Welcome, Guest
Username: Password: Remember me

TOPIC: SPSS export and meaning of NA?

SPSS export and meaning of NA? 3 years 3 months ago #62690

  • blocka
  • blocka's Avatar
  • OFFLINE
  • Fresh Lemon
  • Posts: 17
  • Karma: 0
In an SPSS file - does 'N/A' mean 'not applicable' or 'no answer'?
The administrator has disabled public write access.

Re: SPSS export and meaning of NA? 3 years 3 months ago #62696

  • holch
  • holch's Avatar
  • OFFLINE
  • LimeSurvey Team
  • Posts: 2852
  • Thank you received: 359
  • Karma: 124
I just wanted to ask "does it matter", but depending on your study, it does. I would guess that it stands for those parts that were not applicable, while no answer would create an empty field, but this is only guessing...
Have a look at the manual! It is a really valuable source for information. Here some helpful links:
Manual (EN) | Question Types | Question Attributes | Workarounds

If you found this answer helpful and it saved you some time please consider a donation to the project to keep Limesurvey going!
The administrator has disabled public write access.

Re: SPSS export and meaning of NA? 3 years 3 months ago #62701

  • tpartner
  • tpartner's Avatar
  • OFFLINE
  • LimeSurvey Team
  • Posts: 4277
  • Thank you received: 807
  • Karma: 370
I would guess that it stands for those parts that were not applicable, while no answer would create an empty field
Yes, I would also assume that a "no answer" would result in an ampty field. But perhaps our SPSS wizard, Menno, can give us a definitive answer.
Cheers,
Tony Partner

Solutions, code and workarounds presented in these forums are given without any warranty, implied or otherwise.

LimeSurvey is open-source and run entirely by volunteers so please consider donating to support the project.
The administrator has disabled public write access.

Re: SPSS export and meaning of NA? 3 years 3 months ago #62743

  • blocka
  • blocka's Avatar
  • OFFLINE
  • Fresh Lemon
  • Posts: 17
  • Karma: 0
So, could one assume that the blank circled cell in this table reflects people who did not respond to the question?

2011-06-28_09-47.jpg
The administrator has disabled public write access.

Re: SPSS export and meaning of NA? 3 years 3 months ago #62744

  • tpartner
  • tpartner's Avatar
  • OFFLINE
  • LimeSurvey Team
  • Posts: 4277
  • Thank you received: 807
  • Karma: 370
I think that's a valid assumption.
Cheers,
Tony Partner

Solutions, code and workarounds presented in these forums are given without any warranty, implied or otherwise.

LimeSurvey is open-source and run entirely by volunteers so please consider donating to support the project.
The administrator has disabled public write access.

Re: SPSS export and meaning of NA? 3 years 3 months ago #62746

  • TMSWhite
  • TMSWhite's Avatar
  • OFFLINE
  • LimeSurvey Team
  • Posts: 759
  • Thank you received: 82
  • Karma: 36
Are users looking for greater control over types of missing values?

My epidemiology colleagues tend to use 3 different types of missing values in their surveys:
(1) Not Applicable
(2) Unknown
(3) Refused

Any of those could result in a "null" value, so we'd often code them as 7777, 8888, and 9999, respectively, then tell SPSS that those are special missing values.

Later, we created special data values for each of those missing types so that (a) We could profile results according to the different types of missing values, (b) we could do path-based analysis - e.g. if they go down one path, then backtrack and go down another, we could detect fields than changed from applicable to not applicable or vice-versa, (c) the system would create the proper SPSS code for missing values, (d) different special values could be used for numbers vs. dates vs. text, and (e)we didn't have to worry as much about having a user enter one of those special "missing" values in a free-text field.

Has there been any demand for such functionality?
The administrator has disabled public write access.

Re: SPSS export and meaning of NA? 3 years 3 months ago #62750

  • holch
  • holch's Avatar
  • OFFLINE
  • LimeSurvey Team
  • Posts: 2852
  • Thank you received: 359
  • Karma: 124
I think this is very useful.

Because a missing value can have many reasons and it is different if something is "not applicable" or it was just not answered.

No I assume that 2 and 3 were answer options (where you can easily give an value to it), but but what about 1, how did you include this into the data base?

I would already be happy when it would easy to figure out if there is no answer because the person did not see this question or because the person did not answer anything (non mandatory questions).
Have a look at the manual! It is a really valuable source for information. Here some helpful links:
Manual (EN) | Question Types | Question Attributes | Workarounds

If you found this answer helpful and it saved you some time please consider a donation to the project to keep Limesurvey going!
The administrator has disabled public write access.

Re: SPSS export and meaning of NA? 3 years 3 months ago #62754

  • TMSWhite
  • TMSWhite's Avatar
  • OFFLINE
  • LimeSurvey Team
  • Posts: 759
  • Thank you received: 82
  • Karma: 36
We also had one column per variable, but we created a special value to store for Not Applicable (I believe we used something like "****NA****").

The ExpressionManager would process the Relevance equation to determine whether the question was applicable or not. For questions that aren't relevant, that ****NA**** response was stored in the database.

This would be equivalent to writing ****NA**** for each "hidden" field.

The only down-side to this approach is that it intentionally deletes values for anything that is not applicable. My goal with that was that if it truly not applicable, it would be confusing to the analysts to have a value in the field.

That may not be the desired behavior for LimeSurvey, however.
The administrator has disabled public write access.
Moderators: ITEd
Time to create page: 0.130 seconds
Donation Image