possible pairs of Kappa coefficients for something like 30 raters.
>>>>
>>>> We generated a simple macro which basically gathered up all pairs in
>>>> a sequence
>>>> j1 x j2..j30, j2 x j3..j30, .....j29 x j30.
>>>>
>>>> It occured to me that the resulting OMS output lacks the identifying
>>>> information for which pairs of raters contributed a given Kappa
>>>> coefficient.
>>>>
>>>> Riddle me this,  Given variables j1 ...j30 and a file containing the
>>>> results in the above sequence, how best to append the contributing
>>>> variable names to the coefficients for further analysis?
>>>>
>>>>
>>>>
>>>> -----
>>>> Please reply to the list and not to my personal email.
>>>> Those desiring my consulting or training services please feel free
>>>> to email me.
>>>> ---
>>>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>>>> porcos ne forte conculcent eas pedibus suis."
>>>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum
>>>> cliff in abyssum?"
>>>> --
>>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>>
>>>> =====================
>>>> To manage your subscription to SPSSX-L, send a message to
>>>
>>>> LISTSERV@.UGA
>>>
>>>>  (not to SPSSX-L), with no body text except the command. To leave
>>>> the list, send the command SIGNOFF SPSSX-L For a list of commands to
>>>> manage subscriptions, send the command INFO REFCARD
>>>
>>>
>>>
>>>
>>>
>>> -----
>>> --
>>> Bruce Weaver
>>
>>> bweaver@
>>
>>> http://sites.google.com/a/lakeheadu.ca/bweaver/
>>>
>>> "When all else fails, RTFM."
>>>
>>> NOTE: My Hotmail account is not monitored regularly.
>>> To send me an e-mail, please use the address shown above.
>>>
>>> --
>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>
>>> =====================
>>> To manage your subscription to SPSSX-L, send a message to
>>
>>> LISTSERV@.UGA
>>
>>>  (not to SPSSX-L), with no body text except the command. To leave the
>>> list, send the command SIGNOFF SPSSX-L For a list of commands to
>>> manage subscriptions, send the command INFO REFCARD
>>
>>
>>
>>
>>
>> -----
>> Please reply to the list and not to my personal email.
>> Those desiring my consulting or training services please feel free to
>> email me.
>> ---
>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>> porcos ne forte conculcent eas pedibus suis."
>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum
>> cliff in abyssum?"
>> --
>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>
>> LISTSERV@.UGA
>
>>  (not to SPSSX-L), with no body text except the command. To leave the
>> list, send the command SIGNOFF SPSSX-L For a list of commands to
>> manage subscriptions, send the command INFO REFCARD
>
>
>
>
>
> -----
> --
> Bruce Weaver

> bweaver@

> http://sites.google.com/a/lakeheadu.ca/bweaver/
>
> "When all else fails, RTFM."
>
> NOTE: My Hotmail account is not monitored regularly.
> To send me an e-mail, please use the address shown above.
>
> --
> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>
> =====================
> To manage your subscription to SPSSX-L, send a message to

> LISTSERV@.UGA

>  (not to SPSSX-L), with no body text except the command. To leave the
> list, send the command SIGNOFF SPSSX-L For a list of commands to manage
> subscriptions, send the command INFO REFCARD
>
> =====================
> To manage your subscription to SPSSX-L, send a message to

> LISTSERV@.UGA

>  (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD





-----
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
Reply | Threaded
Open this post in threaded view
|

Re: A data mapping riddle.

Bruce Weaver
Administrator
I don't have SPSS on this machine, but are you thinking of VARSTOCASES with a
variable name index?  



