Hi Charles
Split your dataset into 2 groups:
1. 25% early responses
2. 25% late responses (this shall be a proxy for non-responses)
Run independent-sample t-test on variables of interest. If tgere's no significant difference, then non-response bias is not a concern in your study.
Alternatively, if your responses were received in waves, e.g., wave 1 (received before any reminder being sent) and wave 3 (responses received after 2nd reminder was sent, use this group as a proxy for nonresponses).
Use Mann Whitney U test instead of t-test if your data is nkt normally distributed.
The methodology section in the following section can be helpful. Vote up my answer if you find it useful. Thanks.
http://ro.ecu.edu.au/theses/1640
good luck.
cheers
saiyidi
You need to have at least some information about the non-respondents in in order to compare them to the people who did participate.
Hi Charles
Split your dataset into 2 groups:
1. 25% early responses
2. 25% late responses (this shall be a proxy for non-responses)
Run independent-sample t-test on variables of interest. If tgere's no significant difference, then non-response bias is not a concern in your study.
Alternatively, if your responses were received in waves, e.g., wave 1 (received before any reminder being sent) and wave 3 (responses received after 2nd reminder was sent, use this group as a proxy for nonresponses).
Use Mann Whitney U test instead of t-test if your data is nkt normally distributed.
The methodology section in the following section can be helpful. Vote up my answer if you find it useful. Thanks.
http://ro.ecu.edu.au/theses/1640
good luck.
cheers
saiyidi
Another audience to ask SPSS question is the official SPSS discussion group.
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS