Comparing missing and non-missing subjects for dependent variables

[johnstatistic]

Hello everyone. I am working with a data-set of a cohort study which has 3 different sets of paired data. For the third visit of the subjects, we have a lot of missing. So, I need to compare the basic characteristics (in the first and second visit) of the missing and non-missing subjects for my outcome in the third visit. How can I do that in spss? For example, I want to have the mean difference between missing and non-missing subjects for my dependent variable for the variable "age".Thanks in advance.

 

[Berley]

I'm not clear on what you are trying to do, but my best guess is that you are looking to calculate a new variable. That's on the transform menu.

 

[johnstatistic]

no, I do not want to compute a new variable. I want to compare my subjects who are being tested again and who are not being tested again in terms of their basic characteristics in longitudinal study in order to know whether there is a meaningful difference between them or not. It is like to see if there is a significant mean difference between the baseline age of those who were re-tested and those who were not re-tested. By the way, thank you for your help.

 

[Berley]

Right -- but you asked about missing data.

For example, I want to have the mean difference between missing and non-missing subjects for my dependent variable for the variable "age".

In order to do that, you need to calculate a new variable called "age" that is the mean difference between missing and non-missing subjects.

Or are you instead wanting to compare something along the lines of:
Group A has data for all three rounds -- call them non-missing subjects.
Group B has data for rounds 1 and 2 but 3 is missing -- call them missing subjects.
What is the difference/Is there a difference for the existing variable "age" between Group A and Group B?