David Marso wrote

> I am actually looking for another pair of variables in each row containing
> the variable name for the contributing variable/rater.  Think of how one
> can
> get a variable name into a manipulable form in a system file [two ways
> come
> to mind].
>
> jX jY Kappa XY
> -------------------
> j1 j2 Kappa_1_2
> j1 j3 Kappa_1_3
> ....
> j29 j30 Kappa_29_30
>
> Preferred solution does not require knowing the number of raters.
>
>
> Maguin, Eugene wrote
>> When I saw David's riddle, I thought about what you did but I came away
>> thinking that David might actually have in mind making the rater pair be
>> the variable label for that particular variable. My no very informed
>> impression is that this cannot be done in syntax. Could I be wrong?
>> Gene Maguin
>>
>> -----Original Message-----
>> From: SPSSX(r) Discussion [mailto:
>
>> SPSSX-L@.UGA
>
>> ] On Behalf Of Bruce Weaver
>> Sent: Thursday, February 8, 2018 3:05 PM
>> To:
>
>> SPSSX-L@.UGA
>
>> Subject: Re: A data mapping riddle.
>>
>> So you're just looking to indicate which pair of judges it is for each
>> row?
>> How about this?
>>
>> DATASET ACTIVATE Kappa.
>> NUMERIC J1 J2 (F2.0).
>> COMPUTE #case = 0.
>> LOOP # = 1 to 29.
>>  LOOP ## = #+1 to 30.
>>   COMPUTE #case = #case+1.
>>   DO IF $CASENUM EQ #case.
>>    COMPUTE J1 = #.
>>    COMPUTE J2 = ##.
>>   END IF.
>>  END LOOP.
>> END LOOP.
>> CROSSTABS J1 by J2.
>>
>>
>>
>> David Marso wrote
>>> Indeed I am.  Thanks for adding the link.  I should have included that
>>> in my post.
>>>
>>>
>>> Bruce Weaver wrote
>>>> David, are you talking about the Kappa output from this macro?
>>>>
>>>> http://spssx-discussion.1045642.n5.nabble.com/interrater-reliabillity
>>>> -but-for-any-pair-of-raters-td5735428.html#a5735437
>>>>
>>>>
>>>>
>>>>
>>>> David Marso wrote
>>>>> I have a solution which is really neat and tidy but wanted to see
>>>>> how others approach the following type of situation.
>>>>>  Recall a few weeks ago a user posed the question of getting all
>>>>> possible pairs of Kappa coefficients for something like 30 raters.
>>>>>
>>>>> We generated a simple macro which basically gathered up all pairs in
>>>>> a sequence
>>>>> j1 x j2..j30, j2 x j3..j30, .....j29 x j30.
>>>>>
>>>>> It occured to me that the resulting OMS output lacks the identifying
>>>>> information for which pairs of raters contributed a given Kappa
>>>>> coefficient.
>>>>>
>>>>> Riddle me this,  Given variables j1 ...j30 and a file containing the
>>>>> results in the above sequence, how best to append the contributing
>>>>> variable names to the coefficients for further analysis?
>>>>>
>>>>>
>>>>>
>>>>> -----
>>>>> Please reply to the list and not to my personal email.
>>>>> Those desiring my consulting or training services please feel free
>>>>> to email me.
>>>>> ---
>>>>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>>>>> porcos ne forte conculcent eas pedibus suis."
>>>>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum
>>>>> cliff in abyssum?"
>>>>> --
>>>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>>>
>>>>> =====================
>>>>> To manage your subscription to SPSSX-L, send a message to
>>>>
>>>>> LISTSERV@.UGA
>>>>
>>>>>  (not to SPSSX-L), with no body text except the command. To leave
>>>>> the list, send the command SIGNOFF SPSSX-L For a list of commands to
>>>>> manage subscriptions, send the command INFO REFCARD
>>>>
>>>>
>>>>
>>>>
>>>>
>>>> -----
>>>> --
>>>> Bruce Weaver
>>>
>>>> bweaver@
>>>
>>>> http://sites.google.com/a/lakeheadu.ca/bweaver/
>>>>
>>>> "When all else fails, RTFM."
>>>>
>>>> NOTE: My Hotmail account is not monitored regularly.
>>>> To send me an e-mail, please use the address shown above.
>>>>
>>>> --
>>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>>
>>>> =====================
>>>> To manage your subscription to SPSSX-L, send a message to
>>>
>>>> LISTSERV@.UGA
>>>
>>>>  (not to SPSSX-L), with no body text except the command. To leave the
>>>> list, send the command SIGNOFF SPSSX-L For a list of commands to
>>>> manage subscriptions, send the command INFO REFCARD
>>>
>>>
>>>
>>>
>>>
>>> -----
>>> Please reply to the list and not to my personal email.
>>> Those desiring my consulting or training services please feel free to
>>> email me.
>>> ---
>>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>>> porcos ne forte conculcent eas pedibus suis."
>>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum
>>> cliff in abyssum?"
>>> --
>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>
>>> =====================
>>> To manage your subscription to SPSSX-L, send a message to
>>
>>> LISTSERV@.UGA
>>
>>>  (not to SPSSX-L), with no body text except the command. To leave the
>>> list, send the command SIGNOFF SPSSX-L For a list of commands to
>>> manage subscriptions, send the command INFO REFCARD
>>
>>
>>
>>
>>
>> -----
>> --
>> Bruce Weaver
>
>> bweaver@
>
>> http://sites.google.com/a/lakeheadu.ca/bweaver/
>>
>> "When all else fails, RTFM."
>>
>> NOTE: My Hotmail account is not monitored regularly.
>> To send me an e-mail, please use the address shown above.
>>
>> --
>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>
>> LISTSERV@.UGA
>
>>  (not to SPSSX-L), with no body text except the command. To leave the
>> list, send the command SIGNOFF SPSSX-L For a list of commands to manage
>> subscriptions, send the command INFO REFCARD
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>
>> LISTSERV@.UGA
>
>>  (not to SPSSX-L), with no body text except the
>> command. To leave the list, send the command
>> SIGNOFF SPSSX-L
>> For a list of commands to manage subscriptions, send the command
>> INFO REFCARD
>
>
>
>
>
> -----
> Please reply to the list and not to my personal email.
> Those desiring my consulting or training services please feel free to
> email me.
> ---
> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos
> ne forte conculcent eas pedibus suis."
> Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in
> abyssum?"
> --
> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>
> =====================
> To manage your subscription to SPSSX-L, send a message to

> LISTSERV@.UGA

>  (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD





-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
--
Bruce Weaver
bweaver@lakeheadu.ca
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.
Reply | Threaded
Open this post in threaded view
|

Re: A data mapping riddle.

