Re: SPSS and Mode Averages - mea culpa

[Lemon, John S.]

Dear all

 

Mae Culpa and apologies for cluttering up the list with a silly question – I have now managed to persuade the user / research to part with his data file and have looked at it more closely. It is one that has been created by another programme and the survey had a number of questions like this in it:

q15 How many of your journal publications have been made available online ?

(With a tick box to select the appropriate number, which translated into the values and labels below, so means and any other statistics are based on the code values not on the figure that was presented in the survey.)

               Value     Label

               1              0 ( None )

               2              1

               3              2

               4              3

               5              4

               6              5

               7              6

               8              7

               9              8

               10           9

               11           10

               12           10+

Thus the value stored is 1 but the respondent meant 0 – the user is creating new variables with “COMPUTE Q15x = Q15 – 1” and doing the statistics on that – luckily nobody has responded in the 10+ category !!

 

Again I apologise but it does mean I’ll insist on seeing the data file before I ask questions of the list.

 

Best Wishes

 

John S. Lemon

IT Services - Student Liaison Officer

University of Aberdeen

Edward Wright Building

Tel:  [phone]

 

IT news for Students

 

The University of Aberdeen is a charity registered in Scotland, No SC013683.

[David Marso]

Yeah John (no worries),
  One of the first things I learned when I was doing teksport (circa 1990 -you and I have talked on the phone-) is that users lie (not necessarily with malice)!
They may not even realize it but when the data/syntax/whatever finally materialize it becomes clear.
One of my favorites is the unterminated comment before a SELECT IF or other command which results in 'unexpected behavior'
** The following separates the wheat from the chaff
SELECT IF (material EQ wheat).
freq material.

Lemon, John S. wrote

Dear all

Mae Culpa and apologies for cluttering up the list with a silly question - I have now managed to persuade the user / research to part with his data file and have looked at it more closely. It is one that has been created by another programme and the survey had a number of questions like this in it:
q15 How many of your journal publications have been made available online ?
(With a tick box to select the appropriate number, which translated into the values and labels below, so means and any other statistics are based on the code values not on the figure that was presented in the survey.)
               Value     Label
               1              0 ( None )
               2              1
               3              2
               4              3
               5              4
               6              5
               7              6
               8              7
               9              8
               10           9
               11           10
               12           10+
Thus the value stored is 1 but the respondent meant 0 - the user is creating new variables with "COMPUTE Q15x = Q15 - 1" and doing the statistics on that - luckily nobody has responded in the 10+ category !!

Again I apologise but it does mean I'll insist on seeing the data file before I ask questions of the list.

Best Wishes

John S. Lemon
IT Services<http://www.abdn.ac.uk/dit/> - Student Liaison Officer<http://www.abdn.ac.uk/dit/slo/>
University of Aberdeen<http://www.abdn.ac.uk/>
Edward Wright Building<http://www.abdn.ac.uk/maps/generic-details-2526.php>
Tel:  [phone]

IT news for Students<http://www.abdn.ac.uk/dit/student/news/>





The University of Aberdeen is a charity registered in Scotland, No SC013683.

[Alex Reutter]

Hi John,

FYI, there's an Output setting that produces both the values and the value labels in the pivot table output.  Edit > Options, Output tab.  By default the output just shows labels (if available), but if the user sent output that showed the values and labels, you would have immediately seen what the issue was.  (Better yet, the user's values and labels would be more in sync, but...)

Alex


Lemon, John S. wrote
> Dear all
>
> Mae Culpa and apologies for cluttering up the list with a silly question -
> I have now managed to persuade the user / research to part with his data
> file and have looked at it more closely. It is one that has been created
> by another programme and the survey had a number of questions like this in
> it:
> q15 How many of your journal publications have been made available online
> ?
> (With a tick box to select the appropriate number, which translated into
> the values and labels below, so means and any other statistics are based
> on the code values not on the figure that was presented in the survey.)
>                Value     Label
>                1              0 ( None )
>                2              1
>                3              2
>                4              3
>                5              4
>                6              5
>                7              6
>                8              7
>                9              8
>                10           9
>                11           10
>                12           10+
> Thus the value stored is 1 but the respondent meant 0 - the user is
> creating new variables with "COMPUTE Q15x = Q15 - 1" and doing the
> statistics on that - luckily nobody has responded in the 10+ category !!
>
> Again I apologise but it does mean I'll insist on seeing the data file
> before I ask questions of the list.
>
> Best Wishes
>
> John S. Lemon