Wrong sum scores

Moderators: statman, Analyst Techy, andris, Fierce, GerineL, Smash

Posts: 1
Joined: Fri Jun 12, 2015 5:51 am

Wrong sum scores

Postby Laurenszzz » Fri Jun 12, 2015 5:58 am


In my survey I had the option to fill in N/A. In my spss file I had labeled that option with 5, the highest label (the answers were on a likert scale). So that makes my sum score higher than it should be. Therefore I have recoded everything but now my sum scores are incorrect. Is there anyway to fix this problem or to leave out all the N/A answers in the analyses without reducing the amount of respondents.

I hope anyone can help me :)
Posts: 1477
Joined: Tue Jun 10, 2008 4:50 pm

Re: Wrong sum scores

Postby GerineL » Fri Jun 12, 2015 8:16 am

what do you mean when you say your sumscores are "incorrect"? I.e., give a concrete example of what happens now and what you want to happen.

A few tips:
1. you can recode quite easily via syntax, e.g.:

Code: Select all

recode var1 var2 var3 var4 (5 = 999).
[recodes 5 into 999 for variables var1 var2 var3]

2. you can identify which numbers spss should treat as "missing" and therefore not include in computations.

Code: Select all

MISSING VALUES var1 var2 var3 (5).
[identifies 5 as a missing value for variables var1 var2 var3]

3. if you have missing values, you can compute the mean

Code: Select all

compute varmean = mean(var1,var2,var3). 
or the mean * number of items to get something similar to sum score.

Code: Select all

compute varmean = mean(var1,var2,var3) *3. 

Who is online

Users browsing this forum: No registered users and 3 guests