David Marso
Administrator
Ok three ways to get varnames into a manipulable form.
Yes, VARSTOCASES could be a first step.
Bonus points if you don't explicitly write a file to disk.
---

Bruce Weaver wrote

> I don't have SPSS on this machine, but are you thinking of VARSTOCASES
> with a
> variable name index?  
>
>
>
> David Marso wrote
>> I am actually looking for another pair of variables in each row
>> containing
>> the variable name for the contributing variable/rater.  Think of how one
>> can
>> get a variable name into a manipulable form in a system file [two ways
>> come
>> to mind].
>>
>> jX jY Kappa XY
>> -------------------
>> j1 j2 Kappa_1_2
>> j1 j3 Kappa_1_3
>> ....
>> j29 j30 Kappa_29_30
>>
>> Preferred solution does not require knowing the number of raters.
>>
>>
>> Maguin, Eugene wrote
>>> When I saw David's riddle, I thought about what you did but I came away
>>> thinking that David might actually have in mind making the rater pair be
>>> the variable label for that particular variable. My no very informed
>>> impression is that this cannot be done in syntax. Could I be wrong?
>>> Gene Maguin
>>>
>>> -----Original Message-----
>>> From: SPSSX(r) Discussion [mailto:
>>
>>> SPSSX-L@.UGA
>>
>>> ] On Behalf Of Bruce Weaver
>>> Sent: Thursday, February 8, 2018 3:05 PM
>>> To:
>>
>>> SPSSX-L@.UGA
>>
>>> Subject: Re: A data mapping riddle.
>>>
>>> So you're just looking to indicate which pair of judges it is for each
>>> row?
>>> How about this?
>>>
>>> DATASET ACTIVATE Kappa.
>>> NUMERIC J1 J2 (F2.0).
>>> COMPUTE #case = 0.
>>> LOOP # = 1 to 29.
>>>  LOOP ## = #+1 to 30.
>>>   COMPUTE #case = #case+1.
>>>   DO IF $CASENUM EQ #case.
>>>    COMPUTE J1 = #.
>>>    COMPUTE J2 = ##.
>>>   END IF.
>>>  END LOOP.
>>> END LOOP.
>>> CROSSTABS J1 by J2.
>>>
>>>
>>>
>>> David Marso wrote
>>>> Indeed I am.  Thanks for adding the link.  I should have included that
>>>> in my post.
>>>>
>>>>
>>>> Bruce Weaver wrote
>>>>> David, are you talking about the Kappa output from this macro?
>>>>>
>>>>> http://spssx-discussion.1045642.n5.nabble.com/interrater-reliabillity
>>>>> -but-for-any-pair-of-raters-td5735428.html#a5735437
>>>>>
>>>>>
>>>>>
>>>>>
>>>>> David Marso wrote
>>>>>> I have a solution which is really neat and tidy but wanted to see
>>>>>> how others approach the following type of situation.
>>>>>>  Recall a few weeks ago a user posed the question of getting all
>>>>>> possible pairs of Kappa coefficients for something like 30 raters.
>>>>>>
>>>>>> We generated a simple macro which basically gathered up all pairs in
>>>>>> a sequence
>>>>>> j1 x j2..j30, j2 x j3..j30, .....j29 x j30.
>>>>>>
>>>>>> It occured to me that the resulting OMS output lacks the identifying
>>>>>> information for which pairs of raters contributed a given Kappa
>>>>>> coefficient.
>>>>>>
>>>>>> Riddle me this,  Given variables j1 ...j30 and a file containing the
>>>>>> results in the above sequence, how best to append the contributing
>>>>>> variable names to the coefficients for further analysis?
>>>>>>
>>>>>>
>>>>>>
>>>>>> -----
>>>>>> Please reply to the list and not to my personal email.
>>>>>> Those desiring my consulting or training services please feel free
>>>>>> to email me.
>>>>>> ---
>>>>>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>>>>>> porcos ne forte conculcent eas pedibus suis."
>>>>>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum
>>>>>> cliff in abyssum?"
>>>>>> --
>>>>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>>>>
>>>>>> =====================
>>>>>> To manage your subscription to SPSSX-L, send a message to
>>>>>
>>>>>> LISTSERV@.UGA
>>>>>
>>>>>>  (not to SPSSX-L), with no body text except the command. To leave
>>>>>> the list, send the command SIGNOFF SPSSX-L For a list of commands to
>>>>>> manage subscriptions, send the command INFO REFCARD
>>>>>
>>>>>
>>>>>
>>>>>
>>>>>
>>>>> -----
>>>>> --
>>>>> Bruce Weaver
>>>>
>>>>> bweaver@
>>>>
>>>>> http://sites.google.com/a/lakeheadu.ca/bweaver/
>>>>>
>>>>> "When all else fails, RTFM."
>>>>>
>>>>> NOTE: My Hotmail account is not monitored regularly.
>>>>> To send me an e-mail, please use the address shown above.
>>>>>
>>>>> --
>>>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>>>
>>>>> =====================
>>>>> To manage your subscription to SPSSX-L, send a message to
>>>>
>>>>> LISTSERV@.UGA
>>>>
>>>>>  (not to SPSSX-L), with no body text except the command. To leave the
>>>>> list, send the command SIGNOFF SPSSX-L For a list of commands to
>>>>> manage subscriptions, send the command INFO REFCARD
>>>>
>>>>
>>>>
>>>>
>>>>
>>>> -----
>>>> Please reply to the list and not to my personal email.
>>>> Those desiring my consulting or training services please feel free to
>>>> email me.
>>>> ---
>>>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>>>> porcos ne forte conculcent eas pedibus suis."
>>>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum
>>>> cliff in abyssum?"
>>>> --
>>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>>
>>>> =====================
>>>> To manage your subscription to SPSSX-L, send a message to
>>>
>>>> LISTSERV@.UGA
>>>
>>>>  (not to SPSSX-L), with no body text except the command. To leave the
>>>> list, send the command SIGNOFF SPSSX-L For a list of commands to
>>>> manage subscriptions, send the command INFO REFCARD
>>>
>>>
>>>
>>>
>>>
>>> -----
>>> --
>>> Bruce Weaver
>>
>>> bweaver@
>>
>>> http://sites.google.com/a/lakeheadu.ca/bweaver/
>>>
>>> "When all else fails, RTFM."
>>>
>>> NOTE: My Hotmail account is not monitored regularly.
>>> To send me an e-mail, please use the address shown above.
>>>
>>> --
>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>
>>> =====================
>>> To manage your subscription to SPSSX-L, send a message to
>>
>>> LISTSERV@.UGA
>>
>>>  (not to SPSSX-L), with no body text except the command. To leave the
>>> list, send the command SIGNOFF SPSSX-L For a list of commands to manage
>>> subscriptions, send the command INFO REFCARD
>>>
>>> =====================
>>> To manage your subscription to SPSSX-L, send a message to
>>
>>> LISTSERV@.UGA
>>
>>>  (not to SPSSX-L), with no body text except the
>>> command. To leave the list, send the command
>>> SIGNOFF SPSSX-L
>>> For a list of commands to manage subscriptions, send the command
>>> INFO REFCARD
>>
>>
>>
>>
>>
>> -----
>> Please reply to the list and not to my personal email.
>> Those desiring my consulting or training services please feel free to
>> email me.
>> ---
>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>> porcos
>> ne forte conculcent eas pedibus suis."
>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff
>> in
>> abyssum?"
>> --
>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>
>> LISTSERV@.UGA
>
>>  (not to SPSSX-L), with no body text except the
>> command. To leave the list, send the command
>> SIGNOFF SPSSX-L
>> For a list of commands to manage subscriptions, send the command
>> INFO REFCARD
>
>
>
>
>
> -----
> --
> Bruce Weaver

> bweaver@

> http://sites.google.com/a/lakeheadu.ca/bweaver/
>
> "When all else fails, RTFM."
>
> NOTE: My Hotmail account is not monitored regularly.
> To send me an e-mail, please use the address shown above.
>
> --
> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>
> =====================
> To manage your subscription to SPSSX-L, send a message to

> LISTSERV@.UGA

>  (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD





-----
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
Reply | Threaded
Open this post in threaded view
|

Re: A data mapping riddle.

David Marso
Administrator
Using VARSTOCASES with an index can get the variable names into a column.
You can then use CASESTOVARS to get them into a vector but getting the
length in order to loop and write the pairs is difficult.

This is what I came up with and can't think of a way to do it without
MATRIX.
Any other thoughts?

One can easily match the 'Pairs' file to the file containing the Kappas
created by CROSSTABS /OMS .


DEFINE !DataSimulation (!POS !CHAREND("=")
                      / !POS !CHAREND("(")
                      / !POS !CHAREND(",")
                      / !POS !CHAREND(",")
                      / !POS !CHAREND(")")
                      / !POS !CMDEND  )

MATRIX.
SAVE TRUNC(!2(!3,!4)*!5+1) / OUTFILE= * /VARIABLES !1 .
END MATRIX.
DATASET NAME !6.
!ENDDEFINE.

DEFINE !PairNames ( !POS !CHAREND (">") / !POS !CMDEND)
PRESERVE.
/* ProgMans contribution to allow writing to a dataset without Admin priv */
.
CD '%userprofile%\Desktop' .

DATASET DECLARE !2.
MATRIX.
+  GET Data /FILE * /VARIABLES !1 /NAMES=names.
+  LOOP I=1 TO NCOL(names)  - 1.
+    LOOP J=I+1 TO NCOL(names) .
+      SAVE {names(I),names(J)} /OUTFILE  !2 /VARIABLES Jx Jy /STRING Jx Jy.
+    END LOOP.
+  END LOOP.
END MATRIX.
DATASET ACTIVATE   !2.
RESTORE.
!ENDDEFINE.
!DataSimulation j1 TO j30=UNIFORM(200,30,4) raw.
!PairNames j1 TO j30 > Pairs.



David Marso wrote

> Ok three ways to get varnames into a manipulable form.
> Yes, VARSTOCASES could be a first step.
> Bonus points if you don't explicitly write a file to disk.
> ---
>
> Bruce Weaver wrote
>> I don't have SPSS on this machine, but are you thinking of VARSTOCASES
>> with a
>> variable name index?  
>>
>>
>>
>> David Marso wrote
>>> I am actually looking for another pair of variables in each row
>>> containing
>>> the variable name for the contributing variable/rater.  Think of how one
>>> can
>>> get a variable name into a manipulable form in a system file [two ways
>>> come
>>> to mind].
>>>
>>> jX jY Kappa XY
>>> -------------------
>>> j1 j2 Kappa_1_2
>>> j1 j3 Kappa_1_3
>>> ....
>>> j29 j30 Kappa_29_30
>>>
>>> Preferred solution does not require knowing the number of raters.
>>>
>>>
>>> Maguin, Eugene wrote
>>>> When I saw David's riddle, I thought about what you did but I came away
>>>> thinking that David might actually have in mind making the rater pair
>>>> be
>>>> the variable label for that particular variable. My no very informed
>>>> impression is that this cannot be done in syntax. Could I be wrong?
>>>> Gene Maguin
>>>>
>>>> -----Original Message-----
>>>> From: SPSSX(r) Discussion [mailto:
>>>
>>>> SPSSX-L@.UGA
>>>
>>>> ] On Behalf Of Bruce Weaver
>>>> Sent: Thursday, February 8, 2018 3:05 PM
>>>> To:
>>>
>>>> SPSSX-L@.UGA
>>>
>>>> Subject: Re: A data mapping riddle.
>>>>
>>>> So you're just looking to indicate which pair of judges it is for each
>>>> row?
>>>> How about this?
>>>>
>>>> DATASET ACTIVATE Kappa.
>>>> NUMERIC J1 J2 (F2.0).
>>>> COMPUTE #case = 0.
>>>> LOOP # = 1 to 29.
>>>>  LOOP ## = #+1 to 30.
>>>>   COMPUTE #case = #case+1.
>>>>   DO IF $CASENUM EQ #case.
>>>>    COMPUTE J1 = #.
>>>>    COMPUTE J2 = ##.
>>>>   END IF.
>>>>  END LOOP.
>>>> END LOOP.
>>>> CROSSTABS J1 by J2.
>>>>
>>>>
>>>>
>>>> David Marso wrote
>>>>> Indeed I am.  Thanks for adding the link.  I should have included that
>>>>> in my post.
>>>>>
>>>>>
>>>>> Bruce Weaver wrote
>>>>>> David, are you talking about the Kappa output from this macro?
>>>>>>
>>>>>> http://spssx-discussion.1045642.n5.nabble.com/interrater-reliabillity
>>>>>> -but-for-any-pair-of-raters-td5735428.html#a5735437
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>> David Marso wrote
>>>>>>> I have a solution which is really neat and tidy but wanted to see
>>>>>>> how others approach the following type of situation.
>>>>>>>  Recall a few weeks ago a user posed the question of getting all
>>>>>>> possible pairs of Kappa coefficients for something like 30 raters.
>>>>>>>
>>>>>>> We generated a simple macro which basically gathered up all pairs in
>>>>>>> a sequence
>>>>>>> j1 x j2..j30, j2 x j3..j30, .....j29 x j30.
>>>>>>>
>>>>>>> It occured to me that the resulting OMS output lacks the identifying
>>>>>>> information for which pairs of raters contributed a given Kappa
>>>>>>> coefficient.
>>>>>>>
>>>>>>> Riddle me this,  Given variables j1 ...j30 and a file containing the
>>>>>>> results in the above sequence, how best to append the contributing
>>>>>>> variable names to the coefficients for further analysis?
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>> -----
>>>>>>> Please reply to the list and not to my personal email.
>>>>>>> Those desiring my consulting or training services please feel free
>>>>>>> to email me.
>>>>>>> ---
>>>>>>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>>>>>>> porcos ne forte conculcent eas pedibus suis."
>>>>>>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum
>>>>>>> cliff in abyssum?"
>>>>>>> --
>>>>>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>>>>>
>>>>>>> =====================
>>>>>>> To manage your subscription to SPSSX-L, send a message to
>>>>>>
>>>>>>> LISTSERV@.UGA
>>>>>>
>>>>>>>  (not to SPSSX-L), with no body text except the command. To leave
>>>>>>> the list, send the command SIGNOFF SPSSX-L For a list of commands to
>>>>>>> manage subscriptions, send the command INFO REFCARD
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>> -----
>>>>>> --
>>>>>> Bruce Weaver
>>>>>
>>>>>> bweaver@
>>>>>
>>>>>> http://sites.google.com/a/lakeheadu.ca/bweaver/
>>>>>>
>>>>>> "When all else fails, RTFM."
>>>>>>
>>>>>> NOTE: My Hotmail account is not monitored regularly.
>>>>>> To send me an e-mail, please use the address shown above.
>>>>>>
>>>>>> --
>>>>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>>>>
>>>>>> =====================
>>>>>> To manage your subscription to SPSSX-L, send a message to
>>>>>
>>>>>> LISTSERV@.UGA
>>>>>
>>>>>>  (not to SPSSX-L), with no body text except the command. To leave the
>>>>>> list, send the command SIGNOFF SPSSX-L For a list of commands to
>>>>>> manage subscriptions, send the command INFO REFCARD
>>>>>
>>>>>
>>>>>
>>>>>
>>>>>
>>>>> -----
>>>>> Please reply to the list and not to my personal email.
>>>>> Those desiring my consulting or training services please feel free to
>>>>> email me.
>>>>> ---
>>>>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>>>>> porcos ne forte conculcent eas pedibus suis."
>>>>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum
>>>>> cliff in abyssum?"
>>>>> --
>>>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>>>
>>>>> =====================
>>>>> To manage your subscription to SPSSX-L, send a message to
>>>>
>>>>> LISTSERV@.UGA
>>>>
>>>>>  (not to SPSSX-L), with no body text except the command. To leave the
>>>>> list, send the command SIGNOFF SPSSX-L For a list of commands to
>>>>> manage subscriptions, send the command INFO REFCARD
>>>>
>>>>
>>>>
>>>>
>>>>
>>>> -----
>>>> --
>>>> Bruce Weaver
>>>
>>>> bweaver@
>>>
>>>> http://sites.google.com/a/lakeheadu.ca/bweaver/
>>>>
>>>> "When all else fails, RTFM."
>>>>
>>>> NOTE: My Hotmail account is not monitored regularly.
>>>> To send me an e-mail, please use the address shown above.
>>>>
>>>> --
>>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>>
>>>> =====================
>>>> To manage your subscription to SPSSX-L, send a message to
>>>
>>>> LISTSERV@.UGA
>>>
>>>>  (not to SPSSX-L), with no body text except the command. To leave the
>>>> list, send the command SIGNOFF SPSSX-L For a list of commands to manage
>>>> subscriptions, send the command INFO REFCARD
>>>>
>>>> =====================
>>>> To manage your subscription to SPSSX-L, send a message to
>>>
>>>> LISTSERV@.UGA
>>>
>>>>  (not to SPSSX-L), with no body text except the
>>>> command. To leave the list, send the command
>>>> SIGNOFF SPSSX-L
>>>> For a list of commands to manage subscriptions, send the command
>>>> INFO REFCARD
>>>
>>>
>>>
>>>
>>>
>>> -----
>>> Please reply to the list and not to my personal email.
>>> Those desiring my consulting or training services please feel free to
>>> email me.
>>> ---
>>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>>> porcos
>>> ne forte conculcent eas pedibus suis."
>>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff
>>> in
>>> abyssum?"
>>> --
>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>
>>> =====================
>>> To manage your subscription to SPSSX-L, send a message to
>>
>>> LISTSERV@.UGA
>>
>>>  (not to SPSSX-L), with no body text except the
>>> command. To leave the list, send the command
>>> SIGNOFF SPSSX-L
>>> For a list of commands to manage subscriptions, send the command
>>> INFO REFCARD
>>
>>
>>
>>
>>
>> -----
>> --
>> Bruce Weaver
>
>> bweaver@
>
>> http://sites.google.com/a/lakeheadu.ca/bweaver/
>>
>> "When all else fails, RTFM."
>>
>> NOTE: My Hotmail account is not monitored regularly.
>> To send me an e-mail, please use the address shown above.
>>
>> --
>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>
>> LISTSERV@.UGA
>
>>  (not to SPSSX-L), with no body text except the
>> command. To leave the list, send the command
>> SIGNOFF SPSSX-L
>> For a list of commands to manage subscriptions, send the command
>> INFO REFCARD
>
>
>
>
>
> -----
> Please reply to the list and not to my personal email.
> Those desiring my consulting or training services please feel free to
> email me.
> ---
> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos
> ne forte conculcent eas pedibus suis."
> Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in
> abyssum?"
> --
> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>
> =====================
> To manage your subscription to SPSSX-L, send a message to

> LISTSERV@.UGA

>  (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD





-----
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
Reply | Threaded
Open this post in threaded view
|

Re: A data mapping riddle.

David Marso
Administrator
Without MATRIX... Pseudo code as I am not on SPSS box.

VARSTOCASES.
AGGREGATE> count
CASESTOVARS.
VECTOR
Nested LOOP with XSAVE see Bruce's code or MATRIX guts.
EXECUTE.
GET FILE
done

Another MATRIX solution uses CARTESIAN product.  Search on KRONEKER
Then select if jx < jy..
Interesting that it works with strings.
 I guess X * 1= X irregardless...🐒



David Marso wrote

> Using VARSTOCASES with an index can get the variable names into a column.
> You can then use CASESTOVARS to get them into a vector but getting the
> length in order to loop and write the pairs is difficult.
>
> This is what I came up with and can't think of a way to do it without
> MATRIX.
> Any other thoughts?
>
> One can easily match the 'Pairs' file to the file containing the Kappas
> created by CROSSTABS /OMS .
>
>
> DEFINE !DataSimulation (!POS !CHAREND("=")
>                       / !POS !CHAREND("(")
>                       / !POS !CHAREND(",")
>                       / !POS !CHAREND(",")
>                       / !POS !CHAREND(")")
>                       / !POS !CMDEND  )
>
> MATRIX.
> SAVE TRUNC(!2(!3,!4)*!5+1) / OUTFILE= * /VARIABLES !1 .
> END MATRIX.
> DATASET NAME !6.
> !ENDDEFINE.
>
> DEFINE !PairNames ( !POS !CHAREND (">") / !POS !CMDEND)
> PRESERVE.
> /* ProgMans contribution to allow writing to a dataset without Admin priv
> */
> .
> CD '%userprofile%\Desktop' .
>
> DATASET DECLARE !2.
> MATRIX.
> +  GET Data /FILE * /VARIABLES !1 /NAMES=names.
> +  LOOP I=1 TO NCOL(names)  - 1.
> +    LOOP J=I+1 TO NCOL(names) .
> +      SAVE {names(I),names(J)} /OUTFILE  !2 /VARIABLES Jx Jy /STRING Jx
> Jy.
> +    END LOOP.
> +  END LOOP.
> END MATRIX.
> DATASET ACTIVATE   !2.
> RESTORE.
> !ENDDEFINE.
> !DataSimulation j1 TO j30=UNIFORM(200,30,4) raw.
> !PairNames j1 TO j30 > Pairs.
>
>
>
> David Marso wrote
>> Ok three ways to get varnames into a manipulable form.
>> Yes, VARSTOCASES could be a first step.
>> Bonus points if you don't explicitly write a file to disk.
>> ---
>>
>> Bruce Weaver wrote
>>> I don't have SPSS on this machine, but are you thinking of VARSTOCASES
>>> with a
>>> variable name index?  
>>>
>>>
>>>
>>> David Marso wrote
>>>> I am actually looking for another pair of variables in each row
>>>> containing
>>>> the variable name for the contributing variable/rater.  Think of how
>>>> one
>>>> can
>>>> get a variable name into a manipulable form in a system file [two ways
>>>> come
>>>> to mind].
>>>>
>>>> jX jY Kappa XY
>>>> -------------------
>>>> j1 j2 Kappa_1_2
>>>> j1 j3 Kappa_1_3
>>>> ....
>>>> j29 j30 Kappa_29_30
>>>>
>>>> Preferred solution does not require knowing the number of raters.
>>>>
>>>>
>>>> Maguin, Eugene wrote
>>>>> When I saw David's riddle, I thought about what you did but I came
>>>>> away
>>>>> thinking that David might actually have in mind making the rater pair
>>>>> be
>>>>> the variable label for that particular variable. My no very informed
>>>>> impression is that this cannot be done in syntax. Could I be wrong?
>>>>> Gene Maguin
>>>>>
>>>>> -----Original Message-----
>>>>> From: SPSSX(r) Discussion [mailto:
>>>>
>>>>> SPSSX-L@.UGA
>>>>
>>>>> ] On Behalf Of Bruce Weaver
>>>>> Sent: Thursday, February 8, 2018 3:05 PM
>>>>> To:
>>>>
>>>>> SPSSX-L@.UGA
>>>>
>>>>> Subject: Re: A data mapping riddle.
>>>>>
>>>>> So you're just looking to indicate which pair of judges it is for each
>>>>> row?
>>>>> How about this?
>>>>>
>>>>> DATASET ACTIVATE Kappa.
>>>>> NUMERIC J1 J2 (F2.0).
>>>>> COMPUTE #case = 0.
>>>>> LOOP # = 1 to 29.
>>>>>  LOOP ## = #+1 to 30.
>>>>>   COMPUTE #case = #case+1.
>>>>>   DO IF $CASENUM EQ #case.
>>>>>    COMPUTE J1 = #.
>>>>>    COMPUTE J2 = ##.
>>>>>   END IF.
>>>>>  END LOOP.
>>>>> END LOOP.
>>>>> CROSSTABS J1 by J2.
>>>>>
>>>>>
>>>>>
>>>>> David Marso wrote
>>>>>> Indeed I am.  Thanks for adding the link.  I should have included
>>>>>> that
>>>>>> in my post.
>>>>>>
>>>>>>
>>>>>> Bruce Weaver wrote
>>>>>>> David, are you talking about the Kappa output from this macro?
>>>>>>>
>>>>>>> http://spssx-discussion.1045642.n5.nabble.com/interrater-reliabillity
>>>>>>> -but-for-any-pair-of-raters-td5735428.html#a5735437
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>> David Marso wrote
>>>>>>>> I have a solution which is really neat and tidy but wanted to see
>>>>>>>> how others approach the following type of situation.
>>>>>>>>  Recall a few weeks ago a user posed the question of getting all
>>>>>>>> possible pairs of Kappa coefficients for something like 30 raters.
>>>>>>>>
>>>>>>>> We generated a simple macro which basically gathered up all pairs
>>>>>>>> in
>>>>>>>> a sequence
>>>>>>>> j1 x j2..j30, j2 x j3..j30, .....j29 x j30.
>>>>>>>>
>>>>>>>> It occured to me that the resulting OMS output lacks the
>>>>>>>> identifying
>>>>>>>> information for which pairs of raters contributed a given Kappa
>>>>>>>> coefficient.
>>>>>>>>
>>>>>>>> Riddle me this,  Given variables j1 ...j30 and a file containing
>>>>>>>> the
>>>>>>>> results in the above sequence, how best to append the contributing
>>>>>>>> variable names to the coefficients for further analysis?
>>>>>>>>
>>>>>>>>
>>>>>>>>
>>>>>>>> -----
>>>>>>>> Please reply to the list and not to my personal email.
>>>>>>>> Those desiring my consulting or training services please feel free
>>>>>>>> to email me.
>>>>>>>> ---
>>>>>>>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>>>>>>>> porcos ne forte conculcent eas pedibus suis."
>>>>>>>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum
>>>>>>>> cliff in abyssum?"
>>>>>>>> --
>>>>>>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>>>>>>
>>>>>>>> =====================
>>>>>>>> To manage your subscription to SPSSX-L, send a message to
>>>>>>>
>>>>>>>> LISTSERV@.UGA
>>>>>>>
>>>>>>>>  (not to SPSSX-L), with no body text except the command. To leave
>>>>>>>> the list, send the command SIGNOFF SPSSX-L For a list of commands
>>>>>>>> to
>>>>>>>> manage subscriptions, send the command INFO REFCARD
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>> -----
>>>>>>> --
>>>>>>> Bruce Weaver
>>>>>>
>>>>>>> bweaver@
>>>>>>
>>>>>>> http://sites.google.com/a/lakeheadu.ca/bweaver/
>>>>>>>
>>>>>>> "When all else fails, RTFM."
>>>>>>>
>>>>>>> NOTE: My Hotmail account is not monitored regularly.
>>>>>>> To send me an e-mail, please use the address shown above.
>>>>>>>
>>>>>>> --
>>>>>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>>>>>
>>>>>>> =====================
>>>>>>> To manage your subscription to SPSSX-L, send a message to
>>>>>>
>>>>>>> LISTSERV@.UGA
>>>>>>
>>>>>>>  (not to SPSSX-L), with no body text except the command. To leave
>>>>>>> the
>>>>>>> list, send the command SIGNOFF SPSSX-L For a list of commands to
>>>>>>> manage subscriptions, send the command INFO REFCARD
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>> -----
>>>>>> Please reply to the list and not to my personal email.
>>>>>> Those desiring my consulting or training services please feel free to
>>>>>> email me.
>>>>>> ---
>>>>>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>>>>>> porcos ne forte conculcent eas pedibus suis."
>>>>>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum
>>>>>> cliff in abyssum?"
>>>>>> --
>>>>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>>>>
>>>>>> =====================
>>>>>> To manage your subscription to SPSSX-L, send a message to
>>>>>
>>>>>> LISTSERV@.UGA
>>>>>
>>>>>>  (not to SPSSX-L), with no body text except the command. To leave the
>>>>>> list, send the command SIGNOFF SPSSX-L For a list of commands to
>>>>>> manage subscriptions, send the command INFO REFCARD
>>>>>
>>>>>
>>>>>
>>>>>
>>>>>
>>>>> -----
>>>>> --
>>>>> Bruce Weaver
>>>>
>>>>> bweaver@
>>>>
>>>>> http://sites.google.com/a/lakeheadu.ca/bweaver/
>>>>>
>>>>> "When all else fails, RTFM."
>>>>>
>>>>> NOTE: My Hotmail account is not monitored regularly.
>>>>> To send me an e-mail, please use the address shown above.
>>>>>
>>>>> --
>>>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>>>
>>>>> =====================
>>>>> To manage your subscription to SPSSX-L, send a message to
>>>>
>>>>> LISTSERV@.UGA
>>>>
>>>>>  (not to SPSSX-L), with no body text except the command. To leave the
>>>>> list, send the command SIGNOFF SPSSX-L For a list of commands to
>>>>> manage
>>>>> subscriptions, send the command INFO REFCARD
>>>>>
>>>>> =====================
>>>>> To manage your subscription to SPSSX-L, send a message to
>>>>
>>>>> LISTSERV@.UGA
>>>>
>>>>>  (not to SPSSX-L), with no body text except the
>>>>> command. To leave the list, send the command
>>>>> SIGNOFF SPSSX-L
>>>>> For a list of commands to manage subscriptions, send the command
>>>>> INFO REFCARD
>>>>
>>>>
>>>>
>>>>
>>>>
>>>> -----
>>>> Please reply to the list and not to my personal email.
>>>> Those desiring my consulting or training services please feel free to
>>>> email me.
>>>> ---
>>>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>>>> porcos
>>>> ne forte conculcent eas pedibus suis."
>>>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff
>>>> in
>>>> abyssum?"
>>>> --
>>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>>
>>>> =====================
>>>> To manage your subscription to SPSSX-L, send a message to
>>>
>>>> LISTSERV@.UGA
>>>
>>>>  (not to SPSSX-L), with no body text except the
>>>> command. To leave the list, send the command
>>>> SIGNOFF SPSSX-L
>>>> For a list of commands to manage subscriptions, send the command
>>>> INFO REFCARD
>>>
>>>
>>>
>>>
>>>
>>> -----
>>> --
>>> Bruce Weaver
>>
>>> bweaver@
>>
>>> http://sites.google.com/a/lakeheadu.ca/bweaver/
>>>
>>> "When all else fails, RTFM."
>>>
>>> NOTE: My Hotmail account is not monitored regularly.
>>> To send me an e-mail, please use the address shown above.
>>>
>>> --
>>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>>
>>> =====================
>>> To manage your subscription to SPSSX-L, send a message to
>>
>>> LISTSERV@.UGA
>>
>>>  (not to SPSSX-L), with no body text except the
>>> command. To leave the list, send the command
>>> SIGNOFF SPSSX-L
>>> For a list of commands to manage subscriptions, send the command
>>> INFO REFCARD
>>
>>
>>
>>
>>
>> -----
>> Please reply to the list and not to my personal email.
>> Those desiring my consulting or training services please feel free to
>> email me.
>> ---
>> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante
>> porcos
>> ne forte conculcent eas pedibus suis."
>> Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff
>> in
>> abyssum?"
>> --
>> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>
>> LISTSERV@.UGA
>
>>  (not to SPSSX-L), with no body text except the
>> command. To leave the list, send the command
>> SIGNOFF SPSSX-L
>> For a list of commands to manage subscriptions, send the command
>> INFO REFCARD
>
>
>
>
>
> -----
> Please reply to the list and not to my personal email.
> Those desiring my consulting or training services please feel free to
> email me.
> ---
> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos
> ne forte conculcent eas pedibus suis."
> Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in
> abyssum?"
> --
> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>
> =====================
> To manage your subscription to SPSSX-L, send a message to

> LISTSERV@.UGA

>  (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD





-----
